| Current File : /home/mmdealscpanel/yummmdeals.com/urllib.zip |
PK (�Z __init__.pynu �[��� PK (�Z�%��$ �$ robotparser.pynu �[��� """ robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://www.robotstxt.org/norobots-rfc.txt
"""
import collections
import urllib.parse
import urllib.request
__all__ = ["RobotFileParser"]
RequestRate = collections.namedtuple("RequestRate", "requests seconds")
class RobotFileParser:
""" This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
"""
def __init__(self, url=''):
self.entries = []
self.sitemaps = []
self.default_entry = None
self.disallow_all = False
self.allow_all = False
self.set_url(url)
self.last_checked = 0
def mtime(self):
"""Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
"""
return self.last_checked
def modified(self):
"""Sets the time the robots.txt file was last fetched to the
current time.
"""
import time
self.last_checked = time.time()
def set_url(self, url):
"""Sets the URL referring to a robots.txt file."""
self.url = url
self.host, self.path = urllib.parse.urlparse(url)[1:3]
def read(self):
"""Reads the robots.txt URL and feeds it to the parser."""
try:
f = urllib.request.urlopen(self.url)
except urllib.error.HTTPError as err:
if err.code in (401, 403):
self.disallow_all = True
elif err.code >= 400 and err.code < 500:
self.allow_all = True
else:
raw = f.read()
self.parse(raw.decode("utf-8").splitlines())
def _add_entry(self, entry):
if "*" in entry.useragents:
# the default entry is considered last
if self.default_entry is None:
# the first default entry wins
self.default_entry = entry
else:
self.entries.append(entry)
def parse(self, lines):
"""Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
"""
# states:
# 0: start state
# 1: saw user-agent line
# 2: saw an allow or disallow line
state = 0
entry = Entry()
self.modified()
for line in lines:
if not line:
if state == 1:
entry = Entry()
state = 0
elif state == 2:
self._add_entry(entry)
entry = Entry()
state = 0
# remove optional comment and strip line
i = line.find('#')
if i >= 0:
line = line[:i]
line = line.strip()
if not line:
continue
line = line.split(':', 1)
if len(line) == 2:
line[0] = line[0].strip().lower()
line[1] = urllib.parse.unquote(line[1].strip())
if line[0] == "user-agent":
if state == 2:
self._add_entry(entry)
entry = Entry()
entry.useragents.append(line[1])
state = 1
elif line[0] == "disallow":
if state != 0:
entry.rulelines.append(RuleLine(line[1], False))
state = 2
elif line[0] == "allow":
if state != 0:
entry.rulelines.append(RuleLine(line[1], True))
state = 2
elif line[0] == "crawl-delay":
if state != 0:
# before trying to convert to int we need to make
# sure that robots.txt has valid syntax otherwise
# it will crash
if line[1].strip().isdigit():
entry.delay = int(line[1])
state = 2
elif line[0] == "request-rate":
if state != 0:
numbers = line[1].split('/')
# check if all values are sane
if (len(numbers) == 2 and numbers[0].strip().isdigit()
and numbers[1].strip().isdigit()):
entry.req_rate = RequestRate(int(numbers[0]), int(numbers[1]))
state = 2
elif line[0] == "sitemap":
# According to http://www.sitemaps.org/protocol.html
# "This directive is independent of the user-agent line,
# so it doesn't matter where you place it in your file."
# Therefore we do not change the state of the parser.
self.sitemaps.append(line[1])
if state == 2:
self._add_entry(entry)
def can_fetch(self, useragent, url):
"""using the parsed robots.txt decide if useragent can fetch url"""
if self.disallow_all:
return False
if self.allow_all:
return True
# Until the robots.txt file has been read or found not
# to exist, we must assume that no url is allowable.
# This prevents false positives when a user erroneously
# calls can_fetch() before calling read().
if not self.last_checked:
return False
# search for given user agent matches
# the first match counts
parsed_url = urllib.parse.urlparse(urllib.parse.unquote(url))
url = urllib.parse.urlunparse(('','',parsed_url.path,
parsed_url.params,parsed_url.query, parsed_url.fragment))
url = urllib.parse.quote(url)
if not url:
url = "/"
for entry in self.entries:
if entry.applies_to(useragent):
return entry.allowance(url)
# try the default entry last
if self.default_entry:
return self.default_entry.allowance(url)
# agent not found ==> access granted
return True
def crawl_delay(self, useragent):
if not self.mtime():
return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.delay
if self.default_entry:
return self.default_entry.delay
return None
def request_rate(self, useragent):
if not self.mtime():
return None
for entry in self.entries:
if entry.applies_to(useragent):
return entry.req_rate
if self.default_entry:
return self.default_entry.req_rate
return None
def site_maps(self):
if not self.sitemaps:
return None
return self.sitemaps
def __str__(self):
entries = self.entries
if self.default_entry is not None:
entries = entries + [self.default_entry]
return '\n\n'.join(map(str, entries))
class RuleLine:
"""A rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path."""
def __init__(self, path, allowance):
if path == '' and not allowance:
# an empty value means allow all
allowance = True
path = urllib.parse.urlunparse(urllib.parse.urlparse(path))
self.path = urllib.parse.quote(path)
self.allowance = allowance
def applies_to(self, filename):
return self.path == "*" or filename.startswith(self.path)
def __str__(self):
return ("Allow" if self.allowance else "Disallow") + ": " + self.path
class Entry:
"""An entry has one or more user-agents and zero or more rulelines"""
def __init__(self):
self.useragents = []
self.rulelines = []
self.delay = None
self.req_rate = None
def __str__(self):
ret = []
for agent in self.useragents:
ret.append(f"User-agent: {agent}")
if self.delay is not None:
ret.append(f"Crawl-delay: {self.delay}")
if self.req_rate is not None:
rate = self.req_rate
ret.append(f"Request-rate: {rate.requests}/{rate.seconds}")
ret.extend(map(str, self.rulelines))
return '\n'.join(ret)
def applies_to(self, useragent):
"""check if this entry applies to the specified agent"""
# split the name token and make it lower case
useragent = useragent.split("/")[0].lower()
for agent in self.useragents:
if agent == '*':
# we have the catch-all agent
return True
agent = agent.lower()
if agent in useragent:
return True
return False
def allowance(self, filename):
"""Preconditions:
- our agent applies to this entry
- filename is URL decoded"""
for line in self.rulelines:
if line.applies_to(filename):
return line.allowance
return True
PK (�Z����� �� parse.pynu �[��� """Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
"""
import re
import os
import sys
import collections
import warnings
__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
"urlsplit", "urlunsplit", "urlencode", "parse_qs",
"parse_qsl", "quote", "quote_plus", "quote_from_bytes",
"unquote", "unquote_plus", "unquote_to_bytes",
"DefragResult", "ParseResult", "SplitResult",
"DefragResultBytes", "ParseResultBytes", "SplitResultBytes"]
# A classification of schemes.
# The empty string classifies URLs with no scheme specified,
# being the default value returned by “urlsplit” and “urlparse”.
uses_relative = ['', 'ftp', 'http', 'gopher', 'nntp', 'imap',
'wais', 'file', 'https', 'shttp', 'mms',
'prospero', 'rtsp', 'rtspu', 'sftp',
'svn', 'svn+ssh', 'ws', 'wss']
uses_netloc = ['', 'ftp', 'http', 'gopher', 'nntp', 'telnet',
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync',
'svn', 'svn+ssh', 'sftp', 'nfs', 'git', 'git+ssh',
'ws', 'wss']
uses_params = ['', 'ftp', 'hdl', 'prospero', 'http', 'imap',
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
'mms', 'sftp', 'tel']
# These are not actually used anymore, but should stay for backwards
# compatibility. (They are undocumented, but have a public-looking name.)
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
uses_query = ['', 'http', 'wais', 'imap', 'https', 'shttp', 'mms',
'gopher', 'rtsp', 'rtspu', 'sip', 'sips']
uses_fragment = ['', 'ftp', 'hdl', 'http', 'gopher', 'news',
'nntp', 'wais', 'https', 'shttp', 'snews',
'file', 'prospero']
# Characters valid in scheme names
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
'0123456789'
'+-.')
# Leading and trailing C0 control and space to be stripped per WHATWG spec.
# == "".join([chr(i) for i in range(0, 0x20 + 1)])
_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '
# Unsafe bytes to be removed per WHATWG spec
_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']
# XXX: Consider replacing with functools.lru_cache
MAX_CACHE_SIZE = 20
_parse_cache = {}
def clear_cache():
"""Clear the parse cache and the quoters cache."""
_parse_cache.clear()
_safe_quoters.clear()
# Helpers for bytes handling
# For 3.2, we deliberately require applications that
# handle improperly quoted URLs to do their own
# decoding and encoding. If valid use cases are
# presented, we may relax this by using latin-1
# decoding internally for 3.3
_implicit_encoding = 'ascii'
_implicit_errors = 'strict'
def _noop(obj):
return obj
def _encode_result(obj, encoding=_implicit_encoding,
errors=_implicit_errors):
return obj.encode(encoding, errors)
def _decode_args(args, encoding=_implicit_encoding,
errors=_implicit_errors):
return tuple(x.decode(encoding, errors) if x else '' for x in args)
def _coerce_args(*args):
# Invokes decode if necessary to create str args
# and returns the coerced inputs along with
# an appropriate result coercion function
# - noop for str inputs
# - encoding function otherwise
str_input = isinstance(args[0], str)
for arg in args[1:]:
# We special-case the empty string to support the
# "scheme=''" default argument to some functions
if arg and isinstance(arg, str) != str_input:
raise TypeError("Cannot mix str and non-str arguments")
if str_input:
return args + (_noop,)
return _decode_args(args) + (_encode_result,)
# Result objects are more helpful than simple tuples
class _ResultMixinStr(object):
"""Standard approach to encoding parsed results from str to bytes"""
__slots__ = ()
def encode(self, encoding='ascii', errors='strict'):
return self._encoded_counterpart(*(x.encode(encoding, errors) for x in self))
class _ResultMixinBytes(object):
"""Standard approach to decoding parsed results from bytes to str"""
__slots__ = ()
def decode(self, encoding='ascii', errors='strict'):
return self._decoded_counterpart(*(x.decode(encoding, errors) for x in self))
class _NetlocResultMixinBase(object):
"""Shared methods for the parsed result objects containing a netloc element"""
__slots__ = ()
@property
def username(self):
return self._userinfo[0]
@property
def password(self):
return self._userinfo[1]
@property
def hostname(self):
hostname = self._hostinfo[0]
if not hostname:
return None
# Scoped IPv6 address may have zone info, which must not be lowercased
# like http://[fe80::822a:a8ff:fe49:470c%tESt]:1234/keys
separator = '%' if isinstance(hostname, str) else b'%'
hostname, percent, zone = hostname.partition(separator)
return hostname.lower() + percent + zone
@property
def port(self):
port = self._hostinfo[1]
if port is not None:
try:
port = int(port, 10)
except ValueError:
message = f'Port could not be cast to integer value as {port!r}'
raise ValueError(message) from None
if not ( 0 <= port <= 65535):
raise ValueError("Port out of range 0-65535")
return port
class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):
__slots__ = ()
@property
def _userinfo(self):
netloc = self.netloc
userinfo, have_info, hostinfo = netloc.rpartition('@')
if have_info:
username, have_password, password = userinfo.partition(':')
if not have_password:
password = None
else:
username = password = None
return username, password
@property
def _hostinfo(self):
netloc = self.netloc
_, _, hostinfo = netloc.rpartition('@')
_, have_open_br, bracketed = hostinfo.partition('[')
if have_open_br:
hostname, _, port = bracketed.partition(']')
_, _, port = port.partition(':')
else:
hostname, _, port = hostinfo.partition(':')
if not port:
port = None
return hostname, port
class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):
__slots__ = ()
@property
def _userinfo(self):
netloc = self.netloc
userinfo, have_info, hostinfo = netloc.rpartition(b'@')
if have_info:
username, have_password, password = userinfo.partition(b':')
if not have_password:
password = None
else:
username = password = None
return username, password
@property
def _hostinfo(self):
netloc = self.netloc
_, _, hostinfo = netloc.rpartition(b'@')
_, have_open_br, bracketed = hostinfo.partition(b'[')
if have_open_br:
hostname, _, port = bracketed.partition(b']')
_, _, port = port.partition(b':')
else:
hostname, _, port = hostinfo.partition(b':')
if not port:
port = None
return hostname, port
from collections import namedtuple
_DefragResultBase = namedtuple('DefragResult', 'url fragment')
_SplitResultBase = namedtuple(
'SplitResult', 'scheme netloc path query fragment')
_ParseResultBase = namedtuple(
'ParseResult', 'scheme netloc path params query fragment')
_DefragResultBase.__doc__ = """
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
"""
_DefragResultBase.url.__doc__ = """The URL with no fragment identifier."""
_DefragResultBase.fragment.__doc__ = """
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
"""
_SplitResultBase.__doc__ = """
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
"""
_SplitResultBase.scheme.__doc__ = """Specifies URL scheme for the request."""
_SplitResultBase.netloc.__doc__ = """
Network location where the request is made to.
"""
_SplitResultBase.path.__doc__ = """
The hierarchical path, such as the path to a file to download.
"""
_SplitResultBase.query.__doc__ = """
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
"""
_SplitResultBase.fragment.__doc__ = """
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
"""
_ParseResultBase.__doc__ = """
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
"""
_ParseResultBase.scheme.__doc__ = _SplitResultBase.scheme.__doc__
_ParseResultBase.netloc.__doc__ = _SplitResultBase.netloc.__doc__
_ParseResultBase.path.__doc__ = _SplitResultBase.path.__doc__
_ParseResultBase.params.__doc__ = """
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
"""
_ParseResultBase.query.__doc__ = _SplitResultBase.query.__doc__
_ParseResultBase.fragment.__doc__ = _SplitResultBase.fragment.__doc__
# For backwards compatibility, alias _NetlocResultMixinStr
# ResultBase is no longer part of the documented API, but it is
# retained since deprecating it isn't worth the hassle
ResultBase = _NetlocResultMixinStr
# Structured result objects for string data
class DefragResult(_DefragResultBase, _ResultMixinStr):
__slots__ = ()
def geturl(self):
if self.fragment:
return self.url + '#' + self.fragment
else:
return self.url
class SplitResult(_SplitResultBase, _NetlocResultMixinStr):
__slots__ = ()
def geturl(self):
return urlunsplit(self)
class ParseResult(_ParseResultBase, _NetlocResultMixinStr):
__slots__ = ()
def geturl(self):
return urlunparse(self)
# Structured result objects for bytes data
class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):
__slots__ = ()
def geturl(self):
if self.fragment:
return self.url + b'#' + self.fragment
else:
return self.url
class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):
__slots__ = ()
def geturl(self):
return urlunsplit(self)
class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):
__slots__ = ()
def geturl(self):
return urlunparse(self)
# Set up the encode/decode result pairs
def _fix_result_transcoding():
_result_pairs = (
(DefragResult, DefragResultBytes),
(SplitResult, SplitResultBytes),
(ParseResult, ParseResultBytes),
)
for _decoded, _encoded in _result_pairs:
_decoded._encoded_counterpart = _encoded
_encoded._decoded_counterpart = _decoded
_fix_result_transcoding()
del _fix_result_transcoding
def urlparse(url, scheme='', allow_fragments=True):
"""Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
splitresult = urlsplit(url, scheme, allow_fragments)
scheme, netloc, url, query, fragment = splitresult
if scheme in uses_params and ';' in url:
url, params = _splitparams(url)
else:
params = ''
result = ParseResult(scheme, netloc, url, params, query, fragment)
return _coerce_result(result)
def _splitparams(url):
if '/' in url:
i = url.find(';', url.rfind('/'))
if i < 0:
return url, ''
else:
i = url.find(';')
return url[:i], url[i+1:]
def _splitnetloc(url, start=0):
delim = len(url) # position of end of domain part of url, default is end
for c in '/?#': # look for delimiters; the order is NOT important
wdelim = url.find(c, start) # find first of this delim
if wdelim >= 0: # if found
delim = min(delim, wdelim) # use earliest delim position
return url[start:delim], url[delim:] # return (domain, rest)
def _checknetloc(netloc):
if not netloc or netloc.isascii():
return
# looking for characters like \u2100 that expand to 'a/c'
# IDNA uses NFKC equivalence, so normalize for this check
import unicodedata
n = netloc.replace('@', '') # ignore characters already included
n = n.replace(':', '') # but not the surrounding text
n = n.replace('#', '')
n = n.replace('?', '')
netloc2 = unicodedata.normalize('NFKC', n)
if n == netloc2:
return
for c in '/?#@:':
if c in netloc2:
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")
def _remove_unsafe_bytes_from_url(url):
for b in _UNSAFE_URL_BYTES_TO_REMOVE:
url = url.replace(b, "")
return url
def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
url = _remove_unsafe_bytes_from_url(url)
scheme = _remove_unsafe_bytes_from_url(scheme)
# Only lstrip url as some applications rely on preserving trailing space.
# (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both)
url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)
scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
if cached:
return _coerce_result(cached)
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
clear_cache()
netloc = query = fragment = ''
i = url.find(':')
if i > 0:
if url[:i] == 'http': # optimize the common case
url = url[i+1:]
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
if '?' in url:
url, query = url.split('?', 1)
_checknetloc(netloc)
v = SplitResult('http', netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)
for c in url[:i]:
if c not in scheme_chars:
break
else:
# make sure "url" is not actually a port number (in which case
# "scheme" is really part of the path)
rest = url[i+1:]
if not rest or any(c not in '0123456789' for c in rest):
# not a port number
scheme, url = url[:i].lower(), rest
if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
if '?' in url:
url, query = url.split('?', 1)
_checknetloc(netloc)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)
def urlunparse(components):
"""Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent)."""
scheme, netloc, url, params, query, fragment, _coerce_result = (
_coerce_args(*components))
if params:
url = "%s;%s" % (url, params)
return _coerce_result(urlunsplit((scheme, netloc, url, query, fragment)))
def urlunsplit(components):
"""Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent)."""
scheme, netloc, url, query, fragment, _coerce_result = (
_coerce_args(*components))
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
if url and url[:1] != '/': url = '/' + url
url = '//' + (netloc or '') + url
if scheme:
url = scheme + ':' + url
if query:
url = url + '?' + query
if fragment:
url = url + '#' + fragment
return _coerce_result(url)
def urljoin(base, url, allow_fragments=True):
"""Join a base URL and a possibly relative URL to form an absolute
interpretation of the latter."""
if not base:
return url
if not url:
return base
base, url, _coerce_result = _coerce_args(base, url)
bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
urlparse(base, '', allow_fragments)
scheme, netloc, path, params, query, fragment = \
urlparse(url, bscheme, allow_fragments)
if scheme != bscheme or scheme not in uses_relative:
return _coerce_result(url)
if scheme in uses_netloc:
if netloc:
return _coerce_result(urlunparse((scheme, netloc, path,
params, query, fragment)))
netloc = bnetloc
if not path and not params:
path = bpath
params = bparams
if not query:
query = bquery
return _coerce_result(urlunparse((scheme, netloc, path,
params, query, fragment)))
base_parts = bpath.split('/')
if base_parts[-1] != '':
# the last item is not a directory, so will not be taken into account
# in resolving the relative path
del base_parts[-1]
# for rfc3986, ignore all base path should the first character be root.
if path[:1] == '/':
segments = path.split('/')
else:
segments = base_parts + path.split('/')
# filter out elements that would cause redundant slashes on re-joining
# the resolved_path
segments[1:-1] = filter(None, segments[1:-1])
resolved_path = []
for seg in segments:
if seg == '..':
try:
resolved_path.pop()
except IndexError:
# ignore any .. segments that would otherwise cause an IndexError
# when popped from resolved_path if resolving for rfc3986
pass
elif seg == '.':
continue
else:
resolved_path.append(seg)
if segments[-1] in ('.', '..'):
# do some post-processing here. if the last segment was a relative dir,
# then we need to append the trailing '/'
resolved_path.append('')
return _coerce_result(urlunparse((scheme, netloc, '/'.join(
resolved_path) or '/', params, query, fragment)))
def urldefrag(url):
"""Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
"""
url, _coerce_result = _coerce_args(url)
if '#' in url:
s, n, p, a, q, frag = urlparse(url)
defrag = urlunparse((s, n, p, a, q, ''))
else:
frag = ''
defrag = url
return _coerce_result(DefragResult(defrag, frag))
_hexdig = '0123456789ABCDEFabcdef'
_hextobyte = None
def unquote_to_bytes(string):
"""unquote_to_bytes('abc%20def') -> b'abc def'."""
# Note: strings are encoded as UTF-8. This is only an issue if it contains
# unescaped non-ASCII characters, which URIs should not.
if not string:
# Is it a string-like object?
string.split
return b''
if isinstance(string, str):
string = string.encode('utf-8')
bits = string.split(b'%')
if len(bits) == 1:
return string
res = [bits[0]]
append = res.append
# Delay the initialization of the table to not waste memory
# if the function is never called
global _hextobyte
if _hextobyte is None:
_hextobyte = {(a + b).encode(): bytes.fromhex(a + b)
for a in _hexdig for b in _hexdig}
for item in bits[1:]:
try:
append(_hextobyte[item[:2]])
append(item[2:])
except KeyError:
append(b'%')
append(item)
return b''.join(res)
_asciire = re.compile('([\x00-\x7f]+)')
def unquote(string, encoding='utf-8', errors='replace'):
"""Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
"""
if isinstance(string, bytes):
raise TypeError('Expected str, got bytes')
if '%' not in string:
string.split
return string
if encoding is None:
encoding = 'utf-8'
if errors is None:
errors = 'replace'
bits = _asciire.split(string)
res = [bits[0]]
append = res.append
for i in range(1, len(bits), 2):
append(unquote_to_bytes(bits[i]).decode(encoding, errors))
append(bits[i + 1])
return ''.join(res)
def parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace', max_num_fields=None, separator=None):
"""Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError if there
are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a dictionary.
"""
parsed_result = {}
pairs = parse_qsl(qs, keep_blank_values, strict_parsing,
encoding=encoding, errors=errors,
max_num_fields=max_num_fields, separator=separator)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
else:
parsed_result[name] = [value]
return parsed_result
class _QueryStringSeparatorWarning(RuntimeWarning):
"""Warning for using default `separator` in parse_qs or parse_qsl"""
# The default "separator" for parse_qsl can be specified in a config file.
# It's cached after first read.
_QS_SEPARATOR_CONFIG_FILENAME = '/etc/python/urllib.cfg'
_default_qs_separator = None
def parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace', max_num_fields=None, separator=None):
"""Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError
if there are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a list, as G-d intended.
"""
qs, _coerce_result = _coerce_args(qs)
if isinstance(separator, bytes):
separator = separator.decode('ascii')
if (not separator or (not isinstance(separator, (str, bytes)))) and separator is not None:
raise ValueError("Separator must be of type string or bytes.")
# Used when both "&" and ";" act as separators. (Need a non-string value.)
_legacy = object()
if separator is None:
global _default_qs_separator
separator = _default_qs_separator
envvar_name = 'PYTHON_URLLIB_QS_SEPARATOR'
if separator is None:
# Set default separator from environment variable
separator = os.environ.get(envvar_name)
config_source = 'environment variable'
if separator is None:
# Set default separator from the configuration file
try:
file = open(_QS_SEPARATOR_CONFIG_FILENAME)
except FileNotFoundError:
pass
else:
with file:
import configparser
config = configparser.ConfigParser(
interpolation=None,
comment_prefixes=('#', ),
)
config.read_file(file)
separator = config.get('parse_qs', envvar_name, fallback=None)
_default_qs_separator = separator
config_source = _QS_SEPARATOR_CONFIG_FILENAME
if separator is None:
# The default is '&', but warn if not specified explicitly
if ';' in qs:
from warnings import warn
warn("The default separator of urllib.parse.parse_qsl and "
+ "parse_qs was changed to '&' to avoid a web cache "
+ "poisoning issue (CVE-2021-23336). "
+ "By default, semicolons no longer act as query field "
+ "separators. "
+ "See https://access.redhat.com/articles/5860431 for "
+ "more details.",
_QueryStringSeparatorWarning, stacklevel=2)
separator = '&'
elif separator == 'legacy':
separator = _legacy
elif len(separator) != 1:
raise ValueError(
f'{envvar_name} (from {config_source}) must contain '
+ '1 character, or "legacy". See '
+ 'https://access.redhat.com/articles/5860431 for more details.'
)
# If max_num_fields is defined then check that the number of fields
# is less than max_num_fields. This prevents a memory exhaustion DOS
# attack via post bodies with many fields.
if max_num_fields is not None:
if separator is _legacy:
num_fields = 1 + qs.count('&') + qs.count(';')
else:
num_fields = 1 + qs.count(separator)
if max_num_fields < num_fields:
raise ValueError('Max number of fields exceeded')
if separator is _legacy:
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
else:
pairs = [s1 for s1 in qs.split(separator)]
r = []
for name_value in pairs:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError("bad query field: %r" % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = unquote(name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = unquote(value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
return r
def unquote_plus(string, encoding='utf-8', errors='replace'):
"""Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
"""
string = string.replace('+', ' ')
return unquote(string, encoding, errors)
_ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
b'abcdefghijklmnopqrstuvwxyz'
b'0123456789'
b'_.-~')
_ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE)
_safe_quoters = {}
class Quoter(collections.defaultdict):
"""A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
"""
# Keeps a cache internally, using defaultdict, for efficiency (lookups
# of cached keys don't call Python code at all).
def __init__(self, safe):
"""safe: bytes object."""
self.safe = _ALWAYS_SAFE.union(safe)
def __repr__(self):
# Without this, will just display as a defaultdict
return "<%s %r>" % (self.__class__.__name__, dict(self))
def __missing__(self, b):
# Handle a cache miss. Store quoted string in cache and return.
res = chr(b) if b in self.safe else '%{:02X}'.format(b)
self[b] = res
return res
def quote(string, safe='/', encoding=None, errors=None):
"""quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted. The
quote function offers a cautious (not minimal) way to quote a
string for most of these parts.
RFC 3986 Uniform Resource Identifier (URI): Generic Syntax lists
the following (un)reserved characters.
unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
reserved = gen-delims / sub-delims
gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
/ "*" / "+" / "," / ";" / "="
Each of the reserved characters is reserved in some component of a URL,
but not necessarily in all of them.
The quote function %-escapes all characters that are neither in the
unreserved chars ("always safe") nor the additional chars set via the
safe arg.
The default for the safe arg is '/'. The character is reserved, but in
typical usage the quote function is being called on a path where the
existing slash characters are to be preserved.
Python 3.7 updates from using RFC 2396 to RFC 3986 to quote URL strings.
Now, "~" is included in the set of unreserved characters.
string and safe may be either str or bytes objects. encoding and errors
must not be specified if string is a bytes object.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
"""
if isinstance(string, str):
if not string:
return string
if encoding is None:
encoding = 'utf-8'
if errors is None:
errors = 'strict'
string = string.encode(encoding, errors)
else:
if encoding is not None:
raise TypeError("quote() doesn't support 'encoding' for bytes")
if errors is not None:
raise TypeError("quote() doesn't support 'errors' for bytes")
return quote_from_bytes(string, safe)
def quote_plus(string, safe='', encoding=None, errors=None):
"""Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
"""
# Check if ' ' in string, where string may either be a str or bytes. If
# there are no spaces, the regular quote will produce the right answer.
if ((isinstance(string, str) and ' ' not in string) or
(isinstance(string, bytes) and b' ' not in string)):
return quote(string, safe, encoding, errors)
if isinstance(safe, str):
space = ' '
else:
space = b' '
string = quote(string, safe + space, encoding, errors)
return string.replace(' ', '+')
def quote_from_bytes(bs, safe='/'):
"""Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def\x3f') -> 'abc%20def%3f'
"""
if not isinstance(bs, (bytes, bytearray)):
raise TypeError("quote_from_bytes() expected bytes")
if not bs:
return ''
if isinstance(safe, str):
# Normalize 'safe' by converting to bytes and removing non-ASCII chars
safe = safe.encode('ascii', 'ignore')
else:
safe = bytes([c for c in safe if c < 128])
if not bs.rstrip(_ALWAYS_SAFE_BYTES + safe):
return bs.decode()
try:
quoter = _safe_quoters[safe]
except KeyError:
_safe_quoters[safe] = quoter = Quoter(safe).__getitem__
return ''.join([quoter(char) for char in bs])
def urlencode(query, doseq=False, safe='', encoding=None, errors=None,
quote_via=quote_plus):
"""Encode a dict or sequence of two-element tuples into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The components of a query arg may each be either a string or a bytes type.
The safe, encoding, and errors parameters are passed down to the function
specified by quote_via (encoding and errors only if a component is a str).
"""
if hasattr(query, "items"):
query = query.items()
else:
# It's a bother at times that strings and string-like objects are
# sequences.
try:
# non-sequence items should not work with len()
# non-empty strings will fail this
if len(query) and not isinstance(query[0], tuple):
raise TypeError
# Zero-length sequences of all types will get here and succeed,
# but that's a minor nit. Since the original implementation
# allowed empty dicts that type of behavior probably should be
# preserved for consistency
except TypeError:
ty, va, tb = sys.exc_info()
raise TypeError("not a valid non-string sequence "
"or mapping object").with_traceback(tb)
l = []
if not doseq:
for k, v in query:
if isinstance(k, bytes):
k = quote_via(k, safe)
else:
k = quote_via(str(k), safe, encoding, errors)
if isinstance(v, bytes):
v = quote_via(v, safe)
else:
v = quote_via(str(v), safe, encoding, errors)
l.append(k + '=' + v)
else:
for k, v in query:
if isinstance(k, bytes):
k = quote_via(k, safe)
else:
k = quote_via(str(k), safe, encoding, errors)
if isinstance(v, bytes):
v = quote_via(v, safe)
l.append(k + '=' + v)
elif isinstance(v, str):
v = quote_via(v, safe, encoding, errors)
l.append(k + '=' + v)
else:
try:
# Is this a sufficient test for sequence-ness?
x = len(v)
except TypeError:
# not a sequence
v = quote_via(str(v), safe, encoding, errors)
l.append(k + '=' + v)
else:
# loop over the sequence
for elt in v:
if isinstance(elt, bytes):
elt = quote_via(elt, safe)
else:
elt = quote_via(str(elt), safe, encoding, errors)
l.append(k + '=' + elt)
return '&'.join(l)
def to_bytes(url):
warnings.warn("urllib.parse.to_bytes() is deprecated as of 3.8",
DeprecationWarning, stacklevel=2)
return _to_bytes(url)
def _to_bytes(url):
"""to_bytes(u"URL") --> 'URL'."""
# Most URL schemes require ASCII. If that changes, the conversion
# can be relaxed.
# XXX get rid of to_bytes()
if isinstance(url, str):
try:
url = url.encode("ASCII").decode()
except UnicodeError:
raise UnicodeError("URL " + repr(url) +
" contains non-ASCII characters")
return url
def unwrap(url):
"""Transform a string like '<URL:scheme://host/path>' into 'scheme://host/path'.
The string is returned unchanged if it's not a wrapped URL.
"""
url = str(url).strip()
if url[:1] == '<' and url[-1:] == '>':
url = url[1:-1].strip()
if url[:4] == 'URL:':
url = url[4:].strip()
return url
def splittype(url):
warnings.warn("urllib.parse.splittype() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splittype(url)
_typeprog = None
def _splittype(url):
"""splittype('type:opaquestring') --> 'type', 'opaquestring'."""
global _typeprog
if _typeprog is None:
_typeprog = re.compile('([^/:]+):(.*)', re.DOTALL)
match = _typeprog.match(url)
if match:
scheme, data = match.groups()
return scheme.lower(), data
return None, url
def splithost(url):
warnings.warn("urllib.parse.splithost() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splithost(url)
_hostprog = None
def _splithost(url):
"""splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
global _hostprog
if _hostprog is None:
_hostprog = re.compile('//([^/#?]*)(.*)', re.DOTALL)
match = _hostprog.match(url)
if match:
host_port, path = match.groups()
if path and path[0] != '/':
path = '/' + path
return host_port, path
return None, url
def splituser(host):
warnings.warn("urllib.parse.splituser() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splituser(host)
def _splituser(host):
"""splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
user, delim, host = host.rpartition('@')
return (user if delim else None), host
def splitpasswd(user):
warnings.warn("urllib.parse.splitpasswd() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splitpasswd(user)
def _splitpasswd(user):
"""splitpasswd('user:passwd') -> 'user', 'passwd'."""
user, delim, passwd = user.partition(':')
return user, (passwd if delim else None)
def splitport(host):
warnings.warn("urllib.parse.splitport() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splitport(host)
# splittag('/path#tag') --> '/path', 'tag'
_portprog = None
def _splitport(host):
"""splitport('host:port') --> 'host', 'port'."""
global _portprog
if _portprog is None:
_portprog = re.compile('(.*):([0-9]*)', re.DOTALL)
match = _portprog.fullmatch(host)
if match:
host, port = match.groups()
if port:
return host, port
return host, None
def splitnport(host, defport=-1):
warnings.warn("urllib.parse.splitnport() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splitnport(host, defport)
def _splitnport(host, defport=-1):
"""Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number."""
host, delim, port = host.rpartition(':')
if not delim:
host = port
elif port:
try:
nport = int(port)
except ValueError:
nport = None
return host, nport
return host, defport
def splitquery(url):
warnings.warn("urllib.parse.splitquery() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splitquery(url)
def _splitquery(url):
"""splitquery('/path?query') --> '/path', 'query'."""
path, delim, query = url.rpartition('?')
if delim:
return path, query
return url, None
def splittag(url):
warnings.warn("urllib.parse.splittag() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splittag(url)
def _splittag(url):
"""splittag('/path#tag') --> '/path', 'tag'."""
path, delim, tag = url.rpartition('#')
if delim:
return path, tag
return url, None
def splitattr(url):
warnings.warn("urllib.parse.splitattr() is deprecated as of 3.8, "
"use urllib.parse.urlparse() instead",
DeprecationWarning, stacklevel=2)
return _splitattr(url)
def _splitattr(url):
"""splitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...]."""
words = url.split(';')
return words[0], words[1:]
def splitvalue(attr):
warnings.warn("urllib.parse.splitvalue() is deprecated as of 3.8, "
"use urllib.parse.parse_qsl() instead",
DeprecationWarning, stacklevel=2)
return _splitvalue(attr)
def _splitvalue(attr):
"""splitvalue('attr=value') --> 'attr', 'value'."""
attr, delim, value = attr.partition('=')
return attr, (value if delim else None)
PK (�Z� ��� ��
request.pynu �[��� """An extensible library for opening URLs using a variety of protocols
The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below). It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.
The OpenerDirector manages a collection of Handler objects that do
all the actual work. Each Handler implements a particular protocol or
option. The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL. For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns. The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.
urlopen(url, data=None) -- Basic usage is the same as original
urllib. pass the url and optionally data to post to an HTTP URL, and
get a file-like object back. One difference is that you can also pass
a Request instance instead of URL. Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.
build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers. Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate. If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.
install_opener -- Installs a new opener as the default opener.
objects of interest:
OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.
Request -- An object that encapsulates the state of a request. The
state can be as simple as the URL. It can also include extra HTTP
headers, e.g. a User-Agent.
BaseHandler --
internals:
BaseHandler and parent
_call_chain conventions
Example usage:
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
uri='https://mahler:8092/site-updates.py',
user='klem',
passwd='geheim$parole')
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
"""
# XXX issues:
# If an authentication error handler that tries to perform
# authentication for some reason but fails, how should the error be
# signalled? The client needs to know the HTTP error code. But if
# the handler knows that the problem was, e.g., that it didn't know
# that hash algo that requested in the challenge, it would be good to
# pass that information along to the client, too.
# ftp errors aren't handled cleanly
# check digest against correct (i.e. non-apache) implementation
# Possible extensions:
# complex proxies XXX not sure what exactly was meant by this
# abstract factory for opener
import base64
import bisect
import email
import hashlib
import http.client
import io
import os
import posixpath
import re
import socket
import string
import sys
import time
import tempfile
import contextlib
import warnings
from urllib.error import URLError, HTTPError, ContentTooShortError
from urllib.parse import (
urlparse, urlsplit, urljoin, unwrap, quote, unquote,
_splittype, _splithost, _splitport, _splituser, _splitpasswd,
_splitattr, _splitquery, _splitvalue, _splittag, _to_bytes,
unquote_to_bytes, urlunparse)
from urllib.response import addinfourl, addclosehook
# check for SSL
try:
import ssl
except ImportError:
_have_ssl = False
else:
_have_ssl = True
__all__ = [
# Classes
'Request', 'OpenerDirector', 'BaseHandler', 'HTTPDefaultErrorHandler',
'HTTPRedirectHandler', 'HTTPCookieProcessor', 'ProxyHandler',
'HTTPPasswordMgr', 'HTTPPasswordMgrWithDefaultRealm',
'HTTPPasswordMgrWithPriorAuth', 'AbstractBasicAuthHandler',
'HTTPBasicAuthHandler', 'ProxyBasicAuthHandler', 'AbstractDigestAuthHandler',
'HTTPDigestAuthHandler', 'ProxyDigestAuthHandler', 'HTTPHandler',
'FileHandler', 'FTPHandler', 'CacheFTPHandler', 'DataHandler',
'UnknownHandler', 'HTTPErrorProcessor',
# Functions
'urlopen', 'install_opener', 'build_opener',
'pathname2url', 'url2pathname', 'getproxies',
# Legacy interface
'urlretrieve', 'urlcleanup', 'URLopener', 'FancyURLopener',
]
# used in User-Agent header sent
__version__ = '%d.%d' % sys.version_info[:2]
_opener = None
def urlopen(url, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
*, cafile=None, capath=None, cadefault=False, context=None):
'''Open the URL url, which can be either a string or a Request object.
*data* must be an object specifying additional data to be sent to
the server, or None if no such data is needed. See Request for
details.
urllib.request module uses HTTP/1.1 and includes a "Connection:close"
header in its HTTP requests.
The optional *timeout* parameter specifies a timeout in seconds for
blocking operations like the connection attempt (if not specified, the
global default timeout setting will be used). This only works for HTTP,
HTTPS and FTP connections.
If *context* is specified, it must be a ssl.SSLContext instance describing
the various SSL options. See HTTPSConnection for more details.
The optional *cafile* and *capath* parameters specify a set of trusted CA
certificates for HTTPS requests. cafile should point to a single file
containing a bundle of CA certificates, whereas capath should point to a
directory of hashed certificate files. More information can be found in
ssl.SSLContext.load_verify_locations().
The *cadefault* parameter is ignored.
This function always returns an object which can work as a context
manager and has methods such as
* geturl() - return the URL of the resource retrieved, commonly used to
determine if a redirect was followed
* info() - return the meta-information of the page, such as headers, in the
form of an email.message_from_string() instance (see Quick Reference to
HTTP Headers)
* getcode() - return the HTTP status code of the response. Raises URLError
on errors.
For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse
object slightly modified. In addition to the three new methods above, the
msg attribute contains the same information as the reason attribute ---
the reason phrase returned by the server --- instead of the response
headers as it is specified in the documentation for HTTPResponse.
For FTP, file, and data URLs and requests explicitly handled by legacy
URLopener and FancyURLopener classes, this function returns a
urllib.response.addinfourl object.
Note that None may be returned if no handler handles the request (though
the default installed global OpenerDirector uses UnknownHandler to ensure
this never happens).
In addition, if proxy settings are detected (for example, when a *_proxy
environment variable like http_proxy is set), ProxyHandler is default
installed and makes sure the requests are handled through the proxy.
'''
global _opener
if cafile or capath or cadefault:
import warnings
warnings.warn("cafile, capath and cadefault are deprecated, use a "
"custom context instead.", DeprecationWarning, 2)
if context is not None:
raise ValueError(
"You can't pass both context and any of cafile, capath, and "
"cadefault"
)
if not _have_ssl:
raise ValueError('SSL support not available')
context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH,
cafile=cafile,
capath=capath)
https_handler = HTTPSHandler(context=context)
opener = build_opener(https_handler)
elif context:
https_handler = HTTPSHandler(context=context)
opener = build_opener(https_handler)
elif _opener is None:
_opener = opener = build_opener()
else:
opener = _opener
return opener.open(url, data, timeout)
def install_opener(opener):
global _opener
_opener = opener
_url_tempfiles = []
def urlretrieve(url, filename=None, reporthook=None, data=None):
"""
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
"""
url_type, path = _splittype(url)
with contextlib.closing(urlopen(url, data)) as fp:
headers = fp.info()
# Just return the local path and the "headers" for file://
# URLs. No sense in performing a copy unless requested.
if url_type == "file" and not filename:
return os.path.normpath(path), headers
# Handle temporary file setup.
if filename:
tfp = open(filename, 'wb')
else:
tfp = tempfile.NamedTemporaryFile(delete=False)
filename = tfp.name
_url_tempfiles.append(filename)
with tfp:
result = filename, headers
bs = 1024*8
size = -1
read = 0
blocknum = 0
if "content-length" in headers:
size = int(headers["Content-Length"])
if reporthook:
reporthook(blocknum, bs, size)
while True:
block = fp.read(bs)
if not block:
break
read += len(block)
tfp.write(block)
blocknum += 1
if reporthook:
reporthook(blocknum, bs, size)
if size >= 0 and read < size:
raise ContentTooShortError(
"retrieval incomplete: got only %i out of %i bytes"
% (read, size), result)
return result
def urlcleanup():
"""Clean up temporary files from urlretrieve calls."""
for temp_file in _url_tempfiles:
try:
os.unlink(temp_file)
except OSError:
pass
del _url_tempfiles[:]
global _opener
if _opener:
_opener = None
# copied from cookielib.py
_cut_port_re = re.compile(r":\d+$", re.ASCII)
def request_host(request):
"""Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
"""
url = request.full_url
host = urlparse(url)[1]
if host == "":
host = request.get_header("Host", "")
# remove port, if present
host = _cut_port_re.sub("", host, 1)
return host.lower()
class Request:
def __init__(self, url, data=None, headers={},
origin_req_host=None, unverifiable=False,
method=None):
self.full_url = url
self.headers = {}
self.unredirected_hdrs = {}
self._data = None
self.data = data
self._tunnel_host = None
for key, value in headers.items():
self.add_header(key, value)
if origin_req_host is None:
origin_req_host = request_host(self)
self.origin_req_host = origin_req_host
self.unverifiable = unverifiable
if method:
self.method = method
@property
def full_url(self):
if self.fragment:
return '{}#{}'.format(self._full_url, self.fragment)
return self._full_url
@full_url.setter
def full_url(self, url):
# unwrap('<URL:type://host/path>') --> 'type://host/path'
self._full_url = unwrap(url)
self._full_url, self.fragment = _splittag(self._full_url)
self._parse()
@full_url.deleter
def full_url(self):
self._full_url = None
self.fragment = None
self.selector = ''
@property
def data(self):
return self._data
@data.setter
def data(self, data):
if data != self._data:
self._data = data
# issue 16464
# if we change data we need to remove content-length header
# (cause it's most probably calculated for previous value)
if self.has_header("Content-length"):
self.remove_header("Content-length")
@data.deleter
def data(self):
self.data = None
def _parse(self):
self.type, rest = _splittype(self._full_url)
if self.type is None:
raise ValueError("unknown url type: %r" % self.full_url)
self.host, self.selector = _splithost(rest)
if self.host:
self.host = unquote(self.host)
def get_method(self):
"""Return a string indicating the HTTP request method."""
default_method = "POST" if self.data is not None else "GET"
return getattr(self, 'method', default_method)
def get_full_url(self):
return self.full_url
def set_proxy(self, host, type):
if self.type == 'https' and not self._tunnel_host:
self._tunnel_host = self.host
else:
self.type= type
self.selector = self.full_url
self.host = host
def has_proxy(self):
return self.selector == self.full_url
def add_header(self, key, val):
# useful for something like authentication
self.headers[key.capitalize()] = val
def add_unredirected_header(self, key, val):
# will not be added to a redirected request
self.unredirected_hdrs[key.capitalize()] = val
def has_header(self, header_name):
return (header_name in self.headers or
header_name in self.unredirected_hdrs)
def get_header(self, header_name, default=None):
return self.headers.get(
header_name,
self.unredirected_hdrs.get(header_name, default))
def remove_header(self, header_name):
self.headers.pop(header_name, None)
self.unredirected_hdrs.pop(header_name, None)
def header_items(self):
hdrs = {**self.unredirected_hdrs, **self.headers}
return list(hdrs.items())
class OpenerDirector:
def __init__(self):
client_version = "Python-urllib/%s" % __version__
self.addheaders = [('User-agent', client_version)]
# self.handlers is retained only for backward compatibility
self.handlers = []
# manage the individual handlers
self.handle_open = {}
self.handle_error = {}
self.process_response = {}
self.process_request = {}
def add_handler(self, handler):
if not hasattr(handler, "add_parent"):
raise TypeError("expected BaseHandler instance, got %r" %
type(handler))
added = False
for meth in dir(handler):
if meth in ["redirect_request", "do_open", "proxy_open"]:
# oops, coincidental match
continue
i = meth.find("_")
protocol = meth[:i]
condition = meth[i+1:]
if condition.startswith("error"):
j = condition.find("_") + i + 1
kind = meth[j+1:]
try:
kind = int(kind)
except ValueError:
pass
lookup = self.handle_error.get(protocol, {})
self.handle_error[protocol] = lookup
elif condition == "open":
kind = protocol
lookup = self.handle_open
elif condition == "response":
kind = protocol
lookup = self.process_response
elif condition == "request":
kind = protocol
lookup = self.process_request
else:
continue
handlers = lookup.setdefault(kind, [])
if handlers:
bisect.insort(handlers, handler)
else:
handlers.append(handler)
added = True
if added:
bisect.insort(self.handlers, handler)
handler.add_parent(self)
def close(self):
# Only exists for backwards compatibility.
pass
def _call_chain(self, chain, kind, meth_name, *args):
# Handlers raise an exception if no one else should try to handle
# the request, or return None if they can't but another handler
# could. Otherwise, they return the response.
handlers = chain.get(kind, ())
for handler in handlers:
func = getattr(handler, meth_name)
result = func(*args)
if result is not None:
return result
def open(self, fullurl, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT):
# accept a URL or a Request object
if isinstance(fullurl, str):
req = Request(fullurl, data)
else:
req = fullurl
if data is not None:
req.data = data
req.timeout = timeout
protocol = req.type
# pre-process request
meth_name = protocol+"_request"
for processor in self.process_request.get(protocol, []):
meth = getattr(processor, meth_name)
req = meth(req)
sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())
response = self._open(req, data)
# post-process response
meth_name = protocol+"_response"
for processor in self.process_response.get(protocol, []):
meth = getattr(processor, meth_name)
response = meth(req, response)
return response
def _open(self, req, data=None):
result = self._call_chain(self.handle_open, 'default',
'default_open', req)
if result:
return result
protocol = req.type
result = self._call_chain(self.handle_open, protocol, protocol +
'_open', req)
if result:
return result
return self._call_chain(self.handle_open, 'unknown',
'unknown_open', req)
def error(self, proto, *args):
if proto in ('http', 'https'):
# XXX http[s] protocols are special-cased
dict = self.handle_error['http'] # https is not different than http
proto = args[2] # YUCK!
meth_name = 'http_error_%s' % proto
http_err = 1
orig_args = args
else:
dict = self.handle_error
meth_name = proto + '_error'
http_err = 0
args = (dict, proto, meth_name) + args
result = self._call_chain(*args)
if result:
return result
if http_err:
args = (dict, 'default', 'http_error_default') + orig_args
return self._call_chain(*args)
# XXX probably also want an abstract factory that knows when it makes
# sense to skip a superclass in favor of a subclass and when it might
# make sense to include both
def build_opener(*handlers):
"""Create an opener object from a list of handlers.
The opener will use several default handlers, including support
for HTTP, FTP and when applicable HTTPS.
If any of the handlers passed as arguments are subclasses of the
default handlers, the default handlers will not be used.
"""
opener = OpenerDirector()
default_classes = [ProxyHandler, UnknownHandler, HTTPHandler,
HTTPDefaultErrorHandler, HTTPRedirectHandler,
FTPHandler, FileHandler, HTTPErrorProcessor,
DataHandler]
if hasattr(http.client, "HTTPSConnection"):
default_classes.append(HTTPSHandler)
skip = set()
for klass in default_classes:
for check in handlers:
if isinstance(check, type):
if issubclass(check, klass):
skip.add(klass)
elif isinstance(check, klass):
skip.add(klass)
for klass in skip:
default_classes.remove(klass)
for klass in default_classes:
opener.add_handler(klass())
for h in handlers:
if isinstance(h, type):
h = h()
opener.add_handler(h)
return opener
class BaseHandler:
handler_order = 500
def add_parent(self, parent):
self.parent = parent
def close(self):
# Only exists for backwards compatibility
pass
def __lt__(self, other):
if not hasattr(other, "handler_order"):
# Try to preserve the old behavior of having custom classes
# inserted after default ones (works only for custom user
# classes which are not aware of handler_order).
return True
return self.handler_order < other.handler_order
class HTTPErrorProcessor(BaseHandler):
"""Process HTTP error responses."""
handler_order = 1000 # after all other processing
def http_response(self, request, response):
code, msg, hdrs = response.code, response.msg, response.info()
# According to RFC 2616, "2xx" code indicates that the client's
# request was successfully received, understood, and accepted.
if not (200 <= code < 300):
response = self.parent.error(
'http', request, response, code, msg, hdrs)
return response
https_response = http_response
class HTTPDefaultErrorHandler(BaseHandler):
def http_error_default(self, req, fp, code, msg, hdrs):
raise HTTPError(req.full_url, code, msg, hdrs, fp)
class HTTPRedirectHandler(BaseHandler):
# maximum number of redirections to any single URL
# this is needed because of the state that cookies introduce
max_repeats = 4
# maximum total number of redirections (regardless of URL) before
# assuming we're in a loop
max_redirections = 10
def redirect_request(self, req, fp, code, msg, headers, newurl):
"""Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
"""
m = req.get_method()
if (not (code in (301, 302, 303, 307) and m in ("GET", "HEAD")
or code in (301, 302, 303) and m == "POST")):
raise HTTPError(req.full_url, code, msg, headers, fp)
# Strictly (according to RFC 2616), 301 or 302 in response to
# a POST MUST NOT cause a redirection without confirmation
# from the user (of urllib.request, in this case). In practice,
# essentially all clients do redirect in this case, so we do
# the same.
# Be conciliant with URIs containing a space. This is mainly
# redundant with the more complete encoding done in http_error_302(),
# but it is kept for compatibility with other callers.
newurl = newurl.replace(' ', '%20')
CONTENT_HEADERS = ("content-length", "content-type")
newheaders = {k: v for k, v in req.headers.items()
if k.lower() not in CONTENT_HEADERS}
return Request(newurl,
headers=newheaders,
origin_req_host=req.origin_req_host,
unverifiable=True)
# Implementation note: To avoid the server sending us into an
# infinite loop, the request object needs to track what URLs we
# have already seen. Do this by adding a handler-specific
# attribute to the Request object.
def http_error_302(self, req, fp, code, msg, headers):
# Some servers (incorrectly) return multiple Location headers
# (so probably same goes for URI). Use first header.
if "location" in headers:
newurl = headers["location"]
elif "uri" in headers:
newurl = headers["uri"]
else:
return
# fix a possible malformed URL
urlparts = urlparse(newurl)
# For security reasons we don't allow redirection to anything other
# than http, https or ftp.
if urlparts.scheme not in ('http', 'https', 'ftp', ''):
raise HTTPError(
newurl, code,
"%s - Redirection to url '%s' is not allowed" % (msg, newurl),
headers, fp)
if not urlparts.path and urlparts.netloc:
urlparts = list(urlparts)
urlparts[2] = "/"
newurl = urlunparse(urlparts)
# http.client.parse_headers() decodes as ISO-8859-1. Recover the
# original bytes and percent-encode non-ASCII bytes, and any special
# characters such as the space.
newurl = quote(
newurl, encoding="iso-8859-1", safe=string.punctuation)
newurl = urljoin(req.full_url, newurl)
# XXX Probably want to forget about the state of the current
# request, although that might interact poorly with other
# handlers that also use handler-specific request attributes
new = self.redirect_request(req, fp, code, msg, headers, newurl)
if new is None:
return
# loop detection
# .redirect_dict has a key url if url was previously visited.
if hasattr(req, 'redirect_dict'):
visited = new.redirect_dict = req.redirect_dict
if (visited.get(newurl, 0) >= self.max_repeats or
len(visited) >= self.max_redirections):
raise HTTPError(req.full_url, code,
self.inf_msg + msg, headers, fp)
else:
visited = new.redirect_dict = req.redirect_dict = {}
visited[newurl] = visited.get(newurl, 0) + 1
# Don't close the fp until we are sure that we won't use it
# with HTTPError.
fp.read()
fp.close()
return self.parent.open(new, timeout=req.timeout)
http_error_301 = http_error_303 = http_error_307 = http_error_302
inf_msg = "The HTTP server returned a redirect error that would " \
"lead to an infinite loop.\n" \
"The last 30x error message was:\n"
def _parse_proxy(proxy):
"""Return (scheme, user, password, host/port) given a URL or an authority.
If a URL is supplied, it must have an authority (host:port) component.
According to RFC 3986, having an authority component means the URL must
have two slashes after the scheme.
"""
scheme, r_scheme = _splittype(proxy)
if not r_scheme.startswith("/"):
# authority
scheme = None
authority = proxy
else:
# URL
if not r_scheme.startswith("//"):
raise ValueError("proxy URL with no authority: %r" % proxy)
# We have an authority, so for RFC 3986-compliant URLs (by ss 3.
# and 3.3.), path is empty or starts with '/'
if '@' in r_scheme:
host_separator = r_scheme.find('@')
end = r_scheme.find("/", host_separator)
else:
end = r_scheme.find("/", 2)
if end == -1:
end = None
authority = r_scheme[2:end]
userinfo, hostport = _splituser(authority)
if userinfo is not None:
user, password = _splitpasswd(userinfo)
else:
user = password = None
return scheme, user, password, hostport
class ProxyHandler(BaseHandler):
# Proxies must be in front
handler_order = 100
def __init__(self, proxies=None):
if proxies is None:
proxies = getproxies()
assert hasattr(proxies, 'keys'), "proxies must be a mapping"
self.proxies = proxies
for type, url in proxies.items():
type = type.lower()
setattr(self, '%s_open' % type,
lambda r, proxy=url, type=type, meth=self.proxy_open:
meth(r, proxy, type))
def proxy_open(self, req, proxy, type):
orig_type = req.type
proxy_type, user, password, hostport = _parse_proxy(proxy)
if proxy_type is None:
proxy_type = orig_type
if req.host and proxy_bypass(req.host):
return None
if user and password:
user_pass = '%s:%s' % (unquote(user),
unquote(password))
creds = base64.b64encode(user_pass.encode()).decode("ascii")
req.add_header('Proxy-authorization', 'Basic ' + creds)
hostport = unquote(hostport)
req.set_proxy(hostport, proxy_type)
if orig_type == proxy_type or orig_type == 'https':
# let other handlers take care of it
return None
else:
# need to start over, because the other handlers don't
# grok the proxy's URL type
# e.g. if we have a constructor arg proxies like so:
# {'http': 'ftp://proxy.example.com'}, we may end up turning
# a request for http://acme.example.com/a into one for
# ftp://proxy.example.com/a
return self.parent.open(req, timeout=req.timeout)
class HTTPPasswordMgr:
def __init__(self):
self.passwd = {}
def add_password(self, realm, uri, user, passwd):
# uri could be a single URI or a sequence
if isinstance(uri, str):
uri = [uri]
if realm not in self.passwd:
self.passwd[realm] = {}
for default_port in True, False:
reduced_uri = tuple(
self.reduce_uri(u, default_port) for u in uri)
self.passwd[realm][reduced_uri] = (user, passwd)
def find_user_password(self, realm, authuri):
domains = self.passwd.get(realm, {})
for default_port in True, False:
reduced_authuri = self.reduce_uri(authuri, default_port)
for uris, authinfo in domains.items():
for uri in uris:
if self.is_suburi(uri, reduced_authuri):
return authinfo
return None, None
def reduce_uri(self, uri, default_port=True):
"""Accept authority or URI and extract only the authority and path."""
# note HTTP URLs do not have a userinfo component
parts = urlsplit(uri)
if parts[1]:
# URI
scheme = parts[0]
authority = parts[1]
path = parts[2] or '/'
else:
# host or host:port
scheme = None
authority = uri
path = '/'
host, port = _splitport(authority)
if default_port and port is None and scheme is not None:
dport = {"http": 80,
"https": 443,
}.get(scheme)
if dport is not None:
authority = "%s:%d" % (host, dport)
return authority, path
def is_suburi(self, base, test):
"""Check if test is below base in a URI tree
Both args must be URIs in reduced form.
"""
if base == test:
return True
if base[0] != test[0]:
return False
prefix = base[1]
if prefix[-1:] != '/':
prefix += '/'
return test[1].startswith(prefix)
class HTTPPasswordMgrWithDefaultRealm(HTTPPasswordMgr):
def find_user_password(self, realm, authuri):
user, password = HTTPPasswordMgr.find_user_password(self, realm,
authuri)
if user is not None:
return user, password
return HTTPPasswordMgr.find_user_password(self, None, authuri)
class HTTPPasswordMgrWithPriorAuth(HTTPPasswordMgrWithDefaultRealm):
def __init__(self, *args, **kwargs):
self.authenticated = {}
super().__init__(*args, **kwargs)
def add_password(self, realm, uri, user, passwd, is_authenticated=False):
self.update_authenticated(uri, is_authenticated)
# Add a default for prior auth requests
if realm is not None:
super().add_password(None, uri, user, passwd)
super().add_password(realm, uri, user, passwd)
def update_authenticated(self, uri, is_authenticated=False):
# uri could be a single URI or a sequence
if isinstance(uri, str):
uri = [uri]
for default_port in True, False:
for u in uri:
reduced_uri = self.reduce_uri(u, default_port)
self.authenticated[reduced_uri] = is_authenticated
def is_authenticated(self, authuri):
for default_port in True, False:
reduced_authuri = self.reduce_uri(authuri, default_port)
for uri in self.authenticated:
if self.is_suburi(uri, reduced_authuri):
return self.authenticated[uri]
class AbstractBasicAuthHandler:
# XXX this allows for multiple auth-schemes, but will stupidly pick
# the last one with a realm specified.
# allow for double- and single-quoted realm values
# (single quotes are a violation of the RFC, but appear in the wild)
rx = re.compile('(?:^|,)' # start of the string or ','
'[ \t]*' # optional whitespaces
'([^ \t,]+)' # scheme like "Basic"
'[ \t]+' # mandatory whitespaces
# realm=xxx
# realm='xxx'
# realm="xxx"
'realm=(["\']?)([^"\']*)\\2',
re.I)
# XXX could pre-emptively send auth info already accepted (RFC 2617,
# end of section 2, and section 1.2 immediately after "credentials"
# production).
def __init__(self, password_mgr=None):
if password_mgr is None:
password_mgr = HTTPPasswordMgr()
self.passwd = password_mgr
self.add_password = self.passwd.add_password
def _parse_realm(self, header):
# parse WWW-Authenticate header: accept multiple challenges per header
found_challenge = False
for mo in AbstractBasicAuthHandler.rx.finditer(header):
scheme, quote, realm = mo.groups()
if quote not in ['"', "'"]:
warnings.warn("Basic Auth Realm was unquoted",
UserWarning, 3)
yield (scheme, realm)
found_challenge = True
if not found_challenge:
if header:
scheme = header.split()[0]
else:
scheme = ''
yield (scheme, None)
def http_error_auth_reqed(self, authreq, host, req, headers):
# host may be an authority (without userinfo) or a URL with an
# authority
headers = headers.get_all(authreq)
if not headers:
# no header found
return
unsupported = None
for header in headers:
for scheme, realm in self._parse_realm(header):
if scheme.lower() != 'basic':
unsupported = scheme
continue
if realm is not None:
# Use the first matching Basic challenge.
# Ignore following challenges even if they use the Basic
# scheme.
return self.retry_http_basic_auth(host, req, realm)
if unsupported is not None:
raise ValueError("AbstractBasicAuthHandler does not "
"support the following scheme: %r"
% (scheme,))
def retry_http_basic_auth(self, host, req, realm):
user, pw = self.passwd.find_user_password(realm, host)
if pw is not None:
raw = "%s:%s" % (user, pw)
auth = "Basic " + base64.b64encode(raw.encode()).decode("ascii")
if req.get_header(self.auth_header, None) == auth:
return None
req.add_unredirected_header(self.auth_header, auth)
return self.parent.open(req, timeout=req.timeout)
else:
return None
def http_request(self, req):
if (not hasattr(self.passwd, 'is_authenticated') or
not self.passwd.is_authenticated(req.full_url)):
return req
if not req.has_header('Authorization'):
user, passwd = self.passwd.find_user_password(None, req.full_url)
credentials = '{0}:{1}'.format(user, passwd).encode()
auth_str = base64.standard_b64encode(credentials).decode()
req.add_unredirected_header('Authorization',
'Basic {}'.format(auth_str.strip()))
return req
def http_response(self, req, response):
if hasattr(self.passwd, 'is_authenticated'):
if 200 <= response.code < 300:
self.passwd.update_authenticated(req.full_url, True)
else:
self.passwd.update_authenticated(req.full_url, False)
return response
https_request = http_request
https_response = http_response
class HTTPBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
auth_header = 'Authorization'
def http_error_401(self, req, fp, code, msg, headers):
url = req.full_url
response = self.http_error_auth_reqed('www-authenticate',
url, req, headers)
return response
class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):
auth_header = 'Proxy-authorization'
def http_error_407(self, req, fp, code, msg, headers):
# http_error_auth_reqed requires that there is no userinfo component in
# authority. Assume there isn't one, since urllib.request does not (and
# should not, RFC 3986 s. 3.2.1) support requests for URLs containing
# userinfo.
authority = req.host
response = self.http_error_auth_reqed('proxy-authenticate',
authority, req, headers)
return response
# Return n random bytes.
_randombytes = os.urandom
class AbstractDigestAuthHandler:
# Digest authentication is specified in RFC 2617.
# XXX The client does not inspect the Authentication-Info header
# in a successful response.
# XXX It should be possible to test this implementation against
# a mock server that just generates a static set of challenges.
# XXX qop="auth-int" supports is shaky
def __init__(self, passwd=None):
if passwd is None:
passwd = HTTPPasswordMgr()
self.passwd = passwd
self.add_password = self.passwd.add_password
self.retried = 0
self.nonce_count = 0
self.last_nonce = None
def reset_retry_count(self):
self.retried = 0
def http_error_auth_reqed(self, auth_header, host, req, headers):
authreq = headers.get(auth_header, None)
if self.retried > 5:
# Don't fail endlessly - if we failed once, we'll probably
# fail a second time. Hm. Unless the Password Manager is
# prompting for the information. Crap. This isn't great
# but it's better than the current 'repeat until recursion
# depth exceeded' approach <wink>
raise HTTPError(req.full_url, 401, "digest auth failed",
headers, None)
else:
self.retried += 1
if authreq:
scheme = authreq.split()[0]
if scheme.lower() == 'digest':
return self.retry_http_digest_auth(req, authreq)
elif scheme.lower() != 'basic':
raise ValueError("AbstractDigestAuthHandler does not support"
" the following scheme: '%s'" % scheme)
def retry_http_digest_auth(self, req, auth):
token, challenge = auth.split(' ', 1)
chal = parse_keqv_list(filter(None, parse_http_list(challenge)))
auth = self.get_authorization(req, chal)
if auth:
auth_val = 'Digest %s' % auth
if req.headers.get(self.auth_header, None) == auth_val:
return None
req.add_unredirected_header(self.auth_header, auth_val)
resp = self.parent.open(req, timeout=req.timeout)
return resp
def get_cnonce(self, nonce):
# The cnonce-value is an opaque
# quoted string value provided by the client and used by both client
# and server to avoid chosen plaintext attacks, to provide mutual
# authentication, and to provide some message integrity protection.
# This isn't a fabulous effort, but it's probably Good Enough.
s = "%s:%s:%s:" % (self.nonce_count, nonce, time.ctime())
b = s.encode("ascii") + _randombytes(8)
dig = hashlib.sha1(b).hexdigest()
return dig[:16]
def get_authorization(self, req, chal):
try:
realm = chal['realm']
nonce = chal['nonce']
qop = chal.get('qop')
algorithm = chal.get('algorithm', 'MD5')
# mod_digest doesn't send an opaque, even though it isn't
# supposed to be optional
opaque = chal.get('opaque', None)
except KeyError:
return None
H, KD = self.get_algorithm_impls(algorithm)
if H is None:
return None
user, pw = self.passwd.find_user_password(realm, req.full_url)
if user is None:
return None
# XXX not implemented yet
if req.data is not None:
entdig = self.get_entity_digest(req.data, chal)
else:
entdig = None
A1 = "%s:%s:%s" % (user, realm, pw)
A2 = "%s:%s" % (req.get_method(),
# XXX selector: what about proxies and full urls
req.selector)
# NOTE: As per RFC 2617, when server sends "auth,auth-int", the client could use either `auth`
# or `auth-int` to the response back. we use `auth` to send the response back.
if qop is None:
respdig = KD(H(A1), "%s:%s" % (nonce, H(A2)))
elif 'auth' in qop.split(','):
if nonce == self.last_nonce:
self.nonce_count += 1
else:
self.nonce_count = 1
self.last_nonce = nonce
ncvalue = '%08x' % self.nonce_count
cnonce = self.get_cnonce(nonce)
noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, 'auth', H(A2))
respdig = KD(H(A1), noncebit)
else:
# XXX handle auth-int.
raise URLError("qop '%s' is not supported." % qop)
# XXX should the partial digests be encoded too?
base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
'response="%s"' % (user, realm, nonce, req.selector,
respdig)
if opaque:
base += ', opaque="%s"' % opaque
if entdig:
base += ', digest="%s"' % entdig
base += ', algorithm="%s"' % algorithm
if qop:
base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce)
return base
def get_algorithm_impls(self, algorithm):
# lambdas assume digest modules are imported at the top level
if algorithm == 'MD5':
H = lambda x: hashlib.md5(x.encode("ascii")).hexdigest()
elif algorithm == 'SHA':
H = lambda x: hashlib.sha1(x.encode("ascii")).hexdigest()
# XXX MD5-sess
else:
raise ValueError("Unsupported digest authentication "
"algorithm %r" % algorithm)
KD = lambda s, d: H("%s:%s" % (s, d))
return H, KD
def get_entity_digest(self, data, chal):
# XXX not implemented yet
return None
class HTTPDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):
"""An authentication protocol defined by RFC 2069
Digest authentication improves on basic authentication because it
does not transmit passwords in the clear.
"""
auth_header = 'Authorization'
handler_order = 490 # before Basic auth
def http_error_401(self, req, fp, code, msg, headers):
host = urlparse(req.full_url)[1]
retry = self.http_error_auth_reqed('www-authenticate',
host, req, headers)
self.reset_retry_count()
return retry
class ProxyDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):
auth_header = 'Proxy-Authorization'
handler_order = 490 # before Basic auth
def http_error_407(self, req, fp, code, msg, headers):
host = req.host
retry = self.http_error_auth_reqed('proxy-authenticate',
host, req, headers)
self.reset_retry_count()
return retry
class AbstractHTTPHandler(BaseHandler):
def __init__(self, debuglevel=0):
self._debuglevel = debuglevel
def set_http_debuglevel(self, level):
self._debuglevel = level
def _get_content_length(self, request):
return http.client.HTTPConnection._get_content_length(
request.data,
request.get_method())
def do_request_(self, request):
host = request.host
if not host:
raise URLError('no host given')
if request.data is not None: # POST
data = request.data
if isinstance(data, str):
msg = "POST data should be bytes, an iterable of bytes, " \
"or a file object. It cannot be of type str."
raise TypeError(msg)
if not request.has_header('Content-type'):
request.add_unredirected_header(
'Content-type',
'application/x-www-form-urlencoded')
if (not request.has_header('Content-length')
and not request.has_header('Transfer-encoding')):
content_length = self._get_content_length(request)
if content_length is not None:
request.add_unredirected_header(
'Content-length', str(content_length))
else:
request.add_unredirected_header(
'Transfer-encoding', 'chunked')
sel_host = host
if request.has_proxy():
scheme, sel = _splittype(request.selector)
sel_host, sel_path = _splithost(sel)
if not request.has_header('Host'):
request.add_unredirected_header('Host', sel_host)
for name, value in self.parent.addheaders:
name = name.capitalize()
if not request.has_header(name):
request.add_unredirected_header(name, value)
return request
def do_open(self, http_class, req, **http_conn_args):
"""Return an HTTPResponse object for the request, using http_class.
http_class must implement the HTTPConnection API from http.client.
"""
host = req.host
if not host:
raise URLError('no host given')
# will parse host:port
h = http_class(host, timeout=req.timeout, **http_conn_args)
h.set_debuglevel(self._debuglevel)
headers = dict(req.unredirected_hdrs)
headers.update({k: v for k, v in req.headers.items()
if k not in headers})
# TODO(jhylton): Should this be redesigned to handle
# persistent connections?
# We want to make an HTTP/1.1 request, but the addinfourl
# class isn't prepared to deal with a persistent connection.
# It will try to read all remaining data from the socket,
# which will block while the server waits for the next request.
# So make sure the connection gets closed after the (only)
# request.
headers["Connection"] = "close"
headers = {name.title(): val for name, val in headers.items()}
if req._tunnel_host:
tunnel_headers = {}
proxy_auth_hdr = "Proxy-Authorization"
if proxy_auth_hdr in headers:
tunnel_headers[proxy_auth_hdr] = headers[proxy_auth_hdr]
# Proxy-Authorization should not be sent to origin
# server.
del headers[proxy_auth_hdr]
h.set_tunnel(req._tunnel_host, headers=tunnel_headers)
try:
try:
h.request(req.get_method(), req.selector, req.data, headers,
encode_chunked=req.has_header('Transfer-encoding'))
except OSError as err: # timeout error
raise URLError(err)
r = h.getresponse()
except:
h.close()
raise
# If the server does not send us a 'Connection: close' header,
# HTTPConnection assumes the socket should be left open. Manually
# mark the socket to be closed when this response object goes away.
if h.sock:
h.sock.close()
h.sock = None
r.url = req.get_full_url()
# This line replaces the .msg attribute of the HTTPResponse
# with .headers, because urllib clients expect the response to
# have the reason in .msg. It would be good to mark this
# attribute is deprecated and get then to use info() or
# .headers.
r.msg = r.reason
return r
class HTTPHandler(AbstractHTTPHandler):
def http_open(self, req):
return self.do_open(http.client.HTTPConnection, req)
http_request = AbstractHTTPHandler.do_request_
if hasattr(http.client, 'HTTPSConnection'):
class HTTPSHandler(AbstractHTTPHandler):
def __init__(self, debuglevel=0, context=None, check_hostname=None):
AbstractHTTPHandler.__init__(self, debuglevel)
self._context = context
self._check_hostname = check_hostname
def https_open(self, req):
return self.do_open(http.client.HTTPSConnection, req,
context=self._context, check_hostname=self._check_hostname)
https_request = AbstractHTTPHandler.do_request_
__all__.append('HTTPSHandler')
class HTTPCookieProcessor(BaseHandler):
def __init__(self, cookiejar=None):
import http.cookiejar
if cookiejar is None:
cookiejar = http.cookiejar.CookieJar()
self.cookiejar = cookiejar
def http_request(self, request):
self.cookiejar.add_cookie_header(request)
return request
def http_response(self, request, response):
self.cookiejar.extract_cookies(response, request)
return response
https_request = http_request
https_response = http_response
class UnknownHandler(BaseHandler):
def unknown_open(self, req):
type = req.type
raise URLError('unknown url type: %s' % type)
def parse_keqv_list(l):
"""Parse list of key=value strings where keys are not duplicated."""
parsed = {}
for elt in l:
k, v = elt.split('=', 1)
if v[0] == '"' and v[-1] == '"':
v = v[1:-1]
parsed[k] = v
return parsed
def parse_http_list(s):
"""Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Neither commas nor quotes count if they are escaped.
Only double-quotes count, not single-quotes.
"""
res = []
part = ''
escape = quote = False
for cur in s:
if escape:
part += cur
escape = False
continue
if quote:
if cur == '\\':
escape = True
continue
elif cur == '"':
quote = False
part += cur
continue
if cur == ',':
res.append(part)
part = ''
continue
if cur == '"':
quote = True
part += cur
# append last part
if part:
res.append(part)
return [part.strip() for part in res]
class FileHandler(BaseHandler):
# Use local file or FTP depending on form of URL
def file_open(self, req):
url = req.selector
if url[:2] == '//' and url[2:3] != '/' and (req.host and
req.host != 'localhost'):
if not req.host in self.get_names():
raise URLError("file:// scheme is supported only on localhost")
else:
return self.open_local_file(req)
# names for the localhost
names = None
def get_names(self):
if FileHandler.names is None:
try:
FileHandler.names = tuple(
socket.gethostbyname_ex('localhost')[2] +
socket.gethostbyname_ex(socket.gethostname())[2])
except socket.gaierror:
FileHandler.names = (socket.gethostbyname('localhost'),)
return FileHandler.names
# not entirely sure what the rules are here
def open_local_file(self, req):
import email.utils
import mimetypes
host = req.host
filename = req.selector
localfile = url2pathname(filename)
try:
stats = os.stat(localfile)
size = stats.st_size
modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
mtype = mimetypes.guess_type(filename)[0]
headers = email.message_from_string(
'Content-type: %s\nContent-length: %d\nLast-modified: %s\n' %
(mtype or 'text/plain', size, modified))
if host:
host, port = _splitport(host)
if not host or \
(not port and _safe_gethostbyname(host) in self.get_names()):
if host:
origurl = 'file://' + host + filename
else:
origurl = 'file://' + filename
return addinfourl(open(localfile, 'rb'), headers, origurl)
except OSError as exp:
raise URLError(exp)
raise URLError('file not on local host')
def _safe_gethostbyname(host):
try:
return socket.gethostbyname(host)
except socket.gaierror:
return None
class FTPHandler(BaseHandler):
def ftp_open(self, req):
import ftplib
import mimetypes
host = req.host
if not host:
raise URLError('ftp error: no host given')
host, port = _splitport(host)
if port is None:
port = ftplib.FTP_PORT
else:
port = int(port)
# username/password handling
user, host = _splituser(host)
if user:
user, passwd = _splitpasswd(user)
else:
passwd = None
host = unquote(host)
user = user or ''
passwd = passwd or ''
try:
host = socket.gethostbyname(host)
except OSError as msg:
raise URLError(msg)
path, attrs = _splitattr(req.selector)
dirs = path.split('/')
dirs = list(map(unquote, dirs))
dirs, file = dirs[:-1], dirs[-1]
if dirs and not dirs[0]:
dirs = dirs[1:]
try:
fw = self.connect_ftp(user, passwd, host, port, dirs, req.timeout)
type = file and 'I' or 'D'
for attr in attrs:
attr, value = _splitvalue(attr)
if attr.lower() == 'type' and \
value in ('a', 'A', 'i', 'I', 'd', 'D'):
type = value.upper()
fp, retrlen = fw.retrfile(file, type)
headers = ""
mtype = mimetypes.guess_type(req.full_url)[0]
if mtype:
headers += "Content-type: %s\n" % mtype
if retrlen is not None and retrlen >= 0:
headers += "Content-length: %d\n" % retrlen
headers = email.message_from_string(headers)
return addinfourl(fp, headers, req.full_url)
except ftplib.all_errors as exp:
exc = URLError('ftp error: %r' % exp)
raise exc.with_traceback(sys.exc_info()[2])
def connect_ftp(self, user, passwd, host, port, dirs, timeout):
return ftpwrapper(user, passwd, host, port, dirs, timeout,
persistent=False)
class CacheFTPHandler(FTPHandler):
# XXX would be nice to have pluggable cache strategies
# XXX this stuff is definitely not thread safe
def __init__(self):
self.cache = {}
self.timeout = {}
self.soonest = 0
self.delay = 60
self.max_conns = 16
def setTimeout(self, t):
self.delay = t
def setMaxConns(self, m):
self.max_conns = m
def connect_ftp(self, user, passwd, host, port, dirs, timeout):
key = user, host, port, '/'.join(dirs), timeout
if key in self.cache:
self.timeout[key] = time.time() + self.delay
else:
self.cache[key] = ftpwrapper(user, passwd, host, port,
dirs, timeout)
self.timeout[key] = time.time() + self.delay
self.check_cache()
return self.cache[key]
def check_cache(self):
# first check for old ones
t = time.time()
if self.soonest <= t:
for k, v in list(self.timeout.items()):
if v < t:
self.cache[k].close()
del self.cache[k]
del self.timeout[k]
self.soonest = min(list(self.timeout.values()))
# then check the size
if len(self.cache) == self.max_conns:
for k, v in list(self.timeout.items()):
if v == self.soonest:
del self.cache[k]
del self.timeout[k]
break
self.soonest = min(list(self.timeout.values()))
def clear_cache(self):
for conn in self.cache.values():
conn.close()
self.cache.clear()
self.timeout.clear()
class DataHandler(BaseHandler):
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.full_url
scheme, data = url.split(":",1)
mediatype, data = data.split(",",1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = unquote_to_bytes(data)
if mediatype.endswith(";base64"):
data = base64.decodebytes(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
headers = email.message_from_string("Content-type: %s\nContent-length: %d\n" %
(mediatype, len(data)))
return addinfourl(io.BytesIO(data), headers, url)
# Code move from the old urllib module
MAXFTPCACHE = 10 # Trim the ftp cache beyond this size
# Helper for non-unix systems
if os.name == 'nt':
from nturl2path import url2pathname, pathname2url
else:
def url2pathname(pathname):
"""OS-specific conversion from a relative URL of the 'file' scheme
to a file system path; not recommended for general use."""
return unquote(pathname)
def pathname2url(pathname):
"""OS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use."""
return quote(pathname)
ftpcache = {}
class URLopener:
"""Class to open URLs.
This is a class rather than just a subroutine because we may need
more than one set of global protocol-specific options.
Note -- this is a base class for those who don't want the
automatic handling of errors type 302 (relocated) and 401
(authorization needed)."""
__tempfiles = None
version = "Python-urllib/%s" % __version__
# Constructor
def __init__(self, proxies=None, **x509):
msg = "%(class)s style of invoking requests is deprecated. " \
"Use newer urlopen functions/methods" % {'class': self.__class__.__name__}
warnings.warn(msg, DeprecationWarning, stacklevel=3)
if proxies is None:
proxies = getproxies()
assert hasattr(proxies, 'keys'), "proxies must be a mapping"
self.proxies = proxies
self.key_file = x509.get('key_file')
self.cert_file = x509.get('cert_file')
self.addheaders = [('User-Agent', self.version), ('Accept', '*/*')]
self.__tempfiles = []
self.__unlink = os.unlink # See cleanup()
self.tempcache = None
# Undocumented feature: if you assign {} to tempcache,
# it is used to cache files retrieved with
# self.retrieve(). This is not enabled by default
# since it does not work for changing documents (and I
# haven't got the logic to check expiration headers
# yet).
self.ftpcache = ftpcache
# Undocumented feature: you can use a different
# ftp cache by assigning to the .ftpcache member;
# in case you want logically independent URL openers
# XXX This is not threadsafe. Bah.
def __del__(self):
self.close()
def close(self):
self.cleanup()
def cleanup(self):
# This code sometimes runs when the rest of this module
# has already been deleted, so it can't use any globals
# or import anything.
if self.__tempfiles:
for file in self.__tempfiles:
try:
self.__unlink(file)
except OSError:
pass
del self.__tempfiles[:]
if self.tempcache:
self.tempcache.clear()
def addheader(self, *args):
"""Add a header to be used by the HTTP interface only
e.g. u.addheader('Accept', 'sound/basic')"""
self.addheaders.append(args)
# External interface
def open(self, fullurl, data=None):
"""Use URLopener().open(file) instead of open(file, 'r')."""
fullurl = unwrap(_to_bytes(fullurl))
fullurl = quote(fullurl, safe="%/:=&?~#+!$,;'@()*[]|")
if self.tempcache and fullurl in self.tempcache:
filename, headers = self.tempcache[fullurl]
fp = open(filename, 'rb')
return addinfourl(fp, headers, fullurl)
urltype, url = _splittype(fullurl)
if not urltype:
urltype = 'file'
if urltype in self.proxies:
proxy = self.proxies[urltype]
urltype, proxyhost = _splittype(proxy)
host, selector = _splithost(proxyhost)
url = (host, fullurl) # Signal special case to open_*()
else:
proxy = None
name = 'open_' + urltype
self.type = urltype
name = name.replace('-', '_')
if not hasattr(self, name) or name == 'open_local_file':
if proxy:
return self.open_unknown_proxy(proxy, fullurl, data)
else:
return self.open_unknown(fullurl, data)
try:
if data is None:
return getattr(self, name)(url)
else:
return getattr(self, name)(url, data)
except (HTTPError, URLError):
raise
except OSError as msg:
raise OSError('socket error', msg).with_traceback(sys.exc_info()[2])
def open_unknown(self, fullurl, data=None):
"""Overridable interface to open unknown URL type."""
type, url = _splittype(fullurl)
raise OSError('url error', 'unknown url type', type)
def open_unknown_proxy(self, proxy, fullurl, data=None):
"""Overridable interface to open unknown URL type."""
type, url = _splittype(fullurl)
raise OSError('url error', 'invalid proxy for %s' % type, proxy)
# External interface
def retrieve(self, url, filename=None, reporthook=None, data=None):
"""retrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object."""
url = unwrap(_to_bytes(url))
if self.tempcache and url in self.tempcache:
return self.tempcache[url]
type, url1 = _splittype(url)
if filename is None and (not type or type == 'file'):
try:
fp = self.open_local_file(url1)
hdrs = fp.info()
fp.close()
return url2pathname(_splithost(url1)[1]), hdrs
except OSError as msg:
pass
fp = self.open(url, data)
try:
headers = fp.info()
if filename:
tfp = open(filename, 'wb')
else:
garbage, path = _splittype(url)
garbage, path = _splithost(path or "")
path, garbage = _splitquery(path or "")
path, garbage = _splitattr(path or "")
suffix = os.path.splitext(path)[1]
(fd, filename) = tempfile.mkstemp(suffix)
self.__tempfiles.append(filename)
tfp = os.fdopen(fd, 'wb')
try:
result = filename, headers
if self.tempcache is not None:
self.tempcache[url] = result
bs = 1024*8
size = -1
read = 0
blocknum = 0
if "content-length" in headers:
size = int(headers["Content-Length"])
if reporthook:
reporthook(blocknum, bs, size)
while 1:
block = fp.read(bs)
if not block:
break
read += len(block)
tfp.write(block)
blocknum += 1
if reporthook:
reporthook(blocknum, bs, size)
finally:
tfp.close()
finally:
fp.close()
# raise exception if actual size does not match content-length header
if size >= 0 and read < size:
raise ContentTooShortError(
"retrieval incomplete: got only %i out of %i bytes"
% (read, size), result)
return result
# Each method named open_<type> knows how to open that type of URL
def _open_generic_http(self, connection_factory, url, data):
"""Make an HTTP connection using connection_class.
This is an internal method that should be called from
open_http() or open_https().
Arguments:
- connection_factory should take a host name and return an
HTTPConnection instance.
- url is the url to retrieval or a host, relative-path pair.
- data is payload for a POST request or None.
"""
user_passwd = None
proxy_passwd= None
if isinstance(url, str):
host, selector = _splithost(url)
if host:
user_passwd, host = _splituser(host)
host = unquote(host)
realhost = host
else:
host, selector = url
# check whether the proxy contains authorization information
proxy_passwd, host = _splituser(host)
# now we proceed with the url we want to obtain
urltype, rest = _splittype(selector)
url = rest
user_passwd = None
if urltype.lower() != 'http':
realhost = None
else:
realhost, rest = _splithost(rest)
if realhost:
user_passwd, realhost = _splituser(realhost)
if user_passwd:
selector = "%s://%s%s" % (urltype, realhost, rest)
if proxy_bypass(realhost):
host = realhost
if not host: raise OSError('http error', 'no host given')
if proxy_passwd:
proxy_passwd = unquote(proxy_passwd)
proxy_auth = base64.b64encode(proxy_passwd.encode()).decode('ascii')
else:
proxy_auth = None
if user_passwd:
user_passwd = unquote(user_passwd)
auth = base64.b64encode(user_passwd.encode()).decode('ascii')
else:
auth = None
http_conn = connection_factory(host)
headers = {}
if proxy_auth:
headers["Proxy-Authorization"] = "Basic %s" % proxy_auth
if auth:
headers["Authorization"] = "Basic %s" % auth
if realhost:
headers["Host"] = realhost
# Add Connection:close as we don't support persistent connections yet.
# This helps in closing the socket and avoiding ResourceWarning
headers["Connection"] = "close"
for header, value in self.addheaders:
headers[header] = value
if data is not None:
headers["Content-Type"] = "application/x-www-form-urlencoded"
http_conn.request("POST", selector, data, headers)
else:
http_conn.request("GET", selector, headers=headers)
try:
response = http_conn.getresponse()
except http.client.BadStatusLine:
# something went wrong with the HTTP status line
raise URLError("http protocol error: bad status line")
# According to RFC 2616, "2xx" code indicates that the client's
# request was successfully received, understood, and accepted.
if 200 <= response.status < 300:
return addinfourl(response, response.msg, "http:" + url,
response.status)
else:
return self.http_error(
url, response.fp,
response.status, response.reason, response.msg, data)
def open_http(self, url, data=None):
"""Use HTTP protocol."""
return self._open_generic_http(http.client.HTTPConnection, url, data)
def http_error(self, url, fp, errcode, errmsg, headers, data=None):
"""Handle http errors.
Derived class can override this, or provide specific handlers
named http_error_DDD where DDD is the 3-digit error code."""
# First check if there's a specific handler for this error
name = 'http_error_%d' % errcode
if hasattr(self, name):
method = getattr(self, name)
if data is None:
result = method(url, fp, errcode, errmsg, headers)
else:
result = method(url, fp, errcode, errmsg, headers, data)
if result: return result
return self.http_error_default(url, fp, errcode, errmsg, headers)
def http_error_default(self, url, fp, errcode, errmsg, headers):
"""Default error handler: close the connection and raise OSError."""
fp.close()
raise HTTPError(url, errcode, errmsg, headers, None)
if _have_ssl:
def _https_connection(self, host):
return http.client.HTTPSConnection(host,
key_file=self.key_file,
cert_file=self.cert_file)
def open_https(self, url, data=None):
"""Use HTTPS protocol."""
return self._open_generic_http(self._https_connection, url, data)
def open_file(self, url):
"""Use local file or FTP depending on form of URL."""
if not isinstance(url, str):
raise URLError('file error: proxy support for file protocol currently not implemented')
if url[:2] == '//' and url[2:3] != '/' and url[2:12].lower() != 'localhost/':
raise ValueError("file:// scheme is supported only on localhost")
else:
return self.open_local_file(url)
def open_local_file(self, url):
"""Use local file."""
import email.utils
import mimetypes
host, file = _splithost(url)
localname = url2pathname(file)
try:
stats = os.stat(localname)
except OSError as e:
raise URLError(e.strerror, e.filename)
size = stats.st_size
modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
mtype = mimetypes.guess_type(url)[0]
headers = email.message_from_string(
'Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' %
(mtype or 'text/plain', size, modified))
if not host:
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
return addinfourl(open(localname, 'rb'), headers, urlfile)
host, port = _splitport(host)
if (not port
and socket.gethostbyname(host) in ((localhost(),) + thishost())):
urlfile = file
if file[:1] == '/':
urlfile = 'file://' + file
elif file[:2] == './':
raise ValueError("local file url may start with / or file:. Unknown url of type: %s" % url)
return addinfourl(open(localname, 'rb'), headers, urlfile)
raise URLError('local file error: not on local host')
def open_ftp(self, url):
"""Use FTP protocol."""
if not isinstance(url, str):
raise URLError('ftp error: proxy support for ftp protocol currently not implemented')
import mimetypes
host, path = _splithost(url)
if not host: raise URLError('ftp error: no host given')
host, port = _splitport(host)
user, host = _splituser(host)
if user: user, passwd = _splitpasswd(user)
else: passwd = None
host = unquote(host)
user = unquote(user or '')
passwd = unquote(passwd or '')
host = socket.gethostbyname(host)
if not port:
import ftplib
port = ftplib.FTP_PORT
else:
port = int(port)
path, attrs = _splitattr(path)
path = unquote(path)
dirs = path.split('/')
dirs, file = dirs[:-1], dirs[-1]
if dirs and not dirs[0]: dirs = dirs[1:]
if dirs and not dirs[0]: dirs[0] = '/'
key = user, host, port, '/'.join(dirs)
# XXX thread unsafe!
if len(self.ftpcache) > MAXFTPCACHE:
# Prune the cache, rather arbitrarily
for k in list(self.ftpcache):
if k != key:
v = self.ftpcache[k]
del self.ftpcache[k]
v.close()
try:
if key not in self.ftpcache:
self.ftpcache[key] = \
ftpwrapper(user, passwd, host, port, dirs)
if not file: type = 'D'
else: type = 'I'
for attr in attrs:
attr, value = _splitvalue(attr)
if attr.lower() == 'type' and \
value in ('a', 'A', 'i', 'I', 'd', 'D'):
type = value.upper()
(fp, retrlen) = self.ftpcache[key].retrfile(file, type)
mtype = mimetypes.guess_type("ftp:" + url)[0]
headers = ""
if mtype:
headers += "Content-Type: %s\n" % mtype
if retrlen is not None and retrlen >= 0:
headers += "Content-Length: %d\n" % retrlen
headers = email.message_from_string(headers)
return addinfourl(fp, headers, "ftp:" + url)
except ftperrors() as exp:
raise URLError('ftp error %r' % exp).with_traceback(sys.exc_info()[2])
def open_data(self, url, data=None):
"""Use "data" URL."""
if not isinstance(url, str):
raise URLError('data error: proxy support for data protocol currently not implemented')
# ignore POSTed data
#
# syntax of data URLs:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
try:
[type, data] = url.split(',', 1)
except ValueError:
raise OSError('data error', 'bad data URL')
if not type:
type = 'text/plain;charset=US-ASCII'
semi = type.rfind(';')
if semi >= 0 and '=' not in type[semi:]:
encoding = type[semi+1:]
type = type[:semi]
else:
encoding = ''
msg = []
msg.append('Date: %s'%time.strftime('%a, %d %b %Y %H:%M:%S GMT',
time.gmtime(time.time())))
msg.append('Content-type: %s' % type)
if encoding == 'base64':
# XXX is this encoding/decoding ok?
data = base64.decodebytes(data.encode('ascii')).decode('latin-1')
else:
data = unquote(data)
msg.append('Content-Length: %d' % len(data))
msg.append('')
msg.append(data)
msg = '\n'.join(msg)
headers = email.message_from_string(msg)
f = io.StringIO(msg)
#f.fileno = None # needed for addinfourl
return addinfourl(f, headers, url)
class FancyURLopener(URLopener):
"""Derived class with handlers for errors we can handle (perhaps)."""
def __init__(self, *args, **kwargs):
URLopener.__init__(self, *args, **kwargs)
self.auth_cache = {}
self.tries = 0
self.maxtries = 10
def http_error_default(self, url, fp, errcode, errmsg, headers):
"""Default error handling -- don't raise an exception."""
return addinfourl(fp, headers, "http:" + url, errcode)
def http_error_302(self, url, fp, errcode, errmsg, headers, data=None):
"""Error 302 -- relocated (temporarily)."""
self.tries += 1
try:
if self.maxtries and self.tries >= self.maxtries:
if hasattr(self, "http_error_500"):
meth = self.http_error_500
else:
meth = self.http_error_default
return meth(url, fp, 500,
"Internal Server Error: Redirect Recursion",
headers)
result = self.redirect_internal(url, fp, errcode, errmsg,
headers, data)
return result
finally:
self.tries = 0
def redirect_internal(self, url, fp, errcode, errmsg, headers, data):
if 'location' in headers:
newurl = headers['location']
elif 'uri' in headers:
newurl = headers['uri']
else:
return
fp.close()
# In case the server sent a relative URL, join with original:
newurl = urljoin(self.type + ":" + url, newurl)
urlparts = urlparse(newurl)
# For security reasons, we don't allow redirection to anything other
# than http, https and ftp.
# We are using newer HTTPError with older redirect_internal method
# This older method will get deprecated in 3.3
if urlparts.scheme not in ('http', 'https', 'ftp', ''):
raise HTTPError(newurl, errcode,
errmsg +
" Redirection to url '%s' is not allowed." % newurl,
headers, fp)
return self.open(newurl)
def http_error_301(self, url, fp, errcode, errmsg, headers, data=None):
"""Error 301 -- also relocated (permanently)."""
return self.http_error_302(url, fp, errcode, errmsg, headers, data)
def http_error_303(self, url, fp, errcode, errmsg, headers, data=None):
"""Error 303 -- also relocated (essentially identical to 302)."""
return self.http_error_302(url, fp, errcode, errmsg, headers, data)
def http_error_307(self, url, fp, errcode, errmsg, headers, data=None):
"""Error 307 -- relocated, but turn POST into error."""
if data is None:
return self.http_error_302(url, fp, errcode, errmsg, headers, data)
else:
return self.http_error_default(url, fp, errcode, errmsg, headers)
def http_error_401(self, url, fp, errcode, errmsg, headers, data=None,
retry=False):
"""Error 401 -- authentication required.
This function supports Basic authentication only."""
if 'www-authenticate' not in headers:
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
stuff = headers['www-authenticate']
match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
if not match:
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
scheme, realm = match.groups()
if scheme.lower() != 'basic':
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
if not retry:
URLopener.http_error_default(self, url, fp, errcode, errmsg,
headers)
name = 'retry_' + self.type + '_basic_auth'
if data is None:
return getattr(self,name)(url, realm)
else:
return getattr(self,name)(url, realm, data)
def http_error_407(self, url, fp, errcode, errmsg, headers, data=None,
retry=False):
"""Error 407 -- proxy authentication required.
This function supports Basic authentication only."""
if 'proxy-authenticate' not in headers:
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
stuff = headers['proxy-authenticate']
match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
if not match:
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
scheme, realm = match.groups()
if scheme.lower() != 'basic':
URLopener.http_error_default(self, url, fp,
errcode, errmsg, headers)
if not retry:
URLopener.http_error_default(self, url, fp, errcode, errmsg,
headers)
name = 'retry_proxy_' + self.type + '_basic_auth'
if data is None:
return getattr(self,name)(url, realm)
else:
return getattr(self,name)(url, realm, data)
def retry_proxy_http_basic_auth(self, url, realm, data=None):
host, selector = _splithost(url)
newurl = 'http://' + host + selector
proxy = self.proxies['http']
urltype, proxyhost = _splittype(proxy)
proxyhost, proxyselector = _splithost(proxyhost)
i = proxyhost.find('@') + 1
proxyhost = proxyhost[i:]
user, passwd = self.get_user_passwd(proxyhost, realm, i)
if not (user or passwd): return None
proxyhost = "%s:%s@%s" % (quote(user, safe=''),
quote(passwd, safe=''), proxyhost)
self.proxies['http'] = 'http://' + proxyhost + proxyselector
if data is None:
return self.open(newurl)
else:
return self.open(newurl, data)
def retry_proxy_https_basic_auth(self, url, realm, data=None):
host, selector = _splithost(url)
newurl = 'https://' + host + selector
proxy = self.proxies['https']
urltype, proxyhost = _splittype(proxy)
proxyhost, proxyselector = _splithost(proxyhost)
i = proxyhost.find('@') + 1
proxyhost = proxyhost[i:]
user, passwd = self.get_user_passwd(proxyhost, realm, i)
if not (user or passwd): return None
proxyhost = "%s:%s@%s" % (quote(user, safe=''),
quote(passwd, safe=''), proxyhost)
self.proxies['https'] = 'https://' + proxyhost + proxyselector
if data is None:
return self.open(newurl)
else:
return self.open(newurl, data)
def retry_http_basic_auth(self, url, realm, data=None):
host, selector = _splithost(url)
i = host.find('@') + 1
host = host[i:]
user, passwd = self.get_user_passwd(host, realm, i)
if not (user or passwd): return None
host = "%s:%s@%s" % (quote(user, safe=''),
quote(passwd, safe=''), host)
newurl = 'http://' + host + selector
if data is None:
return self.open(newurl)
else:
return self.open(newurl, data)
def retry_https_basic_auth(self, url, realm, data=None):
host, selector = _splithost(url)
i = host.find('@') + 1
host = host[i:]
user, passwd = self.get_user_passwd(host, realm, i)
if not (user or passwd): return None
host = "%s:%s@%s" % (quote(user, safe=''),
quote(passwd, safe=''), host)
newurl = 'https://' + host + selector
if data is None:
return self.open(newurl)
else:
return self.open(newurl, data)
def get_user_passwd(self, host, realm, clear_cache=0):
key = realm + '@' + host.lower()
if key in self.auth_cache:
if clear_cache:
del self.auth_cache[key]
else:
return self.auth_cache[key]
user, passwd = self.prompt_user_passwd(host, realm)
if user or passwd: self.auth_cache[key] = (user, passwd)
return user, passwd
def prompt_user_passwd(self, host, realm):
"""Override this in a GUI environment!"""
import getpass
try:
user = input("Enter username for %s at %s: " % (realm, host))
passwd = getpass.getpass("Enter password for %s in %s at %s: " %
(user, realm, host))
return user, passwd
except KeyboardInterrupt:
print()
return None, None
# Utility functions
_localhost = None
def localhost():
"""Return the IP address of the magic hostname 'localhost'."""
global _localhost
if _localhost is None:
_localhost = socket.gethostbyname('localhost')
return _localhost
_thishost = None
def thishost():
"""Return the IP addresses of the current host."""
global _thishost
if _thishost is None:
try:
_thishost = tuple(socket.gethostbyname_ex(socket.gethostname())[2])
except socket.gaierror:
_thishost = tuple(socket.gethostbyname_ex('localhost')[2])
return _thishost
_ftperrors = None
def ftperrors():
"""Return the set of errors raised by the FTP class."""
global _ftperrors
if _ftperrors is None:
import ftplib
_ftperrors = ftplib.all_errors
return _ftperrors
_noheaders = None
def noheaders():
"""Return an empty email Message object."""
global _noheaders
if _noheaders is None:
_noheaders = email.message_from_string("")
return _noheaders
# Utility classes
class ftpwrapper:
"""Class used by open_ftp() for cache of open FTP connections."""
def __init__(self, user, passwd, host, port, dirs, timeout=None,
persistent=True):
self.user = user
self.passwd = passwd
self.host = host
self.port = port
self.dirs = dirs
self.timeout = timeout
self.refcount = 0
self.keepalive = persistent
try:
self.init()
except:
self.close()
raise
def init(self):
import ftplib
self.busy = 0
self.ftp = ftplib.FTP()
self.ftp.connect(self.host, self.port, self.timeout)
self.ftp.login(self.user, self.passwd)
_target = '/'.join(self.dirs)
self.ftp.cwd(_target)
def retrfile(self, file, type):
import ftplib
self.endtransfer()
if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1
else: cmd = 'TYPE ' + type; isdir = 0
try:
self.ftp.voidcmd(cmd)
except ftplib.all_errors:
self.init()
self.ftp.voidcmd(cmd)
conn = None
if file and not isdir:
# Try to retrieve as a file
try:
cmd = 'RETR ' + file
conn, retrlen = self.ftp.ntransfercmd(cmd)
except ftplib.error_perm as reason:
if str(reason)[:3] != '550':
raise URLError('ftp error: %r' % reason).with_traceback(
sys.exc_info()[2])
if not conn:
# Set transfer mode to ASCII!
self.ftp.voidcmd('TYPE A')
# Try a directory listing. Verify that directory exists.
if file:
pwd = self.ftp.pwd()
try:
try:
self.ftp.cwd(file)
except ftplib.error_perm as reason:
raise URLError('ftp error: %r' % reason) from reason
finally:
self.ftp.cwd(pwd)
cmd = 'LIST ' + file
else:
cmd = 'LIST'
conn, retrlen = self.ftp.ntransfercmd(cmd)
self.busy = 1
ftpobj = addclosehook(conn.makefile('rb'), self.file_close)
self.refcount += 1
conn.close()
# Pass back both a suitably decorated object and a retrieval length
return (ftpobj, retrlen)
def endtransfer(self):
self.busy = 0
def close(self):
self.keepalive = False
if self.refcount <= 0:
self.real_close()
def file_close(self):
self.endtransfer()
self.refcount -= 1
if self.refcount <= 0 and not self.keepalive:
self.real_close()
def real_close(self):
self.endtransfer()
try:
self.ftp.close()
except ftperrors():
pass
# Proxy handling
def getproxies_environment():
"""Return a dictionary of scheme -> proxy server URL mappings.
Scan the environment for variables named <scheme>_proxy;
this seems to be the standard convention. If you need a
different way, you can pass a proxies dictionary to the
[Fancy]URLopener constructor.
"""
proxies = {}
# in order to prefer lowercase variables, process environment in
# two passes: first matches any, second pass matches lowercase only
for name, value in os.environ.items():
name = name.lower()
if value and name[-6:] == '_proxy':
proxies[name[:-6]] = value
# CVE-2016-1000110 - If we are running as CGI script, forget HTTP_PROXY
# (non-all-lowercase) as it may be set from the web server by a "Proxy:"
# header from the client
# If "proxy" is lowercase, it will still be used thanks to the next block
if 'REQUEST_METHOD' in os.environ:
proxies.pop('http', None)
for name, value in os.environ.items():
if name[-6:] == '_proxy':
name = name.lower()
if value:
proxies[name[:-6]] = value
else:
proxies.pop(name[:-6], None)
return proxies
def proxy_bypass_environment(host, proxies=None):
"""Test if proxies should not be used for a particular host.
Checks the proxy dict for the value of no_proxy, which should
be a list of comma separated DNS suffixes, or '*' for all hosts.
"""
if proxies is None:
proxies = getproxies_environment()
# don't bypass, if no_proxy isn't specified
try:
no_proxy = proxies['no']
except KeyError:
return False
# '*' is special case for always bypass
if no_proxy == '*':
return True
host = host.lower()
# strip port off host
hostonly, port = _splitport(host)
# check if the host ends with any of the DNS suffixes
for name in no_proxy.split(','):
name = name.strip()
if name:
name = name.lstrip('.') # ignore leading dots
name = name.lower()
if hostonly == name or host == name:
return True
name = '.' + name
if hostonly.endswith(name) or host.endswith(name):
return True
# otherwise, don't bypass
return False
# This code tests an OSX specific data structure but is testable on all
# platforms
def _proxy_bypass_macosx_sysconf(host, proxy_settings):
"""
Return True iff this host shouldn't be accessed using a proxy
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
{ 'exclude_simple': bool,
'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
}
"""
from fnmatch import fnmatch
hostonly, port = _splitport(host)
def ip2num(ipAddr):
parts = ipAddr.split('.')
parts = list(map(int, parts))
if len(parts) != 4:
parts = (parts + [0, 0, 0, 0])[:4]
return (parts[0] << 24) | (parts[1] << 16) | (parts[2] << 8) | parts[3]
# Check for simple host names:
if '.' not in host:
if proxy_settings['exclude_simple']:
return True
hostIP = None
for value in proxy_settings.get('exceptions', ()):
# Items in the list are strings like these: *.local, 169.254/16
if not value: continue
m = re.match(r"(\d+(?:\.\d+)*)(/\d+)?", value)
if m is not None:
if hostIP is None:
try:
hostIP = socket.gethostbyname(hostonly)
hostIP = ip2num(hostIP)
except OSError:
continue
base = ip2num(m.group(1))
mask = m.group(2)
if mask is None:
mask = 8 * (m.group(1).count('.') + 1)
else:
mask = int(mask[1:])
if mask < 0 or mask > 32:
# System libraries ignore invalid prefix lengths
continue
mask = 32 - mask
if (hostIP >> mask) == (base >> mask):
return True
elif fnmatch(host, value):
return True
return False
if sys.platform == 'darwin':
from _scproxy import _get_proxy_settings, _get_proxies
def proxy_bypass_macosx_sysconf(host):
proxy_settings = _get_proxy_settings()
return _proxy_bypass_macosx_sysconf(host, proxy_settings)
def getproxies_macosx_sysconf():
"""Return a dictionary of scheme -> proxy server URL mappings.
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
"""
return _get_proxies()
def proxy_bypass(host):
"""Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or from the MacOSX framework SystemConfiguration.
"""
proxies = getproxies_environment()
if proxies:
return proxy_bypass_environment(host, proxies)
else:
return proxy_bypass_macosx_sysconf(host)
def getproxies():
return getproxies_environment() or getproxies_macosx_sysconf()
elif os.name == 'nt':
def getproxies_registry():
"""Return a dictionary of scheme -> proxy server URL mappings.
Win32 uses the registry to store proxies.
"""
proxies = {}
try:
import winreg
except ImportError:
# Std module, so should be around - but you never know!
return proxies
try:
internetSettings = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
r'Software\Microsoft\Windows\CurrentVersion\Internet Settings')
proxyEnable = winreg.QueryValueEx(internetSettings,
'ProxyEnable')[0]
if proxyEnable:
# Returned as Unicode but problems if not converted to ASCII
proxyServer = str(winreg.QueryValueEx(internetSettings,
'ProxyServer')[0])
if '=' in proxyServer:
# Per-protocol settings
for p in proxyServer.split(';'):
protocol, address = p.split('=', 1)
# See if address has a type:// prefix
if not re.match('(?:[^/:]+)://', address):
address = '%s://%s' % (protocol, address)
proxies[protocol] = address
else:
# Use one setting for all protocols
if proxyServer[:5] == 'http:':
proxies['http'] = proxyServer
else:
proxies['http'] = 'http://%s' % proxyServer
proxies['https'] = 'https://%s' % proxyServer
proxies['ftp'] = 'ftp://%s' % proxyServer
internetSettings.Close()
except (OSError, ValueError, TypeError):
# Either registry key not found etc, or the value in an
# unexpected format.
# proxies already set up to be empty so nothing to do
pass
return proxies
def getproxies():
"""Return a dictionary of scheme -> proxy server URL mappings.
Returns settings gathered from the environment, if specified,
or the registry.
"""
return getproxies_environment() or getproxies_registry()
def proxy_bypass_registry(host):
try:
import winreg
except ImportError:
# Std modules, so should be around - but you never know!
return 0
try:
internetSettings = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
r'Software\Microsoft\Windows\CurrentVersion\Internet Settings')
proxyEnable = winreg.QueryValueEx(internetSettings,
'ProxyEnable')[0]
proxyOverride = str(winreg.QueryValueEx(internetSettings,
'ProxyOverride')[0])
# ^^^^ Returned as Unicode but problems if not converted to ASCII
except OSError:
return 0
if not proxyEnable or not proxyOverride:
return 0
# try to make a host list from name and IP address.
rawHost, port = _splitport(host)
host = [rawHost]
try:
addr = socket.gethostbyname(rawHost)
if addr != rawHost:
host.append(addr)
except OSError:
pass
try:
fqdn = socket.getfqdn(rawHost)
if fqdn != rawHost:
host.append(fqdn)
except OSError:
pass
# make a check value list from the registry entry: replace the
# '<local>' string by the localhost entry and the corresponding
# canonical entry.
proxyOverride = proxyOverride.split(';')
# now check if we match one of the registry values.
for test in proxyOverride:
if test == '<local>':
if '.' not in rawHost:
return 1
test = test.replace(".", r"\.") # mask dots
test = test.replace("*", r".*") # change glob sequence
test = test.replace("?", r".") # change glob char
for val in host:
if re.match(test, val, re.I):
return 1
return 0
def proxy_bypass(host):
"""Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
"""
proxies = getproxies_environment()
if proxies:
return proxy_bypass_environment(host, proxies)
else:
return proxy_bypass_registry(host)
else:
# By default use environment variables
getproxies = getproxies_environment
proxy_bypass = proxy_bypass_environment
PK (�Z��P2� � ) __pycache__/response.cpython-36.opt-1.pycnu �[��� 3
\� � @ s^ d Z ddlZddddgZG dd� dej�ZG dd� de�ZG d d� de�ZG d
d� de�ZdS ) a Response classes used by urllib.
The base class, addbase, defines a minimal file-like interface,
including read() and readline(). The typical response object is an
addinfourl instance, which defines an info() method that returns
headers and a geturl() method that returns the url.
� N�addbase� addclosehook�addinfo�
addinfourlc s8 e Zd ZdZ� fdd�Zdd� Zdd� Zdd � Z� ZS )
r zOBase class for addinfo and addclosehook. Is a good idea for garbage collection.c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr )� __class__� �'/usr/lib64/python3.6/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file)r
r r r
�__repr__ s zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueError)r
r r r
� __enter__ s zaddbase.__enter__c C s | j � d S )N)�close)r
�type�value� tracebackr r r
�__exit__! s zaddbase.__exit__) r �
__module__� __qualname__�__doc__r r r r �
__classcell__r r )r r
r s
c s, e Zd ZdZ� fdd�Z� fdd�Z� ZS )r z*Class to add a close hook to an open file.c s t t| �j|� || _|| _d S )N)r r r � closehook�hookargs)r
r r r )r r r
r ( s zaddclosehook.__init__c s> z(| j }| j}|r&d | _ d | _||� W d tt| �j� X d S )N)r r r r r )r
r r )r r r
r - s zaddclosehook.close)r r r r r r r r r )r r
r % s c s( e Zd ZdZ� fdd�Zdd� Z� ZS )r z.class to add an info() method to an open file.c s t t| �j|� || _d S )N)r r r �headers)r
r r )r r r
r < s zaddinfo.__init__c C s | j S )N)r )r
r r r
�info@ s z addinfo.info)r r r r r r! r r r )r r
r 9 s c s2 e Zd ZdZd � fdd� Zdd� Zdd� Z� ZS )
r z9class to add info() and geturl() methods to an open file.Nc s" t t| �j||� || _|| _d S )N)r r r �url�code)r
r r r" r# )r r r
r G s zaddinfourl.__init__c C s | j S )N)r# )r
r r r
�getcodeL s zaddinfourl.getcodec C s | j S )N)r" )r
r r r
�geturlO s zaddinfourl.geturl)N)r r r r r r$ r% r r r )r r
r D s )r Ztempfile�__all__Z_TemporaryFileWrapperr r r r r r r r
�<module> s PK (�Z�
�� � & __pycache__/robotparser.cpython-36.pycnu �[��� 3
\�" � @ s\ d Z ddlZddlZddlZdgZejdd�ZG dd� d�ZG dd� d�Z G d d
� d
�Z
dS ) a% robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://www.robotstxt.org/norobots-rfc.txt
� N�RobotFileParser� RequestRatezrequests secondsc @ sj e Zd ZdZddd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� ZdS )r zs This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
� c C s, g | _ d | _d| _d| _| j|� d| _d S )NFr )�entries�
default_entry� disallow_all� allow_all�set_url� last_checked)�self�url� r
�*/usr/lib64/python3.6/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S )z�Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
)r
)r r
r
r �mtime$ s zRobotFileParser.mtimec C s ddl }|j � | _dS )zYSets the time the robots.txt file was last fetched to the
current time.
r N)�timer
)r r r
r
r �modified- s zRobotFileParser.modifiedc C s& || _ tjj|�dd� \| _| _dS )z,Sets the URL referring to a robots.txt file.� � N)r �urllib�parse�urlparse�host�path)r r r
r
r r 5 s zRobotFileParser.set_urlc C s� yt jj| j�}W nR t jjk
rd } z2|jdkr:d| _n|jdkrT|jdk rTd| _W Y dd}~X n X |j � }| j
|j d�j � � dS ) z4Reads the robots.txt URL and feeds it to the parser.� � Ti� i� Nzutf-8)r r )
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r �f�err�rawr
r
r r : s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | jj|� d S )N�*)�
useragentsr r �append)r �entryr
r
r �
_add_entryG s
zRobotFileParser._add_entryc C s6 d}t � }| j� �x|D �]�}|sT|dkr8t � }d}n |dkrT| j|� t � }d}|jd�}|dkrr|d|� }|j� }|s�q|jdd�}t|�dkr|d j� j� |d< tj j
|d j� �|d< |d dk�r |dkr�| j|� t � }|j j |d � d}q|d dk�r4|dk�r|j
j t|d d �� d}q|d d
k�rh|dk�r|j
j t|d d �� d}q|d d k�r�|dk�r|d j� j� �r�t|d �|_d}q|d d
kr|dkr|d jd�}t|�dk�r|d j� j� �r|d j� j� �rtt|d �t|d ��|_d}qW |dk�r2| j|� dS )z�Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
r r � �#N�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/)�Entryr r( �find�strip�split�len�lowerr r �unquoter% r& � rulelines�RuleLine�isdigit�int�delayr �req_rate)r �lines�stater' �line�iZnumbersr
r
r r P sd
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tjjtjj|��}tjjdd|j|j |j
|j f�}tjj |�}|sfd}x"| j
D ]}|j|�rn|j|�S qnW | jr�| jj|�S dS )z=using the parsed robots.txt decide if useragent can fetch urlFTr r, )r r r
r r r r3 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r � useragentr Z
parsed_urlr' r
r
r � can_fetch� s$
zRobotFileParser.can_fetchc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r8 r )r rB r' r
r
r � crawl_delay� s
zRobotFileParser.crawl_delayc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r9 r )r rB r' r
r
r � request_rate� s
z RobotFileParser.request_ratec C s0 | j }| jd k r || jg }djtt|��d S )N�
)r r �join�map�str)r r r
r
r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__�__doc__r r r r r r( r rC rD rE rJ r
r
r
r r s
C c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r5 zoA rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path.c C s> |dkr| rd}t jjt jj|��}t jj|�| _|| _d S )Nr T)r r r> r r? r rA )r r rA r
r
r r � s
zRuleLine.__init__c C s | j dkp|j| j �S )Nr$ )r �
startswith)r �filenamer
r
r r@ � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rA r )r r
r
r rJ � s zRuleLine.__str__N)rK rL rM rN r r@ rJ r
r
r
r r5 � s r5 c @ s0 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd
S ) r- z?An entry has one or more user-agents and zero or more rulelinesc C s g | _ g | _d | _d | _d S )N)r% r4 r8 r9 )r r
r
r r � s zEntry.__init__c C s� g }x | j D ]}|jd|� �� q W | jd k r@|jd| j� �� | jd k rj| j}|jd|j� d|j� �� |jtt| j �� |jd� dj
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r, r rF ) r% r& r8 r9 ZrequestsZseconds�extendrH rI r4 rG )r Zret�agentZrater
r
r rJ � s
z
Entry.__str__c C sF |j d�d j� }x.| jD ]$}|dkr*dS |j� }||krdS qW dS )z2check if this entry applies to the specified agentr, r r$ TF)r0 r2 r% )r rB rR r
r
r r@ � s zEntry.applies_toc C s$ x | j D ]}|j|�r|jS qW dS )zZPreconditions:
- our agent applies to this entry
- filename is URL decodedT)r4 r@ rA )r rP r< r
r
r rA � s
zEntry.allowanceN)rK rL rM rN r rJ r@ rA r
r
r
r r- � s
r- ) rN � collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r5 r- r
r
r
r �<module> s 2PK (�Z��
z z ) __pycache__/__init__.cpython-36.opt-2.pycnu �[��� 3
�]dh � @ s d S )N� r r r �'/usr/lib64/python3.6/urllib/__init__.py�<module> s PK (�Z��d��
�
& __pycache__/error.cpython-36.opt-1.pycnu �[��� 3
\Q
� @ sP d Z ddlZdddgZG dd� de�ZG dd� deejj�ZG dd� de�Z dS ) a� Exception classes raised by urllib.
The base exception class is URLError, which inherits from OSError. It
doesn't define any behavior of its own, but is the base class for all
exceptions defined in this package.
HTTPError is an exception class that is also a valid HTTP response
instance. It behaves this way because HTTP protocol errors are valid
responses, with a status code, headers, and a body. In some contexts,
an application may want to handle an exception like a regular
response.
� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S )N)�args�reason�filename)�selfr r � r �$/usr/lib64/python3.6/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r )r r r r
�__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r r r r
r s
c @ sX e Zd ZdZejjjZdd� Zdd� Z dd� Z
e dd � �Z e d
d � �Z
e
jd d � �Z
d
S )r zBRaised when HTTP error occurs, but also acts like non-error returnc C s: || _ || _|| _|| _|| _|d k r6| j||||� d S )N)�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r r r
r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s)r r )r r r r
r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>)r r )r r r r
�__repr__7 s zHTTPError.__repr__c C s | j S )N)r )r r r r
r < s zHTTPError.reasonc C s | j S )N)r )r r r r
�headers@ s zHTTPError.headersc C s
|| _ d S )N)r )r r r r r
r D s N)r
r r �__doc__�urllib�response�
addinfourlr r r r �propertyr r �setterr r r r
r # s
c @ s e Zd ZdZdd� ZdS )r zDException raised when downloaded size does not match content-length.c C s t j| |� || _d S )N)r r �content)r �messager r r r
r K s z ContentTooShortError.__init__N)r
r r r r r r r r
r I s )
r Zurllib.responser �__all__�OSErrorr r r r r r r r r
�<module> s
&PK (�ZZ� " __pycache__/request.cpython-36.pycnu �[��� 3
�\dh~� � ) @ s� d Z ddlZddlZddlZddlZddlZddlZddlZddl Z ddl
Z
ddl Z ddl Z ddl
Z
ddlZddlZddlZddlZddlZddlmZmZmZ ddlmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, y ddl-Z-W n e.k
�r& dZ/Y nX dZ/dd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'd(g!Z0d)e
j1dd*� Z2da3de j4fddddd+�d,d �Z5d-d � Z6g Z7d~d.d%�Z8d/d&� Z9e
j:d0e
j;�Z<d1d2� Z=G d3d� d�Z>G d4d � d �Z?d5d!� Z@G d6d
� d
�ZAG d7d � d eA�ZBG d8d � d eA�ZCG d9d � d eA�ZDd:d;� ZEG d<d� deA�ZFG d=d� d�ZGG d>d� deG�ZHG d?d� deH�ZIG d@d� d�ZJG dAd� deJeA�ZKG dBd� deJeA�ZLejMZNG dCd� d�ZOG dDd� deAeO�ZPG dEd� deAeO�ZQG dFdG� dGeA�ZRG dHd� deR�ZSeTejUdI��r2G dJdK� dKeR�ZVe0jWdK� G dLd
� d
eA�ZXG dMd � d eA�ZYdNdO� ZZdPdQ� Z[G dRd� deA�Z\dSdT� Z]G dUd� deA�Z^G dVd� de^�Z_G dWd � d eA�Z`dXZaejbdYk�r�ddZlcmdZdmeZe nd[d#� Zdd\d"� Zei ZfG d]d'� d'�ZgG d^d(� d(eg�Zhdaid_d`� Zjdakdadb� Zldamdcdd� Zndaodedf� ZpG dgdh� dh�Zqdidj� Zrddkdl�Zsdmdn� Zte
judok�r�ddplvmwZwmxZx dqdr� Zydsdt� Zzdudv� Z{dwd$� Z|n6ejbdYk�r�dxdy� Z}dzd$� Z|d{d|� Z~d}dv� Z{nerZ|esZ{dS )�a�
An extensible library for opening URLs using a variety of protocols
The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below). It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.
The OpenerDirector manages a collection of Handler objects that do
all the actual work. Each Handler implements a particular protocol or
option. The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL. For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns. The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.
urlopen(url, data=None) -- Basic usage is the same as original
urllib. pass the url and optionally data to post to an HTTP URL, and
get a file-like object back. One difference is that you can also pass
a Request instance instead of URL. Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.
build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers. Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate. If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.
install_opener -- Installs a new opener as the default opener.
objects of interest:
OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.
Request -- An object that encapsulates the state of a request. The
state can be as simple as the URL. It can also include extra HTTP
headers, e.g. a User-Agent.
BaseHandler --
internals:
BaseHandler and parent
_call_chain conventions
Example usage:
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
uri='https://mahler:8092/site-updates.py',
user='klem',
passwd='geheim$parole')
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote� splittype� splithost� splitport� splituser� splitpasswd� splitattr�
splitquery�
splitvalue�splittag�to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfddl }|jdtd� |dk r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt dkr�t
� a } nt } | j | ||�S ) a$
Open the URL url, which can be either a string or a Request object.
*data* must be an object specifying additional data to be sent to
the server, or None if no such data is needed. See Request for
details.
urllib.request module uses HTTP/1.1 and includes a "Connection:close"
header in its HTTP requests.
The optional *timeout* parameter specifies a timeout in seconds for
blocking operations like the connection attempt (if not specified, the
global default timeout setting will be used). This only works for HTTP,
HTTPS and FTP connections.
If *context* is specified, it must be a ssl.SSLContext instance describing
the various SSL options. See HTTPSConnection for more details.
The optional *cafile* and *capath* parameters specify a set of trusted CA
certificates for HTTPS requests. cafile should point to a single file
containing a bundle of CA certificates, whereas capath should point to a
directory of hashed certificate files. More information can be found in
ssl.SSLContext.load_verify_locations().
The *cadefault* parameter is ignored.
This function always returns an object which can work as a context
manager and has methods such as
* geturl() - return the URL of the resource retrieved, commonly used to
determine if a redirect was followed
* info() - return the meta-information of the page, such as headers, in the
form of an email.message_from_string() instance (see Quick Reference to
HTTP Headers)
* getcode() - return the HTTP status code of the response. Raises URLError
on errors.
For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse
object slightly modified. In addition to the three new methods above, the
msg attribute contains the same information as the reason attribute ---
the reason phrase returned by the server --- instead of the response
headers as it is specified in the documentation for HTTPResponse.
For FTP, file, and data URLs and requests explicitly handled by legacy
URLopener and FancyURLopener classes, this function returns a
urllib.response.addinfourl object.
Note that None may be returned if no handler handles the request (though
the default installed global OpenerDirector uses UnknownHandler to ensure
this never happens).
In addition, if proxy settings are detected (for example, when a *_proxy
environment variable like http_proxy is set), ProxyHandler is default
installed and makes sure the requests are handled through the proxy.
r NzJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.6/urllib/request.pyr0 � s* <
c C s | a d S )N)rF )rK rL rL rM r1 � s c C s4 t | �\}}tjt| |����}|j� }|dkrD| rDtjj|�|fS |rTt|d�}n t j
dd�}|j }t j
|� |�� ||f} d
}
d} d} d}
d |kr�t|d
�} |r�||
|
| � xB|j|
�}|s�P | t|�7 } |j|� |
d7 }
|r�||
|
| � q�W W d Q R X W d Q R X | dk�r0| | k �r0td | | f | ��| S )aW
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
�file�wbF)�deletei � � r zcontent-lengthzContent-LengthNz1retrieval incomplete: got only %i out of %i bytesi ���)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typerX �fp�headers�tfp�result�bs�sizer_ �blocknum�blockrL rL rM r6 � sD
$c C sH x0t D ](} ytj| � W q tk
r, Y qX qW t dd�= trDdadS )z0Clean up temporary files from urlretrieve calls.N)r\ rW �unlink�OSErrorrF )Z temp_filerL rL rM r7 % s
z:\d+$c C s< | j }t|�d }|dkr&| jdd�}tjd|d�}|j� S )z�Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
rR � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host4 s rw c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sp || _ i | _i | _d | _|| _d | _x |j� D ]\}}| j||� q.W |d krVt| �}|| _ || _
|rl|| _ d S )N) rp re �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerrw �origin_req_host� unverifiable�method) �selfrH rI re r} r~ r �key�valuerL rL rM �__init__F s zRequest.__init__c C s | j rdj| j| j �S | jS )Nz{}#{})�fragment�format� _full_url)r� rL rL rM rp X s zRequest.full_urlc C s( t |�| _t| j�\| _| _| j� d S )N)r r� r r� �_parse)r� rH rL rL rM rp ^ s
c C s d | _ d | _d| _d S )Nrn )r� r� �selector)r� rL rL rM rp e s c C s | j S )N)ry )r� rL rL rM rI k s z Request.datac C s( || j kr$|| _ | jd�r$| jd� d S )NzContent-length)ry �
has_header�
remove_header)r� rI rL rL rM rI o s
c C s
d | _ d S )N)rI )r� rL rL rM rI y s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rp r rv r� r
)r� �restrL rL rM r� } s
zRequest._parsec C s | j dk rdnd}t| d|�S )z3Return a string indicating the HTTP request method.N�POST�GETr )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S )N)rp )r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s4 | j dkr | j r | j| _n|| _ | j| _|| _d S )N�https)r� rz rv rp r� )r� rv r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS )N)r� rp )r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |j� < d S )N)re �
capitalize)r� r� �valrL rL rM r| � s zRequest.add_headerc C s || j |j� < d S )N)rx r� )r� r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS )N)re rx )r� � header_namerL rL rM r� � s
zRequest.has_headerc C s | j j|| jj||��S )N)re �getrx )r� r� �defaultrL rL rM rq � s zRequest.get_headerc C s | j j|d � | jj|d � d S )N)re �poprx )r� r� rL rL rM r� � s zRequest.remove_headerc C s" | j j� }|j| j� t|j� �S )N)rx �copy�updatere �listr{ )r� �hdrsrL rL rM � header_items� s
zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrp �setter�deleterrI r� r� r� r� r� r| r� r� rq r� r� rL rL rL rM r D s(
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )NzPython-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sZ t |d�stdt|� ��d}�xt|�D �]}|dkr:q*|jd�}|d |� }||d d � }|jd �r�|jd�| d }||d d � }y t|�}W n tk
r� Y nX | jj |i �} | | j|< n>|d
kr�|}| j
} n*|d kr�|}| j } n|d kr*|}| j } nq*| j
|g �}
|
�r&tj|
|� n
|
j|� d
}q*W |�rVtj| j|� |j| � d S )N�
add_parentz%expected BaseHandler instance, got %rF�redirect_request�do_open�
proxy_open�_rR �errorrG �responseru T)r� r� r� )�hasattr� TypeErrorr� �dir�find�
startswithr^ rB r� r� r� r� r� �
setdefault�bisectZinsortr] r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sJ
zOpenerDirector.add_handlerc C s d S )NrL )r� rL rL rM �close� s zOpenerDirector.closec G s< |j |f �}x*|D ]"}t||�}||� }|d k r|S qW d S )N)r� r� ) r� �chainr� � meth_name�argsr� r� �funcrg rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }x(| jj|g �D ]}t||�}||�}qLW | j ||�} |d }x*| j
j|g �D ]}t||�}||| �} q�W | S )NZ_requestZ _response) �
isinstance�strr rI rJ r� r� r� r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s"
zOpenerDirector.openc C sP | j | jdd|�}|r|S |j}| j | j||d |�}|r>|S | j | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rg r� rL rL rM r� s
zOpenerDirector._openc G s~ |d
kr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S ) N�httpr� r: z
http_error_%srR Z_errorr r� �http_error_default)r� r� )r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrg rL rL rM r� ' s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|j
t� t� }xN|D ]F}x@| D ]8}t|t�rlt||�r�|j|� qHt||�rH|j|� qHW q>W x|D ]}|j|� q�W x|D ]}|j|� � q�W x&| D ] }t|t�r�|� }|j|� q�W |S )a* Create an opener object from a list of handlers.
The opener will use several default handlers, including support
for HTTP, FTP and when applicable HTTPS.
If any of the handlers passed as arguments are subclasses of the
default handlers, the default handlers will not be used.
�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientr] rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 @ s0
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r i� c C s
|| _ d S )N)�parent)r� r� rL rL rM r� g s zBaseHandler.add_parentc C s d S )NrL )r� rL rL rM r� j s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__n s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r d s c @ s e Zd ZdZdZdd� ZeZdS )r/ z Process HTTP error responses.i� c C sJ |j |j|j� }}}d| ko*dk n sF| jjd|||||�}|S )N�� i, r� )�code�msgrV r� r� )r� ru r� r� r� r� rL rL rM �
http_response{ s
z HTTPErrorProcessor.http_responseN)r� r� r� �__doc__r� r� �https_responserL rL rL rM r/ w s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S )N)r rp )r� r� rd r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c sx |j � }|dkr|dkp&|dko&|dks:t|j||||��|jdd �}d� t� fd d
�|jj� D ��}t|||jdd�S )a� Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
�- �. �/ �3 r� �HEADr� � z%20�content-length� content-typec 3 s& | ] \}}|j � � kr||fV qd S )N)rt )�.0�k�v)�CONTENT_HEADERSrL rM � <genexpr>� s z7HTTPRedirectHandler.redirect_request.<locals>.<genexpr>T)re r} r~ )r� r� r� r� )r� r� )r� r� r� )r� r� ) r� r rp �replacer� re r{ r r} ) r� r� rd r� r� re �newurl�mZ
newheadersrL )r� rM r� � s
z$HTTPRedirectHandler.redirect_requestc
C sN d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|j rp|jrpt|�}d|d < t|�}t|d
tj d �}t
|j |�}| j ||||||�}|d kr�d S t
|d ��r|j } |_| j|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| j|d
�d | |< |j� |j� | jj||jd�S )N�location�urir� r� �ftprn z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rR )rJ )r� r� r� rn )r �schemer rX Znetlocr� r r �stringZ punctuationr rp r� r� r r� � max_repeatsr` �max_redirections�inf_msgr_ r� r� rG rJ )
r� r� rd r� r� re r� �urlparts�newZvisitedrL rL rM �http_error_302� s@
z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r
�http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c C s� t | �\}}|jd�s d}| }n:|jd�s6td| ��|jdd�}|dkrNd}|d|� }t|�\}}|dk r|t|�\}}nd }}||||fS )a Return (scheme, user, password, host/port) given a URL or an authority.
If a URL is supplied, it must have an authority (host:port) component.
According to RFC 3986, having an authority component means the URL must
have two slashes after the scheme.
r� Nz//z proxy URL with no authority: %rr: rR rS )r r� rB r� r r ) �proxyr Zr_scheme� authority�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s
r c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C s^ |d krt � }t|d�s td��|| _x2|j� D ]&\}}t| d| ||| jfdd�� q0W d S )N�keyszproxies must be a mappingz%s_openc S s || ||�S )NrL )�rr r� r� rL rL rM �<lambda>% s z'ProxyHandler.__init__.<locals>.<lambda>)r5 r� �AssertionError�proxiesr{ �setattrr� )r� r r� rH rL rL rM r� s
zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } tj| j� �jd�}
|j dd|
� t|�}|j
||� ||ks�|dkr�d S | j j ||j
d�S d S )Nz%s:%s�asciizProxy-authorizationzBasic r� )rJ )r� r rv � proxy_bypassr
�base64� b64encode�encode�decoder| r� r� rG rJ ) r� r� r r� Z orig_typeZ
proxy_typer r r Z user_passZcredsrL rL rM r� ( s zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S )N)�passwd)r� rL rL rM r� F s zHTTPPasswordMgr.__init__c s` t |t�r|g}|�jkr$i �j|< x6dD ].� t� �fdd�|D ��}||f�j| |< q*W d S )NTFc s g | ]}�j |� ��qS rL )�
reduce_uri)r� �u)� default_portr� rL rM �
<listcomp>Q s z0HTTPPasswordMgr.add_password.<locals>.<listcomp>)TF)r� r� r" �tuple)r� �realmr� r r" � reduced_urirL )r% r� rM � add_passwordI s
z HTTPPasswordMgr.add_passwordc C s` | j j|i �}xLdD ]D}| j||�}x2|j� D ]&\}}x |D ]}| j||�r<|S q<W q.W qW dS )NTF)TF)NN)r" r� r# r{ � is_suburi) r� r( �authuriZdomainsr% �reduced_authuriZurisZauthinfor� rL rL rM �find_user_passwordT s
z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d}|}d}t|�\}}|r~|dkr~|dk r~ddd�j|�} | dk r~d || f }||fS )
z@Accept authority or URI and extract only the authority and path.rR r r: r� N�P i� )r� r� z%s:%d)r r
r� )
r� r� r% �partsr r rX rv �portZdportrL rL rM r# ^ s zHTTPPasswordMgr.reduce_uric C sR ||kr dS |d |d kr dS t j|d |d f�}t|�t|d �krNdS dS )zcCheck if test is below base in a URI tree
Both args must be URIs in reduced form.
Tr FrR )� posixpath� commonprefixr` )r� �base�test�commonrL rL rM r+ u s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r* r. r# r+ rL rL rL rM r D s
c @ s e Zd Zdd� ZdS )r! c C s0 t j| ||�\}}|d k r"||fS t j| d |�S )N)r r. )r� r( r, r r rL rL rM r. � s
z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� r. rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S )N)�
authenticated�superr� )r� r� �kwargs)� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | j ||� |d k r&t� jd |||� t� j||||� d S )N)�update_authenticatedr8 r* )r� r( r� r r" �is_authenticated)r: rL rM r* � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C sF t |t�r|g}x0dD ](}x"|D ]}| j||�}|| j|< q W qW d S )NTF)TF)r� r� r# r7 )r� r� r< r% r$ r) rL rL rM r; � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD x>dD ]6}| j ||�}x$| jD ]}| j||�r | j| S q W qW d S )NTF)TF)r# r7 r+ )r� r, r% r- r� rL rL rM r< � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r* r; r< �
__classcell__rL rL )r: rM r" � s
c @ sT e Zd Zejdej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S )N)r r" r* )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c st d}xFt jj|�D ]6}|j� \}}}|d kr:tjdtd� ||fV d}qW |sp|rb|j� d }nd}|d fV d S )
NF�"�'z Basic Auth Realm was unquoted� Tr rn )r> r? )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r( rL rL rM � _parse_realm� s
z%AbstractBasicAuthHandler._parse_realmc C s~ |j |�}|sd S d }xL|D ]D}x>| j|�D ]0\}}|j� dkrF|}q,|d k r,| j|||�S q,W q W |d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allrG rt �retry_http_basic_authrB ) r� �authreqrv r� re Z unsupportedrF r r( rL rL rM �http_error_auth_reqed� s
z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j j||�\}}|d k rtd||f }dtj|j� �jd� }|j| jd �|krTd S |j| j|� | j j
||j d�S d S d S )Nz%s:%szBasic r )rJ ) r" r. r r r r! rq � auth_headerr� r� rG rJ )r� rv r� r( r �pw�raw�authrL rL rM rI � s z.AbstractBasicAuthHandler.retry_http_basic_authc C sx t | jd� s | jj|j� r"|S |jd�st| jjd |j�\}}dj||�j� }tj |�j
� }|j ddj|j � �� |S )Nr< �
Authorizationz{0}:{1}zBasic {})
r� r" r< rp r� r. r� r r Zstandard_b64encoder! r� �strip)r� r� r r" Z credentialsZauth_strrL rL rM � http_request s
z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j ko dk n r8| jj|jd� n| jj|jd� |S )Nr< r� i, TF)r� r" r� r; rp )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�IrA r� rG rK rI rR r� �
https_requestr� rL rL rL rM r# � s
c @ s e Zd ZdZdd� ZdS )r$ rP c C s |j }| jd|||�}|S )Nzwww-authenticate)rp rK )r� r� rd r� r� re rH r� rL rL rM �http_error_401 s
z#HTTPBasicAuthHandler.http_error_401N)r� r� r� rL rW rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% zProxy-authorizationc C s |j }| jd|||�}|S )Nzproxy-authenticate)rv rK )r� r� rd r� r� re r r� rL rL rM �http_error_407+ s
z$ProxyBasicAuthHandler.http_error_407N)r� r� r� rL rX rL rL rL rM r% ' s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S )Nr )r r" r* �retried� nonce_count�
last_nonce)r� r" rL rL rM r� E s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S )Nr )rY )r� rL rL rM �reset_retry_countN s z+AbstractDigestAuthHandler.reset_retry_countc C s| |j |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|j� d }|j� dkr`| j||�S |j� dkrxtd| ��d S ) N� i� zdigest auth failedrR r ZdigestrH zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rY r rp rE rt �retry_http_digest_authrB )r� rL rv r� re rJ r rL rL rM rK Q s
z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |j dd�\}}ttd t|���}| j||�}|rvd| }|jj| jd �|krRd S |j| j|� | j j
||j d�}|S d S )Nr� rR z Digest %s)rJ ) rE �parse_keqv_list�filter�parse_http_list�get_authorizationre r� rL r� r� rG rJ )r� r� rO �tokenZ challenge�chalZauth_valZresprL rL rM r^ e s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |tj� f }|jd�td� }tj|�j� }|d d� S )Nz %s:%s:%s:r rQ � )rZ �timeZctimer � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceq s z$AbstractDigestAuthHandler.get_cnoncec C s� y6|d }|d }|j d�}|j dd�}|j dd �}W n tk
rJ d S X | j|�\}} |d krfd S | jj||j�\}
} |
d kr�d S |jd k r�| j|j|�} nd } d|
|| f }
d|j� |j f }|d k�r.|| j
kr�| j d
7 _ n d
| _ || _
d | j }| j |�}d ||||||�f }| ||
�|�}n2|d k�rT| ||
�d|||�f �}n t
d
| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr( rk �qop� algorithm�MD5�opaquez%s:%s:%sz%s:%srO rR z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr" r. rp rI �get_entity_digestr� r� r[ rZ ro r )r� r� rd r( rk rp rq rs �H�KDr rM ZentdigZA1ZA2ZncvalueZcnonceZnoncebitZrespdigr4 rL rL rM rb | sV
z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nrr c S s t j| jd��j� S )Nr )rh Zmd5r rj )�xrL rL rM r � s z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t j| jd��j� S )Nr )rh ri r rj )ry rL rL rM r � s z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nz%s:%srL )rl �d)rw rL rM r � s )rB )r� rq rx rL )rw rM ru � s
z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S )NrL )r� rI rd rL rL rM rv � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� r\ rK r^ ro rb ru rv rL rL rL rM r& : s
<
c @ s e Zd ZdZdZdZdd� ZdS )r' z�An authentication protocol defined by RFC 2069
Digest authentication improves on basic authentication because it
does not transmit passwords in the clear.
rP i� c C s* t |j�d }| jd|||�}| j� |S )NrR zwww-authenticate)r rp rK r\ )r� r� rd r� r� re rv �retryrL rL rM rW � s
z$HTTPDigestAuthHandler.http_error_401N)r� r� r� r� rL r� rW rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( zProxy-Authorizationi� c C s" |j }| jd|||�}| j� |S )Nzproxy-authenticate)rv rK r\ )r� r� rd r� r� re rv r{ rL rL rM rX � s
z%ProxyDigestAuthHandler.http_error_407N)r� r� r� rL r� rX rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S )N)� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S )N)r} )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jjj|j|j� �S )N)r� r� �HTTPConnection�_get_content_lengthrI r� )r� ru rL rL rM r� � s z'AbstractHTTPHandler._get_content_lengthc C s
|j }|std��|jd k r�|j}t|t�r8d}t|��|jd�sN|jdd� |jd� r�|jd� r�| j|�}|d k r�|jdt|�� n |jdd� |}|j � r�t
|j �\}}t |�\}} |jd�s�|jd|� x2| j
jD ]&\}
} |
j� }
|j|
�s�|j|
| � q�W |S ) Nz
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-typez!application/x-www-form-urlencodedzContent-lengthzTransfer-encodingZchunkedro )rv r rI r� r� r� r� r� r� r� r r� r r� r� r� ) r� ru rv rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr[ r� rL rL rM � do_request_� s>
z AbstractHTTPHandler.do_request_c
s\ |j }|std��||fd|ji|��}|j| j� t|j�� � jt� fdd�|jj � D ��� d� d< tdd� � j � D ��� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � y`y&|j |j
� |j|j� |jd
�d � W n, tk
�r
} zt|��W Y d d }~X nX |j� } W n |j� � Y nX |j�rF|jj� d |_|j� | _| j| _| S )
z�Return an HTTPResponse object for the request, using http_class.
http_class must implement the HTTPConnection API from http.client.
z
no host givenrJ c 3 s" | ]\}}|� kr||fV qd S )NrL )r� r� r� )re rL rM r� ) s z.AbstractHTTPHandler.do_open.<locals>.<genexpr>r� �
Connectionc s s | ]\}}|j � |fV qd S )N)�title)r� r[ r� rL rL rM r� 6 s zProxy-Authorization)re zTransfer-encoding)Zencode_chunkedN)rv r rJ Zset_debuglevelr} r� rx r� re r{ rz Z
set_tunnelru r� r� rI r� rm � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrv r� Ztunnel_headersZproxy_auth_hdr�errr rL )re rM r� s@
"
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r� r� r� r� rL rL rL rM r| � s
&r| c @ s e Zd Zdd� ZejZdS )r) c C s | j tjj|�S )N)r� r� r� r� )r� r� rL rL rM � http_open` s zHTTPHandler.http_openN)r� r� r� r� r| r� rR rL rL rL rM r) ^ s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t j| |� || _|| _d S )N)r| r� �_context�_check_hostname)r� r~ r> �check_hostnamerL rL rM r� i s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� )r� r� rL rL rM �
https_openn s zHTTPSHandler.https_open)r NN)r� r� r� r� r� r| r� rV rL rL rL rM rE g s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|jj� }|| _d S )Nr )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� w s
z HTTPCookieProcessor.__init__c C s | j j|� |S )N)r� Zadd_cookie_header)r� ru rL rL rM rR } s z HTTPCookieProcessor.http_requestc C s | j j||� |S )N)r� Zextract_cookies)r� ru r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� rR r� rV r� rL rL rL rM r v s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sR i }xH| D ]@}|j dd�\}}|d dkrB|d dkrB|dd� }|||< q
W |S )z>Parse list of key=value strings where keys are not duplicated.�=rR r r> rS rS )rE )�lZparsedZeltr� r� rL rL rM r_ � s
r_ c C s� g }d}d }}xt| D ]l}|r,||7 }d}q|rV|dkr@d}qn |dkrLd}||7 }q|dkrn|j |� d}q|dkrzd}||7 }qW |r�|j |� dd� |D �S ) ap Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Neither commas nor quotes count if they are escaped.
Only double-quotes count, not single-quotes.
rn F�\Tr> �,c S s g | ] }|j � �qS rL )rQ )r� �partrL rL rM r& � s z#parse_http_list.<locals>.<listcomp>)r] )rl �resr� �escaper ZcurrL rL rM ra � s4
ra c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| j� krXtd��n
| j|�S d S )Nr: z//r@ r� � localhostz-file:// scheme is supported only on localhost)r� rv � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &
zFileHandler.file_openNc C s` t jd krZy*ttjd�d tjtj� �d �t _W n$ tjk
rX tjd�ft _Y nX t jS )Nr� r: )r* �namesr' r� �gethostbyname_ex� gethostname�gaierror�
gethostbyname)r� rL rL rM r� � s
zFileHandler.get_namesc C s dd l }dd l}|j}|j}t|�}y�tj|�}|j}|jj |j
dd�} |j |�d }
|j d|
pbd|| f �} |r~t
|�\}} | s�| r�t|�| j� kr�|r�d| | }
nd| }
tt|d�| |
�S W n* tk
r� } zt|��W Y d d }~X nX td��d S ) Nr T)�usegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
z
text/plainzfile://�rbzfile not on local host)� email.utils� mimetypesrv r� r4 rW �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rm r )r� r� �emailr� rv rb Z localfile�statsri �modified�mtypere r1 Zorigurl�exprL rL rM r� � s0
zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s& y
t j| �S t jk
r d S X d S )N)r� r� r� )rv rL rL rM r� � s
r� c @ s e Zd Zdd� Zdd� ZdS )r+ c C s. dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}yt
j |�}W n* t k
r� } zt|��W Y d d }~X nX t
|j�\} }
| jd�} ttt | ��} | d d� | d } } | �r| d �r| dd � } y�| j||||| |j�}
| �r8d�p:d}x:|
D ]2}t|�\}}|j� dk�rB|dk�rB|j� }�qBW |
j| |�\}}d}|j|j�d }|�r�|d
| 7 }|d k �r�|dk�r�|d| 7 }tj|�}t |||j�S |j k
�r( } z$td| �}|j t j � d ��W Y d d }~X nX d S )Nr zftp error: no host givenrn r� rR rU �Dr� �a�Ar� rz zContent-type: %s
zContent-length: %d
z
ftp error: %rr: rS rS )r� r� r� rU rz r� )!�ftplibr� rv r r
�FTP_PORTr^ r r r
r� r� rm r r� rE r� �map� connect_ftprJ r rt �upper�retrfiler� rp r� r� r �
all_errors�with_traceback�sys�exc_info)r� r� r� r� rv r1 r r" r� rX �attrs�dirsrN �fwr� �attrr� rd �retrlenre r� r� �excrL rL rM �ftp_open� s\
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r" rv r1 r� rJ rL rL rM r� 1 s zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ � s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< re )�cacherJ �soonest�delay� max_conns)r� rL rL rM r� 8 s
zCacheFTPHandler.__init__c C s
|| _ d S )N)r� )r� �trL rL rM �
setTimeout? s zCacheFTPHandler.setTimeoutc C s
|| _ d S )N)r� )r� r� rL rL rM � setMaxConnsB s zCacheFTPHandler.setMaxConnsc C sr |||dj |�|f}|| jkr4tj� | j | j|< n,t||||||�| j|< tj� | j | j|< | j� | j| S )Nr� )�joinr� rf r� rJ r� � check_cache)r� r r" rv r1 r� rJ r� rL rL rM r� E s
zCacheFTPHandler.connect_ftpc C s� t j � }| j|krTx@t| jj� �D ].\}}||k r"| j| j� | j|= | j|= q"W tt| jj� ��| _t | j�| j
kr�x6t| jj� �D ]$\}}|| jkr�| j|= | j|= P q�W tt| jj� ��| _d S )N) rf r� r� rJ r{ r� r� �min�valuesr` r� )r� r� r� r� rL rL rM r� P s
zCacheFTPHandler.check_cachec C s4 x| j j� D ] }|j� q W | j j� | jj� d S )N)r� r� r� �clearrJ )r� �connrL rL rM � clear_cached s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r� r� rL rL rL rM r, 5 s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|jdd�\}}|jdd�\}}t|�}|jd�rNtj|�}|d d� }|sVd}tjd|t|�f �}t t
j |�||�S ) N�:rR r� z;base64� ztext/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
i����) rp rE r �endswithr � decodebytesr� r� r` r �io�BytesIO)r� r� rH r rI Z mediatypere rL rL rM � data_openk s
zDataHandler.data_openN)r� r� r� r� rL rL rL rM r- j s r� �nt)r4 r3 c C s t | �S )zOS-specific conversion from a relative URL of the 'file' scheme
to a file system path; not recommended for general use.)r
)�pathnamerL rL rM r4 � s c C s t | �S )zOS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use.)r )r� rL rL rM r3 � s c @ s� e Zd ZdZdZde Zd*dd�Zdd� Zdd � Z d
d � Z
d d
� Z d+dd�Z d,dd�Z
d-dd�Zd.dd�Zdd� Zd/dd�Zd0dd�Zd d � Zer�d d � Zd1d d!�Zd"d#� Zd$d%� Zd&d'� Zd2d(d)�ZdS )3r8 a, Class to open URLs.
This is a class rather than just a subroutine because we may need
more than one set of global protocol-specific options.
Note -- this is a base class for those who don't want the
automatic handling of errors type 302 (relocated) and 401
(authorization needed).NzPython-urllib/%sc K s� dd| j ji }tj|tdd� |d kr.t� }t|d�s@td��|| _|j d�| _
|j d�| _ d | j fd g| _
g | _tj| _d | _t| _d S )
NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classr@ )�
stacklevelr zproxies must be a mapping�key_file� cert_filez
User-Agent�Accept�*/*)r� r� )r: r� r? r@ rA r5 r� r r r� r� r� �versionr� �_URLopener__tempfilesrW rl �_URLopener__unlink� tempcache�ftpcache)r� r Zx509r� rL rL rM r� � s zURLopener.__init__c C s | j � d S )N)r� )r� rL rL rM �__del__� s zURLopener.__del__c C s | j � d S )N)�cleanup)r� rL rL rM r� � s zURLopener.closec C sZ | j rFx2| j D ](}y| j|� W q tk
r4 Y qX qW | j d d �= | jrV| jj� d S )N)r� r� rm r� r� )r� rN rL rL rM r� � s
zURLopener.cleanupc G s | j j|� dS )zdAdd a header to be used by the HTTP interface only
e.g. u.addheader('Accept', 'sound/basic')N)r� r] )r� r� rL rL rM � addheader� s zURLopener.addheaderc C sn t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd}d| } || _ | j
dd�} t | | � s�| d kr�|r�| j |||�S | j
||�S y,|dk�r t| | �|�S t| | �||�S W nV ttfk
�r. � Y n< tk
�rh }
z td
|
�jtj� d ��W Y dd}
~
X nX dS ) z6Use URLopener().open(file) instead of open(file, 'r').z%/:=&?~#+!$,;'@()*[]|)r r� rN NZopen_�-r� r� z socket errorr: )r r r r� rG r r r r r� r� r� �open_unknown_proxy� open_unknownr� r r rm r� r� r� )r� r� rI rb re rd �urltyperH r � proxyhostrv r� r[ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��dS )z/Overridable interface to open unknown URL type.z url errorzunknown url typeN)r rm )r� r� rI r� rH rL rL rM r� s zURLopener.open_unknownc C s t |�\}}tdd| |��dS )z/Overridable interface to open unknown URL type.z url errorzinvalid proxy for %sN)r rm )r� r r� rI r� rH rL rL rM r� s z URLopener.open_unknown_proxyc C s& t t|��}| jr&|| jkr&| j| S t|�\}}|dkr�| sH|dkr�y.| j|�}|j� }|j� tt|�d �|fS t k
r� } zW Y dd} ~ X nX | j
||�}�zH|j� }
|r�t
|d�} n|ddl } t|�\}
}t|p�d�\}
}t |p�d�\}}
t
|�p d�\}}
tjj|�d }| j|�\}}| jj|� tj|d�} z�||
f}| jdk �r^|| j|< d }d
}d}d}d |
k�r�t|
d
�}|�r�||||� xH|j|�}|�s�P |t|�7 }| j|� |d7 }|�r�||||� �q�W W d| j� X W d|j� X |dk�r"||k �r"td ||f |��|S )ztretrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object.NrN rR rO r rn i rQ zcontent-lengthzContent-Lengthz1retrieval incomplete: got only %i out of %i bytesi rS )r r r� r r� rV r� r4 r rm rG rZ r r rW rX �splitextZmkstempr� r] �fdopenr^ r_ r` ra r )r� rH rb rc rI r� Zurl1rd r� r� re rf rZ ZgarbagerX �suffix�fdrg rh ri r_ rj rk rL rL rM �retrieve sl
zURLopener.retrievec C s( d}d}t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d}| j� dkrvd}n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t j
|j � �j d�} nd} |�rt|�}t j
|j � �j d�} nd} ||�}
i }| �r*d| |d< | �r<d| |d < |�rJ||d
< d |d < x | j
D ]\}}|||< �qZW |dk �r�d
|d< |
jd|||� n|
jd||d� y |
j� }W n" tjjk
�r� td��Y nX d|j k�o�dk n �rt||jd| |j�S | j||j|j|j|j|�S dS )a� Make an HTTP connection using connection_class.
This is an internal method that should be called from
open_http() or open_https().
Arguments:
- connection_factory should take a host name and return an
HTTPConnection instance.
- url is the url to retrieval or a host, relative-path pair.
- data is payload for a POST request or None.
Nr� z %s://%s%sz
http errorz
no host givenr zBasic %szProxy-AuthorizationrP ro r� r� z!application/x-www-form-urlencodedz Content-Typer� r� )re z$http protocol error: bad status liner� i, zhttp:)r� r� r r r
r rt r rm r r r r! r� ru r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrd r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrv r� Zrealhostr� r� Z
proxy_authrO Z http_connre rF r� r� rL rL rM �_open_generic_httpQ sr
z URLopener._open_generic_httpc C s | j tjj||�S )zUse HTTP protocol.)r� r� r� r� )r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|dkr6||||||�} n|||||||�} | rP| S | j|||||�S )z�Handle http errors.
Derived class can override this, or provide specific handlers
named http_error_DDD where DDD is the 3-digit error code.z
http_error_%dN)r� r� r� )
r� rH rd �errcode�errmsgre rI r[ r rg rL rL rM r� � s
zURLopener.http_errorc C s |j � t||||d��dS )z>Default error handler: close the connection and raise OSError.N)r� r )r� rH rd r� r� re rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r� r� )r� r� r� r� r� )r� rv rL rL rM �_https_connection� s zURLopener._https_connectionc C s | j | j||�S )zUse HTTPS protocol.)r� r� )r� rH rI rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|dd� dkrP|dd� dkrP|dd� j� dkrPtd ��n
| j|�S dS )
z/Use local file or FTP depending on form of URL.zEfile error: proxy support for file protocol currently not implementedNr: z//r@ r� � z
localhost/z-file:// scheme is supported only on localhost)r� r� r rt rB r� )r� rH rL rL rM � open_file� s
4
zURLopener.open_filec C s\ ddl }ddl}t|�\}}t|�}ytj|�}W n0 tk
rb } zt|j|j ��W Y dd}~X nX |j
} |j j |j
dd�}
|j|�d } |jd| p�d| |
f �} |s�|}
|dd� dkr�d | }
tt|d
�| |
�S t|�\}}| o�tj|�t� ft� k�rP|}
|dd� dk�r d | }
n |dd � d k�r>td
| ��tt|d
�| |
�S td��dS )zUse local file.r NT)r� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
z
text/plainrR r� zfile://r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 rW r� rm r �strerrorrb r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rv rN Z localnamer� �eri r� r� re Zurlfiler1 rL rL rM r� � s:
zURLopener.open_local_filec C s� t |t�std��ddl}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd}t|�}t|ppd�}t|p|d�}t j
|�}|s�ddl }|j }nt
|�}t|�\}} t|�}|jd�}
|
dd� |
d }
} |
o�|
d � r�|
dd� }
|
�r|
d �rd|
d< |||dj|
�f} t| j�tk�rlx8t| j�D ]*}
|
| k�r>| j|
}| j|
= |j� �q>W y�| | jk�r�t|||||
�| j| < | �s�d}nd }x:| D ]2}t|�\}}|j� d
k�r�|dk�r�|j� }�q�W | j| j| |�\}}|jd| �d }d}|�r|d| 7 }|dk �r:|dk�r:|d| 7 }t j |�}t ||d| �S t � k
�r� } z td| �j t!j"� d ��W Y dd}~X nX dS )zUse FTP protocol.zCftp error: proxy support for ftp protocol currently not implementedr Nzftp error: no host givenrn r� rR r� rU r� r� r� r� rz zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: rS rS )r� r� r� rU rz r� )#r� r� r r� r r
r r r
r� r� r� r� r^ r rE r� r` r� � MAXFTPCACHEr� r� r� r rt r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rv rX r1 r r" r� r� r� rN r� r� r� r� r� r� rd r� r� re r� rL rL rM �open_ftp� sp
zURLopener.open_ftpc C s< t |t�std��y|jdd�\}}W n tk
rD tdd��Y nX |sNd}|jd�}|dkr�d ||d
� kr�||d d
� }|d
|� }nd }g }|jd tj d
tj
tj� �� � |jd| � |dkr�t j |j
d��jd�}nt|�}|jdt|� � |jd � |j|� dj|�}tj|�}tj|�}t|||�S )zUse "data" URL.zEdata error: proxy support for data protocol currently not implementedr� rR z
data errorz bad data URLztext/plain;charset=US-ASCII�;r r� Nrn zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr r zlatin-1zContent-Length: %d�
)r� r� r rE rB rm �rfindr] rf ZstrftimeZgmtimer r� r r! r
r` r� r� r� r� �StringIOr ) r� rH rI r� Zsemir r� re �frL rL rM � open_data3 s6
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r� r� r� r� r� r� r� r� r� rG r� r� r� r� r� r� r� rC r� r� r� r� r r
rL rL rL rM r8 � s.
$
B\
:c @ s� e Zd ZdZdd� Zdd� Zd#dd�Zd d
� Zd$d d �Zd%d
d�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd�Zd,d d �Zd-d d �Zd!d"� ZdS ).r9 z?Derived class with handlers for errors we can handle (perhaps).c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtries)r� r� r9 rL rL rM r� ` s zFancyURLopener.__init__c C s t ||d| |�S )z3Default error handling -- don't raise an exception.zhttp:)r )r� rH rd r� r� re rL rL rM r� f s z!FancyURLopener.http_error_defaultNc
C sn | j d7 _ zR| jrJ| j | jkrJt| d�r4| j}n| j}|||dd|�S | j||||||�}|S d| _ X dS )z%Error 302 -- relocated (temporarily).rR �http_error_500i� z)Internal Server Error: Redirect RecursionNr )r r
r� r r� �redirect_internal) r� rH rd r� r� re rI r� rg rL rL rM r
j s
z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |j � t| jd | |�}t|�}|jd krnt|||d| ||��| j|�S )
Nr� r� r� r� r� r� rn z( Redirection to url '%s' is not allowed.)r� r� r� rn )r� r r� r r r rG ) r� rH rd r� r� re rI r� r rL rL rM r | s
z FancyURLopener.redirect_internalc C s | j ||||||�S )z*Error 301 -- also relocated (permanently).)r
)r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_301c C s | j ||||||�S )z;Error 303 -- also relocated (essentially identical to 302).)r
)r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_303c C s2 |dkr | j ||||||�S | j|||||�S dS )z1Error 307 -- relocated, but turn POST into error.N)r
r� )r� rH rd r� r� re rI rL rL rM r
� s z FancyURLopener.http_error_307Fc
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )z_Error 401 -- authentication required.
This function supports Basic authentication only.zwww-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rH Zretry_� _basic_authN)r8 r� rS �matchrC rt r� r� )
r� rH rd r� r� re rI r{ �stuffr r r( r[ rL rL rM rW � s&
z FancyURLopener.http_error_401c
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )zeError 407 -- proxy authentication required.
This function supports Basic authentication only.zproxy-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rH Z retry_proxy_r N)r8 r� rS r rC rt r� r� )
r� rH rd r� r� re rI r{ r r r r( r[ rL rL rM rX � s&
z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttp://r� �@rR z%s:%s@%srn )r )r r r r� �get_user_passwdr rG )r� rH r( rI rv r� r� r r� r� �
proxyselectorr� r r" rL rL rM �retry_proxy_http_basic_auth� s
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttps://r� r rR z%s:%s@%srn )r )r r r r� r r rG )r� rH r( rI rv r� r� r r� r� r r� r r" rL rL rM � retry_proxy_https_basic_auth� s
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttp://)r r� r r rG )
r� rH r( rI rv r� r� r r" r� rL rL rM rI � s
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttps://)r r� r r rG )
r� rH r( rI rv r� r� r r" r� rL rL rM �retry_https_basic_auth s
z%FancyURLopener.retry_https_basic_authr c C s` |d |j � }|| jkr2|r(| j|= n
| j| S | j||�\}}|sJ|rX||f| j|< ||fS )Nr )rt r �prompt_user_passwd)r� rv r( r� r� r r" rL rL rM r s
z FancyURLopener.get_user_passwdc C sT ddl }y,td||f �}|j d|||f �}||fS tk
rN t� dS X dS )z#Override this in a GUI environment!r Nz Enter username for %s at %s: z#Enter password for %s in %s at %s: )NN)�getpass�input�KeyboardInterrupt�print)r� rv r( r r r" rL rL rM r $ s z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r� r
r r r r
rW rX r r rI r r r rL rL rL rM r9 ] s$
c C s t dkrtjd�a t S )z8Return the IP address of the magic hostname 'localhost'.Nr� )�
_localhostr� r� rL rL rL rM r� 4 s
r� c C sP t dkrLyttjtj� �d �a W n( tjk
rJ ttjd�d �a Y nX t S )z,Return the IP addresses of the current host.Nr: r� )� _thishostr' r� r� r� r� rL rL rL rM r < s r c C s t dkrddl} | ja t S )z1Return the set of errors raised by the FTP class.Nr )�
_ftperrorsr� r� )r� rL rL rM r G s r c C s t dkrtjd�a t S )z%Return an empty email Message object.Nrn )�
_noheadersr� r� rL rL rL rM � noheadersP s
r" c @ sJ e Zd ZdZddd�Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r� z;Class used by open_ftp() for cache of open FTP connections.NTc C sX || _ || _|| _|| _|| _|| _d| _|| _y | j� W n | j � � Y nX d S )Nr )
r r" rv r1 r� rJ �refcount� keepalive�initr� )r� r r" rv r1 r� rJ r� rL rL rM r� ] s zftpwrapper.__init__c C s\ dd l }d| _|j� | _| jj| j| j| j� | jj| j | j
� dj | j �}| jj
|� d S )Nr r� )r� �busyZFTPr� Zconnectrv r1 rJ Zloginr r" r� r� �cwd)r� r� Z_targetrL rL rM r% m s
zftpwrapper.initc - C s� dd l }| j� |dkr"d}d}n d| }d}y| jj|� W n* |jk
rh | j� | jj|� Y nX d }|r�| r�y d| }| jj|�\}}W nR |jk
r� } z4t|�d d� d kr�t d
| �j
t j � d ��W Y d d }~X nX |�s�| jjd� |�rn| jj
� } zJy| jj|� W n4 |jk
�rP } zt d
| �|�W Y d d }~X nX W d | jj| � X d | }nd
}| jj|�\}}d| _t|jd�| j�}
| jd7 _|j� |
|fS )Nr rz r� zTYPE ArR zTYPE zRETR r@ Z550z
ftp error: %rr: zLIST ZLISTr� )rz r� )r� � endtransferr� Zvoidcmdr� r% Z ntransfercmdZ
error_permr� r r� r� r� �pwdr' r& r �makefile�
file_closer# r� ) r� rN r� r� �cmd�isdirr� r� r� r) ZftpobjrL rL rM r� v sN
$
zftpwrapper.retrfilec C s
d| _ d S )Nr )r& )r� rL rL rM r( � s zftpwrapper.endtransferc C s d| _ | jdkr| j� d S )NFr )r$ r# �
real_close)r� rL rL rM r� � s
zftpwrapper.closec C s4 | j � | jd8 _| jdkr0| j r0| j� d S )NrR r )r( r# r$ r. )r� rL rL rM r+ � s zftpwrapper.file_closec C s2 | j � y| jj� W n t� k
r, Y nX d S )N)r( r� r� r )r� rL rL rM r. � s
zftpwrapper.real_close)NT) r� r� r� r� r� r% r� r( r� r+ r. rL rL rL rM r� Z s
-r� c C s� i } xBt jj� D ]4\}}|j� }|r|dd� dkr|| |dd� < qW dt jkr^| jdd� xXt jj� D ]J\}}|dd� dkrj|j� }|r�|| |dd � < qj| j|dd
� d� qjW | S ) a Return a dictionary of scheme -> proxy server URL mappings.
Scan the environment for variables named <scheme>_proxy;
this seems to be the standard convention. If you need a
different way, you can pass a proxies dictionary to the
[Fancy]URLopener constructor.
� N�_proxyZREQUEST_METHODr� i����i����i����i����i����)rW �environr{ rt r� )r r[ r� rL rL rM �getproxies_environment� s
r2 c
C s� |dkrt � }y |d }W n tk
r. dS X |dkr<dS t| �\}}dd� |jd�D �}xP|D ]H}|rb|jd �}tj|�}d
| }tj||tj�s�tj|| tj�rbdS qbW dS ) z�Test if proxies should not be used for a particular host.
Checks the proxy dict for the value of no_proxy, which should
be a list of comma separated DNS suffixes, or '*' for all hosts.
N�nor �*rR c S s g | ] }|j � �qS rL )rQ )r� r rL rL rM r& � s z,proxy_bypass_environment.<locals>.<listcomp>r� �.z
(.+\.)?%s$) r2 rt r
rE �lstriprS r� r rU )rv r Zno_proxy�hostonlyr1 Z
no_proxy_listr[ �patternrL rL rM �proxy_bypass_environment� s&
r9 c
C s ddl m } t| �\}}dd� }d| kr4|d r4dS d}x�|jd f �D ]�}|sPqFtjd
|�}|dk �r|dkr�ytj|�}||�}W n tk
r� wFY nX ||jd ��} |jd �}
|
dkr�d
|jd �j d�d }
nt
|
d d� �}
d|
}
||
? | |
? k�rdS qF|| |�rFdS qFW dS )aj
Return True iff this host shouldn't be accessed using a proxy
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
{ 'exclude_simple': bool,
'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
}
r )�fnmatchc S sh | j d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nr5 r� r � rR re r: rQ r@ )rE r� r� r^ r` )ZipAddrr0 rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numr5 Zexclude_simpleTN�
exceptionsz(\d+(?:\.\d+)*)(/\d+)?rR r: rQ � F) r: r
r� rS r r� r� rm �group�countr^ ) rv �proxy_settingsr: r7 r1 r< ZhostIPr� r� r4 �maskrL rL rM � _proxy_bypass_macosx_sysconf� s:
rC �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S )N)rE rC )rv rA rL rL rM �proxy_bypass_macosx_sysconf:
s rG c C s t � S )z�Return a dictionary of scheme -> proxy server URL mappings.
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
)rF rL rL rL rM �getproxies_macosx_sysconf>
s rH c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or from the MacOSX framework SystemConfiguration.
N)r2 r9 rG )rv r rL rL rM r H
s
r c C s t � p
t� S )N)r2 rH rL rL rL rM r5 U
s c C s i } y ddl }W n tk
r$ | S X y�|j|jd�}|j|d�d }|r�t|j|d�d �}d|kr�x�|jd�D ]4}|jdd�\}}tjd |�s�d
||f }|| |< qrW n>|dd � d kr�|| d
< n$d| | d
< d| | d< d| | d< |j � W n t
t t fk
�r Y nX | S )zxReturn a dictionary of scheme -> proxy server URL mappings.
Win32 uses the registry to store proxies.
r Nz;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r rR z ^([^/:]+)://z%s://%sr] zhttp:r� z http://%sz
https://%sr� zftp://%sr� )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� rE rS r ZCloserm rB r� )r rJ �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryZ
s8
rR c C s t � p
t� S )z�Return a dictionary of scheme -> proxy server URL mappings.
Returns settings gathered from the environment, if specified,
or the registry.
)r2 rR rL rL rL rM r5 �
s c & C s~ y dd l }W n tk
r dS X y6|j|jd�}|j|d�d }t|j|d�d �}W n tk
rl dS X | sz| r~dS t| �\}}|g} y tj |�}||kr�| j
|� W n tk
r� Y nX y tj |�}||kr�| j
|� W n tk
� r� Y nX |j d�}xp|D ]h} | dk�r*d|k�r*dS | j
dd �} | j
d
d �} | j
d d�} x$| D ] }
tj| |
tj��rTdS �qTW �qW dS )
Nr z;Software\Microsoft\Windows\CurrentVersion\Internet SettingsrI Z
ProxyOverrider z<local>r5 rR z\.r4 z.*�?)rJ rK rL rM rN r� rm r
r� r� r] ZgetfqdnrE r� rS r rU ) rv rJ rO rP Z
proxyOverrideZrawHostr1 ZaddrZfqdnr5 r� rL rL rM �proxy_bypass_registry�
sR
rT c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
N)r2 r9 rT )rv r rL rL rM r �
s
)NNN)N)r� r r� r� rh Z http.clientr� r� rW r2 rS r� r r� rf � collectionsrZ rT r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD rK rC �__all__� version_infor� rF r� r0 r1 r\ r6 r7 rT �ASCIIrr rw r r r2 r r/ r r r r r r! r" r# r$ r% �urandomrg r& r' r( r| r) r� r� rE r] r r. r_ ra r* r� r+ r, r- r r[ Z
nturl2pathr4 r3 r� r8 r9 r r� r r r r r! r" r� r2 r9 rC �platformZ_scproxyrE rF rG rH r r5 rR rT rL rL rL rM �<module>D s� P
T
?n $q *@
o v
+3:5! A W
_
#<
- 2
PK (�Z��P2� � # __pycache__/response.cpython-36.pycnu �[��� 3
\� � @ s^ d Z ddlZddddgZG dd� dej�ZG dd� de�ZG d d� de�ZG d
d� de�ZdS ) a Response classes used by urllib.
The base class, addbase, defines a minimal file-like interface,
including read() and readline(). The typical response object is an
addinfourl instance, which defines an info() method that returns
headers and a geturl() method that returns the url.
� N�addbase� addclosehook�addinfo�
addinfourlc s8 e Zd ZdZ� fdd�Zdd� Zdd� Zdd � Z� ZS )
r zOBase class for addinfo and addclosehook. Is a good idea for garbage collection.c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr )� __class__� �'/usr/lib64/python3.6/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file)r
r r r
�__repr__ s zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueError)r
r r r
� __enter__ s zaddbase.__enter__c C s | j � d S )N)�close)r
�type�value� tracebackr r r
�__exit__! s zaddbase.__exit__) r �
__module__� __qualname__�__doc__r r r r �
__classcell__r r )r r
r s
c s, e Zd ZdZ� fdd�Z� fdd�Z� ZS )r z*Class to add a close hook to an open file.c s t t| �j|� || _|| _d S )N)r r r � closehook�hookargs)r
r r r )r r r
r ( s zaddclosehook.__init__c s> z(| j }| j}|r&d | _ d | _||� W d tt| �j� X d S )N)r r r r r )r
r r )r r r
r - s zaddclosehook.close)r r r r r r r r r )r r
r % s c s( e Zd ZdZ� fdd�Zdd� Z� ZS )r z.class to add an info() method to an open file.c s t t| �j|� || _d S )N)r r r �headers)r
r r )r r r
r < s zaddinfo.__init__c C s | j S )N)r )r
r r r
�info@ s z addinfo.info)r r r r r r! r r r )r r
r 9 s c s2 e Zd ZdZd � fdd� Zdd� Zdd� Z� ZS )
r z9class to add info() and geturl() methods to an open file.Nc s" t t| �j||� || _|| _d S )N)r r r �url�code)r
r r r" r# )r r r
r G s zaddinfourl.__init__c C s | j S )N)r# )r
r r r
�getcodeL s zaddinfourl.getcodec C s | j S )N)r" )r
r r r
�geturlO s zaddinfourl.geturl)N)r r r r r r$ r% r r r )r r
r D s )r Ztempfile�__all__Z_TemporaryFileWrapperr r r r r r r r
�<module> s PK (�Z�
�� � , __pycache__/robotparser.cpython-36.opt-1.pycnu �[��� 3
\�" � @ s\ d Z ddlZddlZddlZdgZejdd�ZG dd� d�ZG dd� d�Z G d d
� d
�Z
dS ) a% robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://www.robotstxt.org/norobots-rfc.txt
� N�RobotFileParser� RequestRatezrequests secondsc @ sj e Zd ZdZddd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� ZdS )r zs This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
� c C s, g | _ d | _d| _d| _| j|� d| _d S )NFr )�entries�
default_entry� disallow_all� allow_all�set_url� last_checked)�self�url� r
�*/usr/lib64/python3.6/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S )z�Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
)r
)r r
r
r �mtime$ s zRobotFileParser.mtimec C s ddl }|j � | _dS )zYSets the time the robots.txt file was last fetched to the
current time.
r N)�timer
)r r r
r
r �modified- s zRobotFileParser.modifiedc C s& || _ tjj|�dd� \| _| _dS )z,Sets the URL referring to a robots.txt file.� � N)r �urllib�parse�urlparse�host�path)r r r
r
r r 5 s zRobotFileParser.set_urlc C s� yt jj| j�}W nR t jjk
rd } z2|jdkr:d| _n|jdkrT|jdk rTd| _W Y dd}~X n X |j � }| j
|j d�j � � dS ) z4Reads the robots.txt URL and feeds it to the parser.� � Ti� i� Nzutf-8)r r )
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r �f�err�rawr
r
r r : s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | jj|� d S )N�*)�
useragentsr r �append)r �entryr
r
r �
_add_entryG s
zRobotFileParser._add_entryc C s6 d}t � }| j� �x|D �]�}|sT|dkr8t � }d}n |dkrT| j|� t � }d}|jd�}|dkrr|d|� }|j� }|s�q|jdd�}t|�dkr|d j� j� |d< tj j
|d j� �|d< |d dk�r |dkr�| j|� t � }|j j |d � d}q|d dk�r4|dk�r|j
j t|d d �� d}q|d d
k�rh|dk�r|j
j t|d d �� d}q|d d k�r�|dk�r|d j� j� �r�t|d �|_d}q|d d
kr|dkr|d jd�}t|�dk�r|d j� j� �r|d j� j� �rtt|d �t|d ��|_d}qW |dk�r2| j|� dS )z�Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
r r � �#N�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/)�Entryr r( �find�strip�split�len�lowerr r �unquoter% r& � rulelines�RuleLine�isdigit�int�delayr �req_rate)r �lines�stater' �line�iZnumbersr
r
r r P sd
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tjjtjj|��}tjjdd|j|j |j
|j f�}tjj |�}|sfd}x"| j
D ]}|j|�rn|j|�S qnW | jr�| jj|�S dS )z=using the parsed robots.txt decide if useragent can fetch urlFTr r, )r r r
r r r r3 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r � useragentr Z
parsed_urlr' r
r
r � can_fetch� s$
zRobotFileParser.can_fetchc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r8 r )r rB r' r
r
r � crawl_delay� s
zRobotFileParser.crawl_delayc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r9 r )r rB r' r
r
r � request_rate� s
z RobotFileParser.request_ratec C s0 | j }| jd k r || jg }djtt|��d S )N�
)r r �join�map�str)r r r
r
r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__�__doc__r r r r r r( r rC rD rE rJ r
r
r
r r s
C c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r5 zoA rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path.c C s> |dkr| rd}t jjt jj|��}t jj|�| _|| _d S )Nr T)r r r> r r? r rA )r r rA r
r
r r � s
zRuleLine.__init__c C s | j dkp|j| j �S )Nr$ )r �
startswith)r �filenamer
r
r r@ � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rA r )r r
r
r rJ � s zRuleLine.__str__N)rK rL rM rN r r@ rJ r
r
r
r r5 � s r5 c @ s0 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd
S ) r- z?An entry has one or more user-agents and zero or more rulelinesc C s g | _ g | _d | _d | _d S )N)r% r4 r8 r9 )r r
r
r r � s zEntry.__init__c C s� g }x | j D ]}|jd|� �� q W | jd k r@|jd| j� �� | jd k rj| j}|jd|j� d|j� �� |jtt| j �� |jd� dj
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r, r rF ) r% r& r8 r9 ZrequestsZseconds�extendrH rI r4 rG )r Zret�agentZrater
r
r rJ � s
z
Entry.__str__c C sF |j d�d j� }x.| jD ]$}|dkr*dS |j� }||krdS qW dS )z2check if this entry applies to the specified agentr, r r$ TF)r0 r2 r% )r rB rR r
r
r r@ � s zEntry.applies_toc C s$ x | j D ]}|j|�r|jS qW dS )zZPreconditions:
- our agent applies to this entry
- filename is URL decodedT)r4 r@ rA )r rP r< r
r
r rA � s
zEntry.allowanceN)rK rL rM rN r rJ r@ rA r
r
r
r r- � s
r- ) rN � collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r5 r- r
r
r
r �<module> s 2PK (�Z��d��
�
__pycache__/error.cpython-36.pycnu �[��� 3
\Q
� @ sP d Z ddlZdddgZG dd� de�ZG dd� deejj�ZG dd� de�Z dS ) a� Exception classes raised by urllib.
The base exception class is URLError, which inherits from OSError. It
doesn't define any behavior of its own, but is the base class for all
exceptions defined in this package.
HTTPError is an exception class that is also a valid HTTP response
instance. It behaves this way because HTTP protocol errors are valid
responses, with a status code, headers, and a body. In some contexts,
an application may want to handle an exception like a regular
response.
� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S )N)�args�reason�filename)�selfr r � r �$/usr/lib64/python3.6/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r )r r r r
�__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r r r r
r s
c @ sX e Zd ZdZejjjZdd� Zdd� Z dd� Z
e dd � �Z e d
d � �Z
e
jd d � �Z
d
S )r zBRaised when HTTP error occurs, but also acts like non-error returnc C s: || _ || _|| _|| _|| _|d k r6| j||||� d S )N)�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r r r
r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s)r r )r r r r
r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>)r r )r r r r
�__repr__7 s zHTTPError.__repr__c C s | j S )N)r )r r r r
r < s zHTTPError.reasonc C s | j S )N)r )r r r r
�headers@ s zHTTPError.headersc C s
|| _ d S )N)r )r r r r r
r D s N)r
r r �__doc__�urllib�response�
addinfourlr r r r �propertyr r �setterr r r r
r # s
c @ s e Zd ZdZdd� ZdS )r zDException raised when downloaded size does not match content-length.c C s t j| |� || _d S )N)r r �content)r �messager r r r
r K s z ContentTooShortError.__init__N)r
r r r r r r r r
r I s )
r Zurllib.responser �__all__�OSErrorr r r r r r r r r
�<module> s
&PK (�ZN�z z ( __pycache__/request.cpython-36.opt-1.pycnu �[��� 3
�\dh~� � ) @ s� d Z ddlZddlZddlZddlZddlZddlZddlZddl Z ddl
Z
ddl Z ddl Z ddl
Z
ddlZddlZddlZddlZddlZddlmZmZmZ ddlmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z) ddl*m+Z+m,Z, y ddl-Z-W n e.k
�r& dZ/Y nX dZ/dd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'd(g!Z0d)e
j1dd*� Z2da3de j4fddddd+�d,d �Z5d-d � Z6g Z7d~d.d%�Z8d/d&� Z9e
j:d0e
j;�Z<d1d2� Z=G d3d� d�Z>G d4d � d �Z?d5d!� Z@G d6d
� d
�ZAG d7d � d eA�ZBG d8d � d eA�ZCG d9d � d eA�ZDd:d;� ZEG d<d� deA�ZFG d=d� d�ZGG d>d� deG�ZHG d?d� deH�ZIG d@d� d�ZJG dAd� deJeA�ZKG dBd� deJeA�ZLejMZNG dCd� d�ZOG dDd� deAeO�ZPG dEd� deAeO�ZQG dFdG� dGeA�ZRG dHd� deR�ZSeTejUdI��r2G dJdK� dKeR�ZVe0jWdK� G dLd
� d
eA�ZXG dMd � d eA�ZYdNdO� ZZdPdQ� Z[G dRd� deA�Z\dSdT� Z]G dUd� deA�Z^G dVd� de^�Z_G dWd � d eA�Z`dXZaejbdYk�r�ddZlcmdZdmeZe nd[d#� Zdd\d"� Zei ZfG d]d'� d'�ZgG d^d(� d(eg�Zhdaid_d`� Zjdakdadb� Zldamdcdd� Zndaodedf� ZpG dgdh� dh�Zqdidj� Zrddkdl�Zsdmdn� Zte
judok�r�ddplvmwZwmxZx dqdr� Zydsdt� Zzdudv� Z{dwd$� Z|n6ejbdYk�r�dxdy� Z}dzd$� Z|d{d|� Z~d}dv� Z{nerZ|esZ{dS )�a�
An extensible library for opening URLs using a variety of protocols
The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below). It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.
The OpenerDirector manages a collection of Handler objects that do
all the actual work. Each Handler implements a particular protocol or
option. The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL. For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns. The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.
urlopen(url, data=None) -- Basic usage is the same as original
urllib. pass the url and optionally data to post to an HTTP URL, and
get a file-like object back. One difference is that you can also pass
a Request instance instead of URL. Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.
build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers. Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate. If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.
install_opener -- Installs a new opener as the default opener.
objects of interest:
OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.
Request -- An object that encapsulates the state of a request. The
state can be as simple as the URL. It can also include extra HTTP
headers, e.g. a User-Agent.
BaseHandler --
internals:
BaseHandler and parent
_call_chain conventions
Example usage:
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
uri='https://mahler:8092/site-updates.py',
user='klem',
passwd='geheim$parole')
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote� splittype� splithost� splitport� splituser� splitpasswd� splitattr�
splitquery�
splitvalue�splittag�to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfddl }|jdtd� |dk r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt dkr�t
� a } nt } | j | ||�S ) a$
Open the URL url, which can be either a string or a Request object.
*data* must be an object specifying additional data to be sent to
the server, or None if no such data is needed. See Request for
details.
urllib.request module uses HTTP/1.1 and includes a "Connection:close"
header in its HTTP requests.
The optional *timeout* parameter specifies a timeout in seconds for
blocking operations like the connection attempt (if not specified, the
global default timeout setting will be used). This only works for HTTP,
HTTPS and FTP connections.
If *context* is specified, it must be a ssl.SSLContext instance describing
the various SSL options. See HTTPSConnection for more details.
The optional *cafile* and *capath* parameters specify a set of trusted CA
certificates for HTTPS requests. cafile should point to a single file
containing a bundle of CA certificates, whereas capath should point to a
directory of hashed certificate files. More information can be found in
ssl.SSLContext.load_verify_locations().
The *cadefault* parameter is ignored.
This function always returns an object which can work as a context
manager and has methods such as
* geturl() - return the URL of the resource retrieved, commonly used to
determine if a redirect was followed
* info() - return the meta-information of the page, such as headers, in the
form of an email.message_from_string() instance (see Quick Reference to
HTTP Headers)
* getcode() - return the HTTP status code of the response. Raises URLError
on errors.
For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse
object slightly modified. In addition to the three new methods above, the
msg attribute contains the same information as the reason attribute ---
the reason phrase returned by the server --- instead of the response
headers as it is specified in the documentation for HTTPResponse.
For FTP, file, and data URLs and requests explicitly handled by legacy
URLopener and FancyURLopener classes, this function returns a
urllib.response.addinfourl object.
Note that None may be returned if no handler handles the request (though
the default installed global OpenerDirector uses UnknownHandler to ensure
this never happens).
In addition, if proxy settings are detected (for example, when a *_proxy
environment variable like http_proxy is set), ProxyHandler is default
installed and makes sure the requests are handled through the proxy.
r NzJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.6/urllib/request.pyr0 � s* <
c C s | a d S )N)rF )rK rL rL rM r1 � s c C s4 t | �\}}tjt| |����}|j� }|dkrD| rDtjj|�|fS |rTt|d�}n t j
dd�}|j }t j
|� |�� ||f} d
}
d} d} d}
d |kr�t|d
�} |r�||
|
| � xB|j|
�}|s�P | t|�7 } |j|� |
d7 }
|r�||
|
| � q�W W d Q R X W d Q R X | dk�r0| | k �r0td | | f | ��| S )aW
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
�file�wbF)�deletei � � r zcontent-lengthzContent-LengthNz1retrieval incomplete: got only %i out of %i bytesi ���)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typerX �fp�headers�tfp�result�bs�sizer_ �blocknum�blockrL rL rM r6 � sD
$c C sH x0t D ](} ytj| � W q tk
r, Y qX qW t dd�= trDdadS )z0Clean up temporary files from urlretrieve calls.N)r\ rW �unlink�OSErrorrF )Z temp_filerL rL rM r7 % s
z:\d+$c C s< | j }t|�d }|dkr&| jdd�}tjd|d�}|j� S )z�Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
rR � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host4 s rw c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sp || _ i | _i | _d | _|| _d | _x |j� D ]\}}| j||� q.W |d krVt| �}|| _ || _
|rl|| _ d S )N) rp re �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerrw �origin_req_host� unverifiable�method) �selfrH rI re r} r~ r �key�valuerL rL rM �__init__F s zRequest.__init__c C s | j rdj| j| j �S | jS )Nz{}#{})�fragment�format� _full_url)r� rL rL rM rp X s zRequest.full_urlc C s( t |�| _t| j�\| _| _| j� d S )N)r r� r r� �_parse)r� rH rL rL rM rp ^ s
c C s d | _ d | _d| _d S )Nrn )r� r� �selector)r� rL rL rM rp e s c C s | j S )N)ry )r� rL rL rM rI k s z Request.datac C s( || j kr$|| _ | jd�r$| jd� d S )NzContent-length)ry �
has_header�
remove_header)r� rI rL rL rM rI o s
c C s
d | _ d S )N)rI )r� rL rL rM rI y s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rp r rv r� r
)r� �restrL rL rM r� } s
zRequest._parsec C s | j dk rdnd}t| d|�S )z3Return a string indicating the HTTP request method.N�POST�GETr )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S )N)rp )r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s4 | j dkr | j r | j| _n|| _ | j| _|| _d S )N�https)r� rz rv rp r� )r� rv r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS )N)r� rp )r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |j� < d S )N)re �
capitalize)r� r� �valrL rL rM r| � s zRequest.add_headerc C s || j |j� < d S )N)rx r� )r� r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS )N)re rx )r� � header_namerL rL rM r� � s
zRequest.has_headerc C s | j j|| jj||��S )N)re �getrx )r� r� �defaultrL rL rM rq � s zRequest.get_headerc C s | j j|d � | jj|d � d S )N)re �poprx )r� r� rL rL rM r� � s zRequest.remove_headerc C s" | j j� }|j| j� t|j� �S )N)rx �copy�updatere �listr{ )r� �hdrsrL rL rM � header_items� s
zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrp �setter�deleterrI r� r� r� r� r� r| r� r� rq r� r� rL rL rL rM r D s(
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )NzPython-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sZ t |d�stdt|� ��d}�xt|�D �]}|dkr:q*|jd�}|d |� }||d d � }|jd �r�|jd�| d }||d d � }y t|�}W n tk
r� Y nX | jj |i �} | | j|< n>|d
kr�|}| j
} n*|d kr�|}| j } n|d kr*|}| j } nq*| j
|g �}
|
�r&tj|
|� n
|
j|� d
}q*W |�rVtj| j|� |j| � d S )N�
add_parentz%expected BaseHandler instance, got %rF�redirect_request�do_open�
proxy_open�_rR �errorrG �responseru T)r� r� r� )�hasattr� TypeErrorr� �dir�find�
startswithr^ rB r� r� r� r� r� �
setdefault�bisectZinsortr] r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sJ
zOpenerDirector.add_handlerc C s d S )NrL )r� rL rL rM �close� s zOpenerDirector.closec G s< |j |f �}x*|D ]"}t||�}||� }|d k r|S qW d S )N)r� r� ) r� �chainr� � meth_name�argsr� r� �funcrg rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }x(| jj|g �D ]}t||�}||�}qLW | j ||�} |d }x*| j
j|g �D ]}t||�}||| �} q�W | S )NZ_requestZ _response) �
isinstance�strr rI rJ r� r� r� r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s"
zOpenerDirector.openc C sP | j | jdd|�}|r|S |j}| j | j||d |�}|r>|S | j | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rg r� rL rL rM r� s
zOpenerDirector._openc G s~ |d
kr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S ) N�httpr� r: z
http_error_%srR Z_errorr r� �http_error_default)r� r� )r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrg rL rL rM r� ' s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|j
t� t� }xN|D ]F}x@| D ]8}t|t�rlt||�r�|j|� qHt||�rH|j|� qHW q>W x|D ]}|j|� q�W x|D ]}|j|� � q�W x&| D ] }t|t�r�|� }|j|� q�W |S )a* Create an opener object from a list of handlers.
The opener will use several default handlers, including support
for HTTP, FTP and when applicable HTTPS.
If any of the handlers passed as arguments are subclasses of the
default handlers, the default handlers will not be used.
�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientr] rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 @ s0
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r i� c C s
|| _ d S )N)�parent)r� r� rL rL rM r� g s zBaseHandler.add_parentc C s d S )NrL )r� rL rL rM r� j s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__n s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r d s c @ s e Zd ZdZdZdd� ZeZdS )r/ z Process HTTP error responses.i� c C sJ |j |j|j� }}}d| ko*dk n sF| jjd|||||�}|S )N�� i, r� )�code�msgrV r� r� )r� ru r� r� r� r� rL rL rM �
http_response{ s
z HTTPErrorProcessor.http_responseN)r� r� r� �__doc__r� r� �https_responserL rL rL rM r/ w s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S )N)r rp )r� r� rd r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c sx |j � }|dkr|dkp&|dko&|dks:t|j||||��|jdd �}d� t� fd d
�|jj� D ��}t|||jdd�S )a� Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
�- �. �/ �3 r� �HEADr� � z%20�content-length� content-typec 3 s& | ] \}}|j � � kr||fV qd S )N)rt )�.0�k�v)�CONTENT_HEADERSrL rM � <genexpr>� s z7HTTPRedirectHandler.redirect_request.<locals>.<genexpr>T)re r} r~ )r� r� r� r� )r� r� )r� r� r� )r� r� ) r� r rp �replacer� re r{ r r} ) r� r� rd r� r� re �newurl�mZ
newheadersrL )r� rM r� � s
z$HTTPRedirectHandler.redirect_requestc
C sN d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|j rp|jrpt|�}d|d < t|�}t|d
tj d �}t
|j |�}| j ||||||�}|d kr�d S t
|d ��r|j } |_| j|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| j|d
�d | |< |j� |j� | jj||jd�S )N�location�urir� r� �ftprn z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rR )rJ )r� r� r� rn )r �schemer rX Znetlocr� r r �stringZ punctuationr rp r� r� r r� � max_repeatsr` �max_redirections�inf_msgr_ r� r� rG rJ )
r� r� rd r� r� re r� �urlparts�newZvisitedrL rL rM �http_error_302� s@
z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r
�http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c C s� t | �\}}|jd�s d}| }n:|jd�s6td| ��|jdd�}|dkrNd}|d|� }t|�\}}|dk r|t|�\}}nd }}||||fS )a Return (scheme, user, password, host/port) given a URL or an authority.
If a URL is supplied, it must have an authority (host:port) component.
According to RFC 3986, having an authority component means the URL must
have two slashes after the scheme.
r� Nz//z proxy URL with no authority: %rr: rR rS )r r� rB r� r r ) �proxyr Zr_scheme� authority�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s
r c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C sL |d krt � }|| _x2|j� D ]&\}}t| d| ||| jfdd�� q W d S )Nz%s_openc S s || ||�S )NrL )�rr r� r� rL rL rM �<lambda>% s z'ProxyHandler.__init__.<locals>.<lambda>)r5 �proxiesr{ �setattrr� )r� r r� rH rL rL rM r� s
zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } tj| j� �jd�}
|j dd|
� t|�}|j
||� ||ks�|dkr�d S | j j ||j
d�S d S )Nz%s:%s�asciizProxy-authorizationzBasic r� )rJ )r� r rv � proxy_bypassr
�base64� b64encode�encode�decoder| r� r� rG rJ ) r� r� r r� Z orig_typeZ
proxy_typer r r Z user_passZcredsrL rL rM r� ( s zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S )N)�passwd)r� rL rL rM r� F s zHTTPPasswordMgr.__init__c s` t |t�r|g}|�jkr$i �j|< x6dD ].� t� �fdd�|D ��}||f�j| |< q*W d S )NTFc s g | ]}�j |� ��qS rL )�
reduce_uri)r� �u)� default_portr� rL rM �
<listcomp>Q s z0HTTPPasswordMgr.add_password.<locals>.<listcomp>)TF)r� r� r �tuple)r� �realmr� r r � reduced_urirL )r# r� rM � add_passwordI s
z HTTPPasswordMgr.add_passwordc C s` | j j|i �}xLdD ]D}| j||�}x2|j� D ]&\}}x |D ]}| j||�r<|S q<W q.W qW dS )NTF)TF)NN)r r� r! r{ � is_suburi) r� r& �authuriZdomainsr# �reduced_authuriZurisZauthinfor� rL rL rM �find_user_passwordT s
z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d}|}d}t|�\}}|r~|dkr~|dk r~ddd�j|�} | dk r~d || f }||fS )
z@Accept authority or URI and extract only the authority and path.rR r r: r� N�P i� )r� r� z%s:%d)r r
r� )
r� r� r# �partsr r rX rv �portZdportrL rL rM r! ^ s zHTTPPasswordMgr.reduce_uric C sR ||kr dS |d |d kr dS t j|d |d f�}t|�t|d �krNdS dS )zcCheck if test is below base in a URI tree
Both args must be URIs in reduced form.
Tr FrR )� posixpath� commonprefixr` )r� �base�test�commonrL rL rM r) u s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r( r, r! r) rL rL rL rM r D s
c @ s e Zd Zdd� ZdS )r! c C s0 t j| ||�\}}|d k r"||fS t j| d |�S )N)r r, )r� r& r* r r rL rL rM r, � s
z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� r, rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S )N)�
authenticated�superr� )r� r� �kwargs)� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | j ||� |d k r&t� jd |||� t� j||||� d S )N)�update_authenticatedr6 r( )r� r& r� r r �is_authenticated)r8 rL rM r( � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C sF t |t�r|g}x0dD ](}x"|D ]}| j||�}|| j|< q W qW d S )NTF)TF)r� r� r! r5 )r� r� r: r# r" r' rL rL rM r9 � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD x>dD ]6}| j ||�}x$| jD ]}| j||�r | j| S q W qW d S )NTF)TF)r! r5 r) )r� r* r# r+ r� rL rL rM r: � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r( r9 r: �
__classcell__rL rL )r8 rM r" � s
c @ sT e Zd Zejdej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S )N)r r r( )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c st d}xFt jj|�D ]6}|j� \}}}|d kr:tjdtd� ||fV d}qW |sp|rb|j� d }nd}|d fV d S )
NF�"�'z Basic Auth Realm was unquoted� Tr rn )r< r= )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r& rL rL rM � _parse_realm� s
z%AbstractBasicAuthHandler._parse_realmc C s~ |j |�}|sd S d }xL|D ]D}x>| j|�D ]0\}}|j� dkrF|}q,|d k r,| j|||�S q,W q W |d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allrE rt �retry_http_basic_authrB ) r� �authreqrv r� re Z unsupportedrD r r& rL rL rM �http_error_auth_reqed� s
z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j j||�\}}|d k rtd||f }dtj|j� �jd� }|j| jd �|krTd S |j| j|� | j j
||j d�S d S d S )Nz%s:%szBasic r )rJ ) r r, r r r r rq � auth_headerr� r� rG rJ )r� rv r� r& r �pw�raw�authrL rL rM rG � s z.AbstractBasicAuthHandler.retry_http_basic_authc C sx t | jd� s | jj|j� r"|S |jd�st| jjd |j�\}}dj||�j� }tj |�j
� }|j ddj|j � �� |S )Nr: �
Authorizationz{0}:{1}zBasic {})
r� r r: rp r� r, r� r r Zstandard_b64encoder r� �strip)r� r� r r Z credentialsZauth_strrL rL rM � http_request s
z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j ko dk n r8| jj|jd� n| jj|jd� |S )Nr: r� i, TF)r� r r� r9 rp )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�Ir? r� rE rI rG rP r� �
https_requestr� rL rL rL rM r# � s
c @ s e Zd ZdZdd� ZdS )r$ rN c C s |j }| jd|||�}|S )Nzwww-authenticate)rp rI )r� r� rd r� r� re rH r� rL rL rM �http_error_401 s
z#HTTPBasicAuthHandler.http_error_401N)r� r� r� rJ rU rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% zProxy-authorizationc C s |j }| jd|||�}|S )Nzproxy-authenticate)rv rI )r� r� rd r� r� re r r� rL rL rM �http_error_407+ s
z$ProxyBasicAuthHandler.http_error_407N)r� r� r� rJ rV rL rL rL rM r% ' s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S )Nr )r r r( �retried� nonce_count�
last_nonce)r� r rL rL rM r� E s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S )Nr )rW )r� rL rL rM �reset_retry_countN s z+AbstractDigestAuthHandler.reset_retry_countc C s| |j |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|j� d }|j� dkr`| j||�S |j� dkrxtd| ��d S ) N� i� zdigest auth failedrR r ZdigestrF zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rW r rp rC rt �retry_http_digest_authrB )r� rJ rv r� re rH r rL rL rM rI Q s
z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |j dd�\}}ttd t|���}| j||�}|rvd| }|jj| jd �|krRd S |j| j|� | j j
||j d�}|S d S )Nr� rR z Digest %s)rJ ) rC �parse_keqv_list�filter�parse_http_list�get_authorizationre r� rJ r� r� rG rJ )r� r� rM �tokenZ challenge�chalZauth_valZresprL rL rM r\ e s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |tj� f }|jd�td� }tj|�j� }|d d� S )Nz %s:%s:%s:r rQ � )rX �timeZctimer � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceq s z$AbstractDigestAuthHandler.get_cnoncec C s� y6|d }|d }|j d�}|j dd�}|j dd �}W n tk
rJ d S X | j|�\}} |d krfd S | jj||j�\}
} |
d kr�d S |jd k r�| j|j|�} nd } d|
|| f }
d|j� |j f }|d k�r.|| j
kr�| j d
7 _ n d
| _ || _
d | j }| j |�}d ||||||�f }| ||
�|�}n2|d k�rT| ||
�d|||�f �}n t
d
| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr& ri �qop� algorithm�MD5�opaquez%s:%s:%sz%s:%srM rR z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr r, rp rI �get_entity_digestr� r� rY rX rm r )r� r� rb r& ri rn ro rq �H�KDr rK ZentdigZA1ZA2ZncvalueZcnonceZnoncebitZrespdigr2 rL rL rM r` | sV
z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nrp c S s t j| jd��j� S )Nr )rf Zmd5r rh )�xrL rL rM r � s z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t j| jd��j� S )Nr )rf rg r rh )rw rL rL rM r � s z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nz%s:%srL )rj �d)ru rL rM r � s )rB )r� ro rv rL )ru rM rs � s
z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S )NrL )r� rI rb rL rL rM rt � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� rZ rI r\ rm r` rs rt rL rL rL rM r& : s
<
c @ s e Zd ZdZdZdZdd� ZdS )r' z�An authentication protocol defined by RFC 2069
Digest authentication improves on basic authentication because it
does not transmit passwords in the clear.
rN i� c C s* t |j�d }| jd|||�}| j� |S )NrR zwww-authenticate)r rp rI rZ )r� r� rd r� r� re rv �retryrL rL rM rU � s
z$HTTPDigestAuthHandler.http_error_401N)r� r� r� r� rJ r� rU rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( zProxy-Authorizationi� c C s" |j }| jd|||�}| j� |S )Nzproxy-authenticate)rv rI rZ )r� r� rd r� r� re rv ry rL rL rM rV � s
z%ProxyDigestAuthHandler.http_error_407N)r� r� r� rJ r� rV rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S )N)� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S )N)r{ )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jjj|j|j� �S )N)r� r� �HTTPConnection�_get_content_lengthrI r� )r� ru rL rL rM r� � s z'AbstractHTTPHandler._get_content_lengthc C s
|j }|std��|jd k r�|j}t|t�r8d}t|��|jd�sN|jdd� |jd� r�|jd� r�| j|�}|d k r�|jdt|�� n |jdd� |}|j � r�t
|j �\}}t |�\}} |jd�s�|jd|� x2| j
jD ]&\}
} |
j� }
|j|
�s�|j|
| � q�W |S ) Nz
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-typez!application/x-www-form-urlencodedzContent-lengthzTransfer-encodingZchunkedro )rv r rI r� r� r� r� r� r� r� r r� r r� r� r� ) r� ru rv rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr[ r� rL rL rM � do_request_� s>
z AbstractHTTPHandler.do_request_c
s\ |j }|std��||fd|ji|��}|j| j� t|j�� � jt� fdd�|jj � D ��� d� d< tdd� � j � D ��� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � y`y&|j |j
� |j|j� |jd
�d � W n, tk
�r
} zt|��W Y d d }~X nX |j� } W n |j� � Y nX |j�rF|jj� d |_|j� | _| j| _| S )
z�Return an HTTPResponse object for the request, using http_class.
http_class must implement the HTTPConnection API from http.client.
z
no host givenrJ c 3 s" | ]\}}|� kr||fV qd S )NrL )r� r� r� )re rL rM r� ) s z.AbstractHTTPHandler.do_open.<locals>.<genexpr>r� �
Connectionc s s | ]\}}|j � |fV qd S )N)�title)r� r[ r� rL rL rM r� 6 s zProxy-Authorization)re zTransfer-encoding)Zencode_chunkedN)rv r rJ Zset_debuglevelr{ r� rx r� re r{ rz Z
set_tunnelru r� r� rI r� rm � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrv r� Ztunnel_headersZproxy_auth_hdr�errr rL )re rM r� s@
"
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r~ r� r� r� rL rL rL rM rz � s
&rz c @ s e Zd Zdd� ZejZdS )r) c C s | j tjj|�S )N)r� r� r� r )r� r� rL rL rM � http_open` s zHTTPHandler.http_openN)r� r� r� r� rz r� rP rL rL rL rM r) ^ s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t j| |� || _|| _d S )N)rz r� �_context�_check_hostname)r� r| r> �check_hostnamerL rL rM r� i s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� )r� r� rL rL rM �
https_openn s zHTTPSHandler.https_open)r NN)r� r� r� r� r� rz r� rT rL rL rL rM rE g s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|jj� }|| _d S )Nr )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� w s
z HTTPCookieProcessor.__init__c C s | j j|� |S )N)r� Zadd_cookie_header)r� ru rL rL rM rP } s z HTTPCookieProcessor.http_requestc C s | j j||� |S )N)r� Zextract_cookies)r� ru r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� rP r� rT r� rL rL rL rM r v s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sR i }xH| D ]@}|j dd�\}}|d dkrB|d dkrB|dd� }|||< q
W |S )z>Parse list of key=value strings where keys are not duplicated.�=rR r r< rS rS )rC )�lZparsedZeltr� r� rL rL rM r] � s
r] c C s� g }d}d }}xt| D ]l}|r,||7 }d}q|rV|dkr@d}qn |dkrLd}||7 }q|dkrn|j |� d}q|dkrzd}||7 }qW |r�|j |� dd� |D �S ) ap Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Neither commas nor quotes count if they are escaped.
Only double-quotes count, not single-quotes.
rn F�\Tr< �,c S s g | ] }|j � �qS rL )rO )r� �partrL rL rM r$ � s z#parse_http_list.<locals>.<listcomp>)r] )rj �resr� �escaper ZcurrL rL rM r_ � s4
r_ c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| j� krXtd��n
| j|�S d S )Nr: z//r> r� � localhostz-file:// scheme is supported only on localhost)r� rv � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &
zFileHandler.file_openNc C s` t jd krZy*ttjd�d tjtj� �d �t _W n$ tjk
rX tjd�ft _Y nX t jS )Nr� r: )r* �namesr% r� �gethostbyname_ex� gethostname�gaierror�
gethostbyname)r� rL rL rM r� � s
zFileHandler.get_namesc C s dd l }dd l}|j}|j}t|�}y�tj|�}|j}|jj |j
dd�} |j |�d }
|j d|
pbd|| f �} |r~t
|�\}} | s�| r�t|�| j� kr�|r�d| | }
nd| }
tt|d�| |
�S W n* tk
r� } zt|��W Y d d }~X nX td��d S ) Nr T)�usegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
z
text/plainzfile://�rbzfile not on local host)� email.utils� mimetypesrv r� r4 rW �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rm r )r� r� �emailr� rv rb Z localfile�statsri �modified�mtypere r/ Zorigurl�exprL rL rM r� � s0
zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s& y
t j| �S t jk
r d S X d S )N)r� r� r� )rv rL rL rM r� � s
r� c @ s e Zd Zdd� Zdd� ZdS )r+ c C s. dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}yt
j |�}W n* t k
r� } zt|��W Y d d }~X nX t
|j�\} }
| jd�} ttt | ��} | d d� | d } } | �r| d �r| dd � } y�| j||||| |j�}
| �r8d�p:d}x:|
D ]2}t|�\}}|j� dk�rB|dk�rB|j� }�qBW |
j| |�\}}d}|j|j�d }|�r�|d
| 7 }|d k �r�|dk�r�|d| 7 }tj|�}t |||j�S |j k
�r( } z$td| �}|j t j � d ��W Y d d }~X nX d S )Nr zftp error: no host givenrn r� rR rS �Dr� �a�Ar� rx zContent-type: %s
zContent-length: %d
z
ftp error: %rr: rS rS )r� r� r� rS rx r� )!�ftplibr� rv r r
�FTP_PORTr^ r r r
r� r� rm r r� rC r� �map� connect_ftprJ r rt �upper�retrfiler� rp r� r� r �
all_errors�with_traceback�sys�exc_info)r� r� r� r� rv r/ r r r� rX �attrs�dirsrN �fwr� �attrr� rd �retrlenre r� r� �excrL rL rM �ftp_open� s\
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r rv r/ r� rJ rL rL rM r� 1 s zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ � s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< rc )�cacherJ �soonest�delay� max_conns)r� rL rL rM r� 8 s
zCacheFTPHandler.__init__c C s
|| _ d S )N)r� )r� �trL rL rM �
setTimeout? s zCacheFTPHandler.setTimeoutc C s
|| _ d S )N)r� )r� r� rL rL rM � setMaxConnsB s zCacheFTPHandler.setMaxConnsc C sr |||dj |�|f}|| jkr4tj� | j | j|< n,t||||||�| j|< tj� | j | j|< | j� | j| S )Nr� )�joinr� rd r� rJ r� � check_cache)r� r r rv r/ r� rJ r� rL rL rM r� E s
zCacheFTPHandler.connect_ftpc C s� t j � }| j|krTx@t| jj� �D ].\}}||k r"| j| j� | j|= | j|= q"W tt| jj� ��| _t | j�| j
kr�x6t| jj� �D ]$\}}|| jkr�| j|= | j|= P q�W tt| jj� ��| _d S )N) rd r� r� rJ r{ r� r� �min�valuesr` r� )r� r� r� r� rL rL rM r� P s
zCacheFTPHandler.check_cachec C s4 x| j j� D ] }|j� q W | j j� | jj� d S )N)r� r� r� �clearrJ )r� �connrL rL rM � clear_cached s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r� r� rL rL rL rM r, 5 s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|jdd�\}}|jdd�\}}t|�}|jd�rNtj|�}|d d� }|sVd}tjd|t|�f �}t t
j |�||�S ) N�:rR r� z;base64� ztext/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
i����) rp rC r �endswithr � decodebytesr� r� r` r �io�BytesIO)r� r� rH r rI Z mediatypere rL rL rM � data_openk s
zDataHandler.data_openN)r� r� r� r� rL rL rL rM r- j s r� �nt)r4 r3 c C s t | �S )zOS-specific conversion from a relative URL of the 'file' scheme
to a file system path; not recommended for general use.)r
)�pathnamerL rL rM r4 � s c C s t | �S )zOS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use.)r )r� rL rL rM r3 � s c @ s� e Zd ZdZdZde Zd*dd�Zdd� Zdd � Z d
d � Z
d d
� Z d+dd�Z d,dd�Z
d-dd�Zd.dd�Zdd� Zd/dd�Zd0dd�Zd d � Zer�d d � Zd1d d!�Zd"d#� Zd$d%� Zd&d'� Zd2d(d)�ZdS )3r8 a, Class to open URLs.
This is a class rather than just a subroutine because we may need
more than one set of global protocol-specific options.
Note -- this is a base class for those who don't want the
automatic handling of errors type 302 (relocated) and 401
(authorization needed).NzPython-urllib/%sc K sz dd| j ji }tj|tdd� |d kr.t� }|| _|jd�| _|jd�| _ d| j
fd
g| _ g | _ t
j| _d | _t| _d S ) NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classr> )�
stacklevel�key_file� cert_filez
User-Agent�Accept�*/*)r� r� )r8 r� r? r@ rA r5 r r� r� r� �versionr� �_URLopener__tempfilesrW rl �_URLopener__unlink� tempcache�ftpcache)r� r Zx509r� rL rL rM r� � s zURLopener.__init__c C s | j � d S )N)r� )r� rL rL rM �__del__� s zURLopener.__del__c C s | j � d S )N)�cleanup)r� rL rL rM r� � s zURLopener.closec C sZ | j rFx2| j D ](}y| j|� W q tk
r4 Y qX qW | j d d �= | jrV| jj� d S )N)r� r� rm r� r� )r� rN rL rL rM r� � s
zURLopener.cleanupc G s | j j|� dS )zdAdd a header to be used by the HTTP interface only
e.g. u.addheader('Accept', 'sound/basic')N)r� r] )r� r� rL rL rM � addheader� s zURLopener.addheaderc C sn t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd}d| } || _ | j
dd�} t | | � s�| d kr�|r�| j |||�S | j
||�S y,|dk�r t| | �|�S t| | �||�S W nV ttfk
�r. � Y n< tk
�rh }
z td
|
�jtj� d ��W Y dd}
~
X nX dS ) z6Use URLopener().open(file) instead of open(file, 'r').z%/:=&?~#+!$,;'@()*[]|)r r� rN NZopen_�-r� r� z socket errorr: )r r r r� rG r r r r r� r� r� �open_unknown_proxy� open_unknownr� r r rm r� r� r� )r� r� rI rb re rd �urltyperH r � proxyhostrv r� r[ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��dS )z/Overridable interface to open unknown URL type.z url errorzunknown url typeN)r rm )r� r� rI r� rH rL rL rM r� s zURLopener.open_unknownc C s t |�\}}tdd| |��dS )z/Overridable interface to open unknown URL type.z url errorzinvalid proxy for %sN)r rm )r� r r� rI r� rH rL rL rM r� s z URLopener.open_unknown_proxyc C s& t t|��}| jr&|| jkr&| j| S t|�\}}|dkr�| sH|dkr�y.| j|�}|j� }|j� tt|�d �|fS t k
r� } zW Y dd} ~ X nX | j
||�}�zH|j� }
|r�t
|d�} n|ddl } t|�\}
}t|p�d�\}
}t |p�d�\}}
t
|�p d�\}}
tjj|�d }| j|�\}}| jj|� tj|d�} z�||
f}| jdk �r^|| j|< d }d
}d}d}d |
k�r�t|
d
�}|�r�||||� xH|j|�}|�s�P |t|�7 }| j|� |d7 }|�r�||||� �q�W W d| j� X W d|j� X |dk�r"||k �r"td ||f |��|S )ztretrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object.NrN rR rO r rn i rQ zcontent-lengthzContent-Lengthz1retrieval incomplete: got only %i out of %i bytesi rS )r r r� r r� rV r� r4 r rm rG rZ r r rW rX �splitextZmkstempr� r] �fdopenr^ r_ r` ra r )r� rH rb rc rI r� Zurl1rd r� r� re rf rZ ZgarbagerX �suffix�fdrg rh ri r_ rj rk rL rL rM �retrieve sl
zURLopener.retrievec C s( d}d}t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d}| j� dkrvd}n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t j
|j � �j d�} nd} |�rt|�}t j
|j � �j d�} nd} ||�}
i }| �r*d| |d< | �r<d| |d < |�rJ||d
< d |d < x | j
D ]\}}|||< �qZW |dk �r�d
|d< |
jd|||� n|
jd||d� y |
j� }W n" tjjk
�r� td��Y nX d|j k�o�dk n �rt||jd| |j�S | j||j|j|j|j|�S dS )a� Make an HTTP connection using connection_class.
This is an internal method that should be called from
open_http() or open_https().
Arguments:
- connection_factory should take a host name and return an
HTTPConnection instance.
- url is the url to retrieval or a host, relative-path pair.
- data is payload for a POST request or None.
Nr� z %s://%s%sz
http errorz
no host givenr zBasic %szProxy-AuthorizationrN ro r� r� z!application/x-www-form-urlencodedz Content-Typer� r� )re z$http protocol error: bad status liner� i, zhttp:)r� r� r r r
r rt r rm r r r r r� ru r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrd r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrv r� Zrealhostr� r� Z
proxy_authrM Z http_connre rD r� r� rL rL rM �_open_generic_httpQ sr
z URLopener._open_generic_httpc C s | j tjj||�S )zUse HTTP protocol.)r� r� r� r )r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|dkr6||||||�} n|||||||�} | rP| S | j|||||�S )z�Handle http errors.
Derived class can override this, or provide specific handlers
named http_error_DDD where DDD is the 3-digit error code.z
http_error_%dN)r� r� r� )
r� rH rd �errcode�errmsgre rI r[ r rg rL rL rM r� � s
zURLopener.http_errorc C s |j � t||||d��dS )z>Default error handler: close the connection and raise OSError.N)r� r )r� rH rd r� r� re rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r� r� )r� r� r� r� r� )r� rv rL rL rM �_https_connection� s zURLopener._https_connectionc C s | j | j||�S )zUse HTTPS protocol.)r� r� )r� rH rI rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|dd� dkrP|dd� dkrP|dd� j� dkrPtd ��n
| j|�S dS )
z/Use local file or FTP depending on form of URL.zEfile error: proxy support for file protocol currently not implementedNr: z//r> r� � z
localhost/z-file:// scheme is supported only on localhost)r� r� r rt rB r� )r� rH rL rL rM � open_file� s
4
zURLopener.open_filec C s\ ddl }ddl}t|�\}}t|�}ytj|�}W n0 tk
rb } zt|j|j ��W Y dd}~X nX |j
} |j j |j
dd�}
|j|�d } |jd| p�d| |
f �} |s�|}
|dd� dkr�d | }
tt|d
�| |
�S t|�\}}| o�tj|�t� ft� k�rP|}
|dd� dk�r d | }
n |dd � d k�r>td
| ��tt|d
�| |
�S td��dS )zUse local file.r NT)r� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
z
text/plainrR r� zfile://r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 rW r� rm r �strerrorrb r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rv rN Z localnamer� �eri r� r� re Zurlfiler/ rL rL rM r� � s:
zURLopener.open_local_filec C s� t |t�std��ddl}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd}t|�}t|ppd�}t|p|d�}t j
|�}|s�ddl }|j }nt
|�}t|�\}} t|�}|jd�}
|
dd� |
d }
} |
o�|
d � r�|
dd� }
|
�r|
d �rd|
d< |||dj|
�f} t| j�tk�rlx8t| j�D ]*}
|
| k�r>| j|
}| j|
= |j� �q>W y�| | jk�r�t|||||
�| j| < | �s�d}nd }x:| D ]2}t|�\}}|j� d
k�r�|dk�r�|j� }�q�W | j| j| |�\}}|jd| �d }d}|�r|d| 7 }|dk �r:|dk�r:|d| 7 }t j |�}t ||d| �S t � k
�r� } z td| �j t!j"� d ��W Y dd}~X nX dS )zUse FTP protocol.zCftp error: proxy support for ftp protocol currently not implementedr Nzftp error: no host givenrn r� rR r� rS r� r� r� r� rx zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: rS rS )r� r� r� rS rx r� )#r� r� r r� r r
r r r
r� r� r� r� r^ r rC r� r` r� � MAXFTPCACHEr� r� r� r rt r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rv rX r/ r r r� r� r� rN r� r� r� r� r� r� rd r� r� re r� rL rL rM �open_ftp� sp
zURLopener.open_ftpc C s< t |t�std��y|jdd�\}}W n tk
rD tdd��Y nX |sNd}|jd�}|dkr�d ||d
� kr�||d d
� }|d
|� }nd }g }|jd tj d
tj
tj� �� � |jd| � |dkr�t j |j
d��jd�}nt|�}|jdt|� � |jd � |j|� dj|�}tj|�}tj|�}t|||�S )zUse "data" URL.zEdata error: proxy support for data protocol currently not implementedr� rR z
data errorz bad data URLztext/plain;charset=US-ASCII�;r r� Nrn zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr r zlatin-1zContent-Length: %d�
)r� r� r rC rB rm �rfindr] rd ZstrftimeZgmtimer r� r r r
r` r� r� r� r� �StringIOr ) r� rH rI r� Zsemir r� re �frL rL rM � open_data3 s6
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r� r� r� r� r� r� r� r� r� rG r� r� r� r� r� r� r� rC r� r� r� r� r r rL rL rL rM r8 � s.
$
B\
:c @ s� e Zd ZdZdd� Zdd� Zd#dd�Zd d
� Zd$d d �Zd%d
d�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd�Zd,d d �Zd-d d �Zd!d"� ZdS ).r9 z?Derived class with handlers for errors we can handle (perhaps).c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtries)r� r� r7 rL rL rM r� ` s zFancyURLopener.__init__c C s t ||d| |�S )z3Default error handling -- don't raise an exception.zhttp:)r )r� rH rd r� r� re rL rL rM r� f s z!FancyURLopener.http_error_defaultNc
C sn | j d7 _ zR| jrJ| j | jkrJt| d�r4| j}n| j}|||dd|�S | j||||||�}|S d| _ X dS )z%Error 302 -- relocated (temporarily).rR �http_error_500i� z)Internal Server Error: Redirect RecursionNr )r
r r� r r� �redirect_internal) r� rH rd r� r� re rI r� rg rL rL rM r
j s
z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |j � t| jd | |�}t|�}|jd krnt|||d| ||��| j|�S )
Nr� r� r� r� r� r� rn z( Redirection to url '%s' is not allowed.)r� r� r� rn )r� r r� r r r rG ) r� rH rd r� r� re rI r� r rL rL rM r
| s
z FancyURLopener.redirect_internalc C s | j ||||||�S )z*Error 301 -- also relocated (permanently).)r
)r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_301c C s | j ||||||�S )z;Error 303 -- also relocated (essentially identical to 302).)r
)r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_303c C s2 |dkr | j ||||||�S | j|||||�S dS )z1Error 307 -- relocated, but turn POST into error.N)r
r� )r� rH rd r� r� re rI rL rL rM r
� s z FancyURLopener.http_error_307Fc
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )z_Error 401 -- authentication required.
This function supports Basic authentication only.zwww-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rF Zretry_� _basic_authN)r8 r� rQ �matchrA rt r� r� )
r� rH rd r� r� re rI ry �stuffr r r& r[ rL rL rM rU � s&
z FancyURLopener.http_error_401c
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )zeError 407 -- proxy authentication required.
This function supports Basic authentication only.zproxy-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rF Z retry_proxy_r N)r8 r� rQ r rA rt r� r� )
r� rH rd r� r� re rI ry r r r r& r[ rL rL rM rV � s&
z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttp://r� �@rR z%s:%s@%srn )r )r r r r� �get_user_passwdr rG )r� rH r& rI rv r� r� r r� r� �
proxyselectorr� r r rL rL rM �retry_proxy_http_basic_auth� s
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttps://r� r rR z%s:%s@%srn )r )r r r r� r r rG )r� rH r& rI rv r� r� r r� r� r r� r r rL rL rM � retry_proxy_https_basic_auth� s
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttp://)r r� r r rG )
r� rH r& rI rv r� r� r r r� rL rL rM rG � s
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttps://)r r� r r rG )
r� rH r& rI rv r� r� r r r� rL rL rM �retry_https_basic_auth s
z%FancyURLopener.retry_https_basic_authr c C s` |d |j � }|| jkr2|r(| j|= n
| j| S | j||�\}}|sJ|rX||f| j|< ||fS )Nr )rt r �prompt_user_passwd)r� rv r& r� r� r r rL rL rM r s
z FancyURLopener.get_user_passwdc C sT ddl }y,td||f �}|j d|||f �}||fS tk
rN t� dS X dS )z#Override this in a GUI environment!r Nz Enter username for %s at %s: z#Enter password for %s in %s at %s: )NN)�getpass�input�KeyboardInterrupt�print)r� rv r& r r r rL rL rM r $ s z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r� r
r
r r r
rU rV r r rG r r r rL rL rL rM r9 ] s$
c C s t dkrtjd�a t S )z8Return the IP address of the magic hostname 'localhost'.Nr� )�
_localhostr� r� rL rL rL rM r� 4 s
r� c C sP t dkrLyttjtj� �d �a W n( tjk
rJ ttjd�d �a Y nX t S )z,Return the IP addresses of the current host.Nr: r� )� _thishostr% r� r� r� r� rL rL rL rM r� < s r� c C s t dkrddl} | ja t S )z1Return the set of errors raised by the FTP class.Nr )�
_ftperrorsr� r� )r� rL rL rM r G s r c C s t dkrtjd�a t S )z%Return an empty email Message object.Nrn )�
_noheadersr� r� rL rL rL rM � noheadersP s
r c @ sJ e Zd ZdZddd�Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r� z;Class used by open_ftp() for cache of open FTP connections.NTc C sX || _ || _|| _|| _|| _|| _d| _|| _y | j� W n | j � � Y nX d S )Nr )
r r rv r/ r� rJ �refcount� keepalive�initr� )r� r r rv r/ r� rJ r� rL rL rM r� ] s zftpwrapper.__init__c C s\ dd l }d| _|j� | _| jj| j| j| j� | jj| j | j
� dj | j �}| jj
|� d S )Nr r� )r� �busyZFTPr� Zconnectrv r/ rJ Zloginr r r� r� �cwd)r� r� Z_targetrL rL rM r# m s
zftpwrapper.initc - C s� dd l }| j� |dkr"d}d}n d| }d}y| jj|� W n* |jk
rh | j� | jj|� Y nX d }|r�| r�y d| }| jj|�\}}W nR |jk
r� } z4t|�d d� d kr�t d
| �j
t j � d ��W Y d d }~X nX |�s�| jjd� |�rn| jj
� } zJy| jj|� W n4 |jk
�rP } zt d
| �|�W Y d d }~X nX W d | jj| � X d | }nd
}| jj|�\}}d| _t|jd�| j�}
| jd7 _|j� |
|fS )Nr rx r� zTYPE ArR zTYPE zRETR r> Z550z
ftp error: %rr: zLIST ZLISTr� )rx r� )r� � endtransferr� Zvoidcmdr� r# Z ntransfercmdZ
error_permr� r r� r� r� �pwdr% r$ r �makefile�
file_closer! r� ) r� rN r� r� �cmd�isdirr� r� r� r' ZftpobjrL rL rM r� v sN
$
zftpwrapper.retrfilec C s
d| _ d S )Nr )r$ )r� rL rL rM r& � s zftpwrapper.endtransferc C s d| _ | jdkr| j� d S )NFr )r" r! �
real_close)r� rL rL rM r� � s
zftpwrapper.closec C s4 | j � | jd8 _| jdkr0| j r0| j� d S )NrR r )r& r! r" r, )r� rL rL rM r) � s zftpwrapper.file_closec C s2 | j � y| jj� W n t� k
r, Y nX d S )N)r& r� r� r )r� rL rL rM r, � s
zftpwrapper.real_close)NT) r� r� r� r� r� r# r� r& r� r) r, rL rL rL rM r� Z s
-r� c C s� i } xBt jj� D ]4\}}|j� }|r|dd� dkr|| |dd� < qW dt jkr^| jdd� xXt jj� D ]J\}}|dd� dkrj|j� }|r�|| |dd � < qj| j|dd
� d� qjW | S ) a Return a dictionary of scheme -> proxy server URL mappings.
Scan the environment for variables named <scheme>_proxy;
this seems to be the standard convention. If you need a
different way, you can pass a proxies dictionary to the
[Fancy]URLopener constructor.
� N�_proxyZREQUEST_METHODr� i����i����i����i����i����)rW �environr{ rt r� )r r[ r� rL rL rM �getproxies_environment� s
r0 c
C s� |dkrt � }y |d }W n tk
r. dS X |dkr<dS t| �\}}dd� |jd�D �}xP|D ]H}|rb|jd �}tj|�}d
| }tj||tj�s�tj|| tj�rbdS qbW dS ) z�Test if proxies should not be used for a particular host.
Checks the proxy dict for the value of no_proxy, which should
be a list of comma separated DNS suffixes, or '*' for all hosts.
N�nor �*rR c S s g | ] }|j � �qS rL )rO )r� r rL rL rM r$ � s z,proxy_bypass_environment.<locals>.<listcomp>r� �.z
(.+\.)?%s$) r0 rr r
rC �lstriprQ r� r rS )rv r Zno_proxy�hostonlyr/ Z
no_proxy_listr[ �patternrL rL rM �proxy_bypass_environment� s&
r7 c
C s ddl m } t| �\}}dd� }d| kr4|d r4dS d}x�|jd f �D ]�}|sPqFtjd
|�}|dk �r|dkr�ytj|�}||�}W n tk
r� wFY nX ||jd ��} |jd �}
|
dkr�d
|jd �j d�d }
nt
|
d d� �}
d|
}
||
? | |
? k�rdS qF|| |�rFdS qFW dS )aj
Return True iff this host shouldn't be accessed using a proxy
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
{ 'exclude_simple': bool,
'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
}
r )�fnmatchc S sh | j d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nr3 r� r � rR rc r: rQ r> )rC r� r� r^ r` )ZipAddrr. rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numr3 Zexclude_simpleTN�
exceptionsz(\d+(?:\.\d+)*)(/\d+)?rR r: rQ � F) r8 r
r� rQ r r� r� rm �group�countr^ ) rv �proxy_settingsr8 r5 r/ r: ZhostIPr� r� r2 �maskrL rL rM � _proxy_bypass_macosx_sysconf� s:
rA �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S )N)rC rA )rv r? rL rL rM �proxy_bypass_macosx_sysconf:
s rE c C s t � S )z�Return a dictionary of scheme -> proxy server URL mappings.
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
)rD rL rL rL rM �getproxies_macosx_sysconf>
s rF c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or from the MacOSX framework SystemConfiguration.
N)r0 r7 rE )rv r rL rL rM r H
s
r c C s t � p
t� S )N)r0 rF rL rL rL rM r5 U
s c C s i } y ddl }W n tk
r$ | S X y�|j|jd�}|j|d�d }|r�t|j|d�d �}d|kr�x�|jd�D ]4}|jdd�\}}tjd |�s�d
||f }|| |< qrW n>|dd � d kr�|| d
< n$d| | d
< d| | d< d| | d< |j � W n t
t t fk
�r Y nX | S )zxReturn a dictionary of scheme -> proxy server URL mappings.
Win32 uses the registry to store proxies.
r Nz;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r rR z ^([^/:]+)://z%s://%sr[ zhttp:r� z http://%sz
https://%sr� zftp://%sr� )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� rC rQ r ZCloserm rB r� )r rH �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryZ
s8
rP c C s t � p
t� S )z�Return a dictionary of scheme -> proxy server URL mappings.
Returns settings gathered from the environment, if specified,
or the registry.
)r0 rP rL rL rL rM r5 �
s c & C s~ y dd l }W n tk
r dS X y6|j|jd�}|j|d�d }t|j|d�d �}W n tk
rl dS X | sz| r~dS t| �\}}|g} y tj |�}||kr�| j
|� W n tk
r� Y nX y tj |�}||kr�| j
|� W n tk
� r� Y nX |j d�}xp|D ]h} | dk�r*d|k�r*dS | j
dd �} | j
d
d �} | j
d d�} x$| D ] }
tj| |
tj��rTdS �qTW �qW dS )
Nr z;Software\Microsoft\Windows\CurrentVersion\Internet SettingsrG Z
ProxyOverrider z<local>r3 rR z\.r2 z.*�?)rH rI rJ rK rL r� rm r
r� r� r] ZgetfqdnrC r� rQ r rS ) rv rH rM rN Z
proxyOverrideZrawHostr/ ZaddrZfqdnr3 r� rL rL rM �proxy_bypass_registry�
sR
rR c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
N)r0 r7 rR )rv r rL rL rM r �
s
)NNN)N)r� r r� r� rf Z http.clientr� r� rW r0 rQ r� r r� rd � collectionsrZ rT r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD rI rC �__all__� version_infor� rF r� r0 r1 r\ r6 r7 rR �ASCIIrr rw r r r2 r r/ r r r r r r! r" r# r$ r% �urandomre r& r' r( rz r) r� r� rE r] r r. r] r_ r* r� r+ r, r- r r[ Z
nturl2pathr4 r3 r� r8 r9 r r� r r� r r r r r� r0 r7 rA �platformZ_scproxyrC rD rE rF r r5 rP rR rL rL rL rM �<module>D s� P
T
?n $q *@
o v
+3:5! A W
_
#<
- 2
PK (�Z�s/�l� l� & __pycache__/parse.cpython-36.opt-1.pycnu �[��� 3
�\dhɨ � @ s� d Z ddlZddlZddlZddlZddlZddddddd d
d d d
ddddddddddgZddddd d d d d d!d"d#d$d%d&d'd(d)d*gZddddd d+d d d d"d d!d,d#d$d%d-d'd(d&d.d/d0d)d*gZddd1d#dd d d!d$d%d2d3d"d&d4gZ dd1d5d6d+d d d,d2d3g
Z
ddd d d d!d"dd$d%d2d3g Z ddd1ddd6d d d d!d,d d#g
Z d7Z
d8Zd9d:d;gZd<Zi Zd=d>� Zd?Zd@ZdAdB� ZeefdCdD�ZeefdEdF�ZdGdH� ZG dIdJ� dJe�ZG dKdL� dLe�ZG dMdN� dNe�Z G dOdP� dPe e�Z G dQdR� dRe e�Z ddSlm Z e ddT�Z e ddU�Z!e ddV�Z"dWe _ dXe j#_ dYe j$_ dZe!_ d[e!j%_ d\e!j&_ d]e!j'_ d^e!j(_ d_e!j$_ d`e"_ e!j%j e"j%_ e!j&j e"j&_ e!j'j e"j'_ dae"j)_ e!j(j e"j(_ e!j$j e"j$_ e Z*G dbd� de e�Z+G dcd� de!e �Z,G ddd� de"e �Z-G ded� de e�Z.G dfd� de!e �Z/G dgd� de"e �Z0dhdi� Z1e1� [1d�dkd�Z2dldm� Z3d�dndo�Z4dpdq� Z5drds� Z6dtdu� Z7d�dvd�Z8dwd� Z9dxd� Z:d�dyd�Z;dzd� Z<d{Z=da>d|d� Z?ej@d}�ZAd�d�d�ZBd�d�d
�ZCG d�d�� d�eD�ZEd�ZFdaGd�d�d �ZHd�d�d�ZIeJd��ZKeLeK�ZMi ZNG d�d�� d�ejO�ZPd�d�d �ZQd�d�d
�ZRd�d�d�ZSd�dddeRfd�d �ZTd�d�� ZUd�d�� ZVdaWd�d�� ZXdaYd�d�� ZZd�d�� Z[d�d�� Z\da]d�d�� Z^d�d�d��Z_d�d�� Z`d�d�� Zad�d�� Zbd�d�� ZcdS )�a3 Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t j� tj� dS )z,Clear the parse cache and the quoters cache.N)� _parse_cache�clear�
_safe_quoters� r! r! �$/usr/lib64/python3.6/urllib/parse.py� clear_cache` s r# �ascii�strictc C s | S )Nr! )�objr! r! r" �_noopo s r' c C s | j ||�S )N)�encode)r& �encoding�errorsr! r! r" �_encode_resultr s r+ c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|j � ��nd V qdS )r N)�decode)�.0�x)r) r* r! r" � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr) r* r! )r) r* r" � _decode_argsv s r2 c G sZ t | d t�}x.| dd � D ] }|r t |t�|kr td��q W |rL| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr' r2 r+ )r1 Z str_input�argr! r! r" � _coerce_argsz s
r8 c @ s e Zd ZdZf Zddd�ZdS )�_ResultMixinStrz>Standard approach to encoding parsed results from str to bytesr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r( )r- r. )r) r* r! r" r/ � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart)�selfr) r* r! )r) r* r" r( � s z_ResultMixinStr.encodeN)r$ r% )�__name__�
__module__� __qualname__�__doc__� __slots__r( r! r! r! r" r9 � s r9 c @ s e Zd ZdZf Zddd�ZdS )�_ResultMixinBytesz>Standard approach to decoding parsed results from bytes to strr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r, )r- r. )r) r* r! r" r/ � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpart)r; r) r* r! )r) r* r" r, � s z_ResultMixinBytes.decodeN)r$ r% )r< r= r> r? r@ r, r! r! r! r" rA � s rA c @ sD e Zd ZdZf Zedd� �Zedd� �Zedd� �Zedd � �Z d
S ) �_NetlocResultMixinBasezHShared methods for the parsed result objects containing a netloc elementc C s
| j d S )Nr )� _userinfo)r; r! r! r" �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr3 )rD )r; r! r! r" �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|j|�\}}}|j� | | S )Nr �%� %)� _hostinfor4 r5 � partition�lower)r; �hostname� separatorZpercentZzoner! r! r" rL � s
z _NetlocResultMixinBase.hostnamec C s@ | j d }|d k r<t|d�}d| ko.dkn s<td��|S )Nr3 �
r i�� zPort out of range 0-65535)rI �int�
ValueError)r; �portr! r! r" rQ � s
z_NetlocResultMixinBase.portN)
r< r= r> r? r@ �propertyrE rF rL rQ r! r! r! r" rC � s rC c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinStrc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N�@�:)�netloc�
rpartitionrJ )r; rV �userinfo� have_info�hostinforE �
have_passwordrF r! r! r" rD � s z _NetlocResultMixinStr._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )NrT �[�]rU )rV rW rJ )r; rV �_rZ � have_open_br� bracketedrL rQ r! r! r" rI � s z _NetlocResultMixinStr._hostinfoN)r< r= r> r@ rR rD rI r! r! r! r" rS � s rS c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinBytesc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N� @� :)rV rW rJ )r; rV rX rY rZ rE r[ rF r! r! r" rD � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )Nrb � [� ]rc )rV rW rJ )r; rV r^ rZ r_ r` rL rQ r! r! r" rI � s z!_NetlocResultMixinBytes._hostinfoN)r< r= r> r@ rR rD rI r! r! r! r" ra � s ra )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zr
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N�#)�fragment�url)r; r! r! r" �geturlE s zDefragResult.geturlN)r< r= r> r@ rj r! r! r! r" r C s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj M s zSplitResult.geturlN)r< r= r> r@ rj r! r! r! r" r K s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj R s zParseResult.geturlN)r< r= r> r@ rj r! r! r! r" r P s c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N� #)rh ri )r; r! r! r" rj X s zDefragResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r V s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj ` s zSplitResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r ^ s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj e s zParseResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r c s c C s8 t tfttfttff} x | D ]\}}||_||_q W d S )N)r r r r r r r: rB )Z
_result_pairsZ_decodedZ_encodedr! r! r" �_fix_result_transcodingi s
rl Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )a# Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.�;r )r8 r � uses_params� _splitparamsr )
ri �scheme�allow_fragments�_coerce_resultZ splitresultrV �queryrh �params�resultr! r! r" r v s c C sR d| kr,| j d| jd��}|dk r6| dfS n
| j d�}| d |� | |d d � fS )N�/rm r r r3 )�find�rfind)ri �ir! r! r" ro � s
ro c C sL t | �}x*dD ]"}| j||�}|dkrt||�}qW | ||� | |d � fS )Nz/?#r )�lenrw �min)ri �start�delim�cZwdelimr! r! r" � _splitnetloc� s
r c C s� | st dd� | D �� r d S dd l}| jdd�}|jdd�}|jdd�}|jdd�}|jd |�}||krnd S x(d
D ] }||krttd | d d
��qtW d S )Nc s s | ]}t |�d kV qdS )� N)�ord)r- r~ r! r! r" r/ � s z _checknetloc.<locals>.<genexpr>r rT r rU rg �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�any� unicodedata�replace� normalizerP )rV r� �nZnetloc2r~ r! r! r" � _checknetloc� s
r� c C s xt D ]}| j|d�} qW | S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )ri �br! r! r" � _remove_unsafe_bytes_from_url� s
r� c C sB | j d�r tjd| �s>td��n tj| �}t|tj�r>td��d S )N�vz\Av[a-fA-F0-9]+\..+\Zz IPvFuture address is invalidz%An IPv4 address cannot be in brackets)�
startswith�re�matchrP � ipaddressZ
ip_addressr4 Z IPv4Address)rL Zipr! r! r" �_check_bracketed_host� s
r� c C s� t | |�\} }}t| �} t|�}| jt�} |jt�}t|�}| ||t| �t|�f}tj|d�}|rj||�S t t�t
kr|t � d } }}| j d�} | dk�r�| d| � dk�r~| d| � j
� }| | d d� } | dd� dk�r t| d�\}} d |ko�d
|k�sd
|k�r d |k�r td ��|�r<d | k�r<| jd d�\} }d
| k�rV| jd
d�\} }t|� t||| ||�}
|
t|< ||
�S xd| d| � D ]} | tk�r�P �q�W | | d d� } | �s�tdd� | D ���r�| d| � j
� | }} | dd� dk�rht| d�\}} d |k�rd
|k�s,d
|k�r4d |k�r4td ��d |k�rhd
|k�rh|jd �d jd
�d }
t|
� |�r�d | k�r�| jd d�\} }d
| k�r�| jd
d�\} }t|� t||| ||�}
|
t|< ||
�S )a Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.Nr rU r r r3 � z//r\ r] zInvalid IPv6 URLrg r� c s s | ]}|d kV qdS )�
0123456789Nr! )r- r~ r! r! r" r/ � s zurlsplit.<locals>.<genexpr>)r8 r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getrz �MAX_CACHE_SIZEr# rw rK r rP �splitr� r � scheme_charsr� rJ r� )ri rp rq rr �key�cachedrV rs rh ry r� r~ �restZbracketed_hostr! r! r" r � sj
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )z�Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent).z%s;%s)r8 r )�
componentsrp rV ri rt rs rh rr r! r! r" r � s c C s� t | � \}}}}}}|s4|r`|tkr`|dd� dkr`|rP|dd� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S )
ak Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent).Nr� z//r3 rv r rU r� rg )r8 � uses_netloc)r� rp rV ri rs rh rr r! r! r" r s c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | r�|
r�|} |}
|s�|}|t|
| | |
||f��S |jd�}|d dkr�|d= | dd� dk� r�| jd�}n(|| jd� }td|dd � �|dd
�< g }xX|D ]P}|dk�rdy |j� W n tk
�r` Y nX n|dk�rt�q0n
|j |� �q0W |d d k�r�|j d� |t|
| dj
|��p�d|
||f��S )
zaJoin a base URL and a possibly relative URL to form an absolute
interpretation of the latter.r rv r3 N�..�.���r� r� r� r� )r� r� ) r8 r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baseri rq rr ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentrp rV �pathrt rs rh Z
base_partsZsegmentsZ
resolved_pathZsegr! r! r" r sT
c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )z�Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
rg r )r8 r r r ) ri rr �sr� �p�a�qZfragZdefragr! r! r" r _ s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| jd�} | j d�}t|�dkr<| S |d g}|j}tdkrbdd� tD �axb|dd� D ]R}y(|t|dd � � ||d d� � W qp tk
r� |d� ||� Y qpX qpW dj |�S )
z,unquote_to_bytes('abc%20def') -> b'abc def'.� zutf-8rH r3 r Nc S s4 i | ],}t D ]"}tt|| d �g�|| j� �q qS )� )�_hexdig�bytesrO r( )r- r� r� r! r! r" �
<dictcomp>� s z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r4 r5 r( rz r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr! r! r" r r s*
z([ -]+)�utf-8r� c C s� d| kr| j | S |dkr d}|dkr*d}tj | �}|d g}|j}x@tdt|�d�D ],}|t|| �j||�� |||d � qVW dj|�S ) a� Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
rG Nzutf-8r� r r3 r� r )r� �_asciirer� �rangerz r r, r� )r� r) r* r� r� r� ry r! r! r" r � s
Fc C sR i }t | ||||||d�}x2|D ]*\} }
| |kr@|| j|
� q |
g|| < q W |S )a� Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError if there
are more than n fields read by parse_qsl().
Returns a dictionary.
)r) r* �max_num_fieldsrM )r
r� ) �qs�keep_blank_values�strict_parsingr) r* r� rM Z
parsed_result�pairs�name�valuer! r! r" r � s c @ s e Zd ZdZdS )� _QueryStringSeparatorWarningz>Warning for using default `separator` in parse_qs or parse_qslN)r< r= r> r? r! r! r! r" r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |jd�}| s6t|ttf� rF|dk rFtd��t� }|dk�rVt}d} |dkrvtj j
| �}d}
|dkr�y t t �} W n t
k
r� Y nJX | �: ddl} | jdd'd�}
|
j| � |
j
d | dd
�}|aW dQ R X t }
|dk�r d | k�rdd lm} |d-tdd� d}n:|dk�r,|}n*t|�dk�rVt| � d|
� d�d d ��|dk �r�||k�r�d| jd� | jd � }nd| j|� }||k �r�td ��||k�r�d d � | jd�D �}nd d � | j|�D �}g }x�|D ]�}| �r�| �r��q�|jd!d�}t|�dk�r>|�r(td"|f ��|�r�|jd#� n�q�t|d ��sR|�r�|d jd$d%�}t|||d&�}||�}|d jd$d%�}t|||d&�}||�}|j||f� �q�W |S ).a� Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError
if there are more than n fields read by parse_qsl().
Returns a list, as G-d intended.
r$ Nz*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler rg )Z
interpolationZcomment_prefixesr )Zfallbackrm )�warnz4The default separator of urllib.parse.parse_qsl and z1parse_qs was changed to '&' to avoid a web cache z"poisoning issue (CVE-2021-23336). z4By default, semicolons no longer act as query field z separators. z3See https://access.redhat.com/articles/5860431 for z
more details.r� )�
stacklevel�&Zlegacyr3 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|j d �D ]}|�qqS )rm )r� )r- �s1�s2r! r! r" �
<listcomp>< s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r! r! )r- r� r! r! r" r� > s �=zbad query field: %rr �+� )r) r* )rg zeThe default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for a The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.)r8 r4 r� r, r5 rP �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� rz �countr� r� r� r )r� r� r� r) r* r� rM rr Z_legacyZ envvar_nameZ
config_sourcer r� �configr� �
num_fieldsr� �rZ
name_valueZnvr� r� r! r! r" r
� s�
c C s | j dd�} t| ||�S )z�Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
r� r� )r� r )r� r) r* r! r! r" r V s sA ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) �Quoterz�A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
c C s t j|�| _dS )zsafe: bytes object.N)� _ALWAYS_SAFE�union�safe)r; r� r! r! r" �__init__n s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__r< �dict)r; r! r! r" �__repr__r s zQuoter.__repr__c C s( || j krt|�ndj|�}|| |< |S )Nz%{:02X})r� �chr�format)r; r� r� r! r! r" � __missing__v s zQuoter.__missing__N)r< r= r> r? r� r� r� r! r! r! r" r� f s r� rv c C sb t | t�r8| s| S |dkr d}|dkr*d}| j||�} n |dk rHtd��|dk rXtd��t| |�S )a� quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted.
RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
the following reserved characters.
reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
"$" | ","
Each of these characters is reserved in some component of a URL,
but not necessarily in all of them.
By default, the quote function is intended for quoting the path
section of a URL. Thus, it will not encode '/'. This character
is reserved, but in typical usage the quote function is being
called on a path where the existing slash characters are used as
reserved characters.
string and safe may be either str or bytes objects. encoding and errors
must not be specified if string is a bytes object.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
Nzutf-8r% z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r4 r5 r( r6 r
)r� r� r) r* r! r! r" r | s
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | jdd�S )z�Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
r� � r� )r4 r5 r� r r� )r� r� r) r* Zspacer! r! r" r � s
c s� t | ttf�std��| s dS t |t�r6|jdd�}ntdd� |D ��}| jt| �s^| j� S y t | � W n& t
k
r� t |�j t |< � Y nX dj
� fdd�| D ��S )z�Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def?') -> 'abc%20def%3f'
z!quote_from_bytes() expected bytesr r$ �ignorec S s g | ]}|d k r|�qS )� r! )r- r~ r! r! r" r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r! r! )r- �char)�quoterr! r" r� � s )r4 r� � bytearrayr6 r5 r( �rstrip�_ALWAYS_SAFE_BYTESr, r r� r� � __getitem__r� )Zbsr� r! )r� r" r
� s
c C s t | d�r| j� } nRy t| �r2t| d t� r2t�W n0 tk
rd tj� \}}}td�j|��Y nX g } |s�xr| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | j |
d | � qtW �n,�x(| D �] \}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rL|| |�} | j |
d | � q�t| t
��rz|| |||�} | j |
d | � q�y t| �} W n: tk
�r� |t
| �|||�} | j |
d | � Y q�X xJ| D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| j |
d |
� �q�W q�W dj | �S )a^ Encode a dict or sequence of two-element tuples into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The components of a query arg may each be either a string or a bytes type.
The safe, encoding, and errors parameters are passed down to the function
specified by quote_via (encoding and errors only if a component is a str).
�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� rz r4 r0 r6 �sys�exc_info�with_tracebackr� r5 r� r� )rs Zdoseqr� r) r* Z quote_viaZtyZva�tb�l�kr� r. Zeltr! r! r" r � sP
c C sJ t | t�rFy| jd�j� } W n( tk
rD tdt| � d ��Y nX | S )zto_bytes(u"URL") --> 'URL'.�ASCIIzURL z contains non-ASCII characters)r4 r5 r( r, � UnicodeError�repr)ri r! r! r" �to_bytes s
r� c C s` t | �j� } | dd� dkr<| dd� dkr<| dd� j� } | dd� dkr\| dd� j� } | S ) z8unwrap('<URL:type://host/path>') --> 'type://host/path'.Nr3 �<�>� zURL:r� r� )r5 r� )ri r! r! r" �unwrap, s r c C sD t dkrtjdtj�a t j| �}|r<|j� \}}|j� |fS d| fS )z:splittype('type:opaquestring') --> 'type', 'opaquestring'.Nz
([^/:]+):(.*))� _typeprogr� �compile�DOTALLr� �groupsrK )ri r� rp �datar! r! r" � splittype5 s
r c C sX t dkrtjdtj�a t j| �}|rP|j� \}}|rH|d dkrHd| }||fS d| fS )z;splithost('//host[:port]/path') --> 'host[:port]', '/path'.Nz//([^/#?]*)(.*)r rv )� _hostprogr� r r r� r )ri r� Z host_portr� r! r! r" � splithostB s
r c C s | j d�\}}} |r|nd| fS )zJsplituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.rT N)rW )�host�userr} r! r! r" � splituserP s r c C s | j d�\} }}| |r|ndfS )z/splitpasswd('user:passwd') -> 'user', 'passwd'.rU N)rJ )r r} Zpasswdr! r! r" � splitpasswdU s r
c C sD t dkrtjdtj�a t j| �}|r<|j� \} }|r<| |fS | dfS )z*splitport('host:port') --> 'host', 'port'.Nz(.*):([0-9]*)$)� _portprogr� r r r� r )r
r� rQ r! r! r" � splitport\ s
r r3 c C sT | j d�\} }}|s|} n2|rLy t|�}W n tk
rB d}Y nX | |fS | |fS )z�Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number.rU N)rW rO rP )r
Zdefportr} rQ Znportr! r! r" �
splitnporti s
r c C s$ | j d�\}}}|r ||fS | dfS )z/splitquery('/path?query') --> '/path', 'query'.r� N)rW )ri r� r} rs r! r! r" �
splitqueryy s r c C s$ | j d�\}}}|r ||fS | dfS )z)splittag('/path#tag') --> '/path', 'tag'.rg N)rW )ri r� r} �tagr! r! r" �splittag� s r c C s | j d�}|d |dd� fS )zksplitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...].rm r r3 N)r� )ri Zwordsr! r! r" � splitattr� s
r c C s | j d�\} }}| |r|ndfS )z-splitvalue('attr=value') --> 'attr', 'value'.r� N)rJ )�attrr} r� r! r! r" �
splitvalue� s r )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )rv NN)r NN)rv r� )r� )dr? r� r� r� � collectionsr� �__all__r� r� rn Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r# Z_implicit_encodingZ_implicit_errorsr' r+ r2 r8 r� r9 rA rC rS ra rf Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBaseri rh rp rV r� rs rt Z
ResultBaser r r r r r rl r ro r r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r � defaultdictr� r r r
r r� r r r r r r r
r r r r r r r r! r! r! r" �<module> s
!
C
E
&
y
,
O
PK (�Z�犽�b �b & __pycache__/parse.cpython-36.opt-2.pycnu �[��� 3
�\dhɨ � @ s� d dl Z d dlZd dlZd dlZd dlZdddddddd d
d d d
dddddddddgZdddddd d d d d d!d"d#d$d%d&d'd(d)gZdddddd*d d d d!d d d+d"d#d$d,d&d'd%d-d.d/d(d)gZddd0d"dd d d d#d$d1d2d!d%d3gZdd0d4d5d*d d d+d1d2g
Z ddd d d d d!dd#d$d1d2g Z
ddd0ddd5dd d d d+d d"g
Z d6Z d7Z
d8d9d:gZd;Zi Zd<d=� Zd>Zd?Zd@dA� ZeefdBdC�ZeefdDdE�ZdFdG� ZG dHdI� dIe�ZG dJdK� dKe�ZG dLdM� dMe�ZG dNdO� dOee�Z G dPdQ� dQee�Z d dRlm Z e ddS�Z e ddT�Z e ddU�Z!dVe _"dWe j#_"dXe j$_"dYe _"dZe j%_"d[e j&_"d\e j'_"d]e j(_"d^e j$_"d_e!_"e j%j"e!j%_"e j&j"e!j&_"e j'j"e!j'_"d`e!j)_"e j(j"e!j(_"e j$j"e!j$_"e Z*G dad� de e�Z+G dbd� de e �Z,G dcd� de!e �Z-G ddd� de e�Z.G ded� de e �Z/G dfd� de!e �Z0dgdh� Z1e1� [1d�djd�Z2dkdl� Z3d�dmdn�Z4dodp� Z5dqdr� Z6dsdt� Z7d�dud�Z8dvd� Z9dwd� Z:d�dxd�Z;dyd� Z<dzZ=da>d{d� Z?e j@d|�ZAd�dd�ZBd�d�d �ZCG d�d�� d�eD�ZEd�ZFdaGd�d�d
�ZHd�d�d�ZIeJd��ZKeLeK�ZMi ZNG d�d�� d�ejO�ZPd�d�d �ZQd�d�d �ZRd�d�d
�ZSd�dddeRfd�d�ZTd�d�� ZUd�d�� ZVdaWd�d�� ZXdaYd�d�� ZZd�d�� Z[d�d�� Z\da]d�d�� Z^d�d�d��Z_d�d�� Z`d�d�� Zad�d�� Zbd�d�� ZcdS )�� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t j� tj� d S )N)� _parse_cache�clear�
_safe_quoters� r! r! �$/usr/lib64/python3.6/urllib/parse.py� clear_cache` s r# �ascii�strictc C s | S )Nr! )�objr! r! r" �_noopo s r' c C s | j ||�S )N)�encode)r& �encoding�errorsr! r! r" �_encode_resultr s r+ c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|j � ��nd V qdS )r N)�decode)�.0�x)r) r* r! r" � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr) r* r! )r) r* r" � _decode_argsv s r2 c G sZ t | d t�}x.| dd � D ] }|r t |t�|kr td��q W |rL| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr' r2 r+ )r1 Z str_input�argr! r! r" � _coerce_argsz s
r8 c @ s e Zd Zf Zddd�ZdS )�_ResultMixinStrr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r( )r- r. )r) r* r! r" r/ � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart)�selfr) r* r! )r) r* r" r( � s z_ResultMixinStr.encodeN)r$ r% )�__name__�
__module__� __qualname__� __slots__r( r! r! r! r" r9 � s r9 c @ s e Zd Zf Zddd�ZdS )�_ResultMixinBytesr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r, )r- r. )r) r* r! r" r/ � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpart)r; r) r* r! )r) r* r" r, � s z_ResultMixinBytes.decodeN)r$ r% )r< r= r> r? r, r! r! r! r" r@ � s r@ c @ s@ e Zd Zf Zedd� �Zedd� �Zedd� �Zedd� �Zd S )
�_NetlocResultMixinBasec C s
| j d S )Nr )� _userinfo)r; r! r! r" �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr3 )rC )r; r! r! r" �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|j|�\}}}|j� | | S )Nr �%� %)� _hostinfor4 r5 � partition�lower)r; �hostname� separatorZpercentZzoner! r! r" rK � s
z _NetlocResultMixinBase.hostnamec C s@ | j d }|d k r<t|d�}d| ko.dkn s<td��|S )Nr3 �
r i�� zPort out of range 0-65535)rH �int�
ValueError)r; �portr! r! r" rP � s
z_NetlocResultMixinBase.portN) r< r= r> r? �propertyrD rE rK rP r! r! r! r" rB � s
rB c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinStrc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N�@�:)�netloc�
rpartitionrI )r; rU �userinfo� have_info�hostinforD �
have_passwordrE r! r! r" rC � s z _NetlocResultMixinStr._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )NrS �[�]rT )rU rV rI )r; rU �_rY � have_open_br� bracketedrK rP r! r! r" rH � s z _NetlocResultMixinStr._hostinfoN)r< r= r> r? rQ rC rH r! r! r! r" rR � s rR c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinBytesc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N� @� :)rU rV rI )r; rU rW rX rY rD rZ rE r! r! r" rC � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )Nra � [� ]rb )rU rV rI )r; rU r] rY r^ r_ rK rP r! r! r" rH � s z!_NetlocResultMixinBytes._hostinfoN)r< r= r> r? rQ rC rH r! r! r! r" r` � s r` )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zr
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N�#)�fragment�url)r; r! r! r" �geturlE s zDefragResult.geturlN)r< r= r> r? ri r! r! r! r" r C s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" ri M s zSplitResult.geturlN)r< r= r> r? ri r! r! r! r" r K s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" ri R s zParseResult.geturlN)r< r= r> r? ri r! r! r! r" r P s c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N� #)rg rh )r; r! r! r" ri X s zDefragResultBytes.geturlN)r< r= r> r? ri r! r! r! r" r V s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" ri ` s zSplitResultBytes.geturlN)r< r= r> r? ri r! r! r! r" r ^ s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" ri e s zParseResultBytes.geturlN)r< r= r> r? ri r! r! r! r" r c s c C s8 t tfttfttff} x | D ]\}}||_||_q W d S )N)r r r r r r r: rA )Z
_result_pairsZ_decodedZ_encodedr! r! r" �_fix_result_transcodingi s
rk Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )N�;r )r8 r � uses_params� _splitparamsr )
rh �scheme�allow_fragments�_coerce_resultZ splitresultrU �queryrg �params�resultr! r! r" r v s c C sR d| kr,| j d| jd��}|dk r6| dfS n
| j d�}| d |� | |d d � fS )N�/rl r r r3 )�find�rfind)rh �ir! r! r" rn � s
rn c C sL t | �}x*dD ]"}| j||�}|dkrt||�}qW | ||� | |d � fS )Nz/?#r )�lenrv �min)rh �start�delim�cZwdelimr! r! r" � _splitnetloc� s
r~ c C s� | st dd� | D �� r d S dd l}| jdd�}|jdd�}|jdd�}|jdd�}|jd |�}||krnd S x(d
D ] }||krttd | d d
��qtW d S )Nc s s | ]}t |�d kV qdS )� N)�ord)r- r} r! r! r" r/ � s z _checknetloc.<locals>.<genexpr>r rS r rT rf �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�any� unicodedata�replace� normalizerO )rU r� �nZnetloc2r} r! r! r" � _checknetloc� s
r� c C s xt D ]}| j|d�} qW | S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )rh �br! r! r" � _remove_unsafe_bytes_from_url� s
r� c C sB | j d�r tjd| �s>td��n tj| �}t|tj�r>td��d S )N�vz\Av[a-fA-F0-9]+\..+\Zz IPvFuture address is invalidz%An IPv4 address cannot be in brackets)�
startswith�re�matchrO � ipaddressZ
ip_addressr4 Z IPv4Address)rK Zipr! r! r" �_check_bracketed_host� s
r� c C s� t | |�\} }}t| �} t|�}| jt�} |jt�}t|�}| ||t| �t|�f}tj|d �}|rj||�S t t�t
kr|t � d } }}| j d�} | dk�r�| d | � dk�r~| d | � j
� }| | d d � } | d d� dk�r t| d�\}} d|ko�d |k�sd |k�r d|k�r td
��|�r<d | k�r<| jd d�\} }d | k�rV| jd d�\} }t|� t||| ||�}
|
t|< ||
�S xd| d | � D ]} | tk�r�P �q�W | | d d � } | �s�td
d� | D ���r�| d | � j
� | }} | d d� dk�rht| d�\}} d|k�rd |k�s,d |k�r4d|k�r4td
��d|k�rhd |k�rh|jd�d jd �d }
t|
� |�r�d | k�r�| jd d�\} }d | k�r�| jd d�\} }t|� t||| ||�}
|
t|< ||
�S )Nr rT r r r3 � z//r[ r\ zInvalid IPv6 URLrf r� c s s | ]}|d kV qdS )�
0123456789Nr! )r- r} r! r! r" r/ � s zurlsplit.<locals>.<genexpr>)r8 r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getry �MAX_CACHE_SIZEr# rv rJ r~ rO �splitr� r � scheme_charsr� rI r� )rh ro rp rq �key�cachedrU rr rg rx r� r} �restZbracketed_hostr! r! r" r � sj
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )Nz%s;%s)r8 r )�
componentsro rU rh rs rr rg rq r! r! r" r � s c C s� t | � \}}}}}}|s4|r`|tkr`|d d� dkr`|rP|d d� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S ) Nr� z//r3 ru r rT r� rf )r8 � uses_netloc)r� ro rU rh rr rg rq r! r! r" r s c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | r�|
r�|} |}
|s�|}|t|
| | |
||f��S |jd�}|d dkr�|d= | d d� dk� r�| jd�}n(|| jd� }td |dd� �|dd �< g }xX|D ]P}|dk�rdy |j� W n tk
�r` Y nX n|dk�rt�q0n
|j |� �q0W |d
d k�r�|j d� |t|
| dj
|��p�d|
||f��S ) Nr ru r3 �..�.���r� r� r� r� )r� r� ) r8 r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baserh rp rq ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentro rU �pathrs rr rg Z
base_partsZsegmentsZ
resolved_pathZsegr! r! r" r sT
c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )Nrf r )r8 r r r ) rh rq �sr� �p�a�qZfragZdefragr! r! r" r _ s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| jd�} | j d�}t|�dkr<| S |d g}|j}td krbdd� tD �axb|dd � D ]R}y(|t|d d� � ||dd � � W qp tk
r� |d� ||� Y qpX qpW dj |�S ) N� zutf-8rG r3 r c S s4 i | ],}t D ]"}tt|| d �g�|| j� �q qS )� )�_hexdig�bytesrN r( )r- r� r� r! r! r" �
<dictcomp>� s z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r4 r5 r( ry r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr! r! r" r r s*
z([ -]+)�utf-8r� c C s� d| kr| j | S |d kr d}|d kr*d}tj | �}|d g}|j}x@tdt|�d�D ],}|t|| �j||�� |||d � qVW dj|�S )NrF zutf-8r� r r3 r� r )r� �_asciirer� �rangery r r, r� )r� r) r* r� r� r� rx r! r! r" r � s
Fc C sR i }t | ||||||d�}x2|D ]*\} }
| |kr@|| j|
� q |
g|| < q W |S )N)r) r* �max_num_fieldsrL )r
r� ) �qs�keep_blank_values�strict_parsingr) r* r� rL Z
parsed_result�pairs�name�valuer! r! r" r � s c @ s e Zd ZdS )� _QueryStringSeparatorWarningN)r< r= r> r! r! r! r" r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |jd�}| s6t|ttf� rF|d k rFtd��t� }|d k�rVt}d} |d krvtj j
| �}d}
|d kr�y t t �} W n t
k
r� Y nJX | �: dd l} | jd d&d�}
|
j| � |
j
d| d d �}|aW d Q R X t }
|d k�r d
| k�rdd lm} |d,tdd� d}n:|dk�r,|}n*t|�dk�rVt| � d|
� d�d d ��|d k �r�||k�r�d| jd� | jd
� }nd| j|� }||k �r�td ��||k�r�d d � | jd�D �}nd d � | j|�D �}g }x�|D ]�}| �r�| �r��q�|jd d�}t|�dk�r>|�r(td!|f ��|�r�|jd"� n�q�t|d ��sR|�r�|d jd#d$�}t|||d%�}||�}|d jd#d$�}t|||d%�}||�}|j||f� �q�W |S )-Nr$ z*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler rf )Z
interpolationZcomment_prefixesr )Zfallbackrl )�warnz4The default separator of urllib.parse.parse_qsl and z1parse_qs was changed to '&' to avoid a web cache z"poisoning issue (CVE-2021-23336). z4By default, semicolons no longer act as query field z separators. z3See https://access.redhat.com/articles/5860431 for z
more details.r� )�
stacklevel�&Zlegacyr3 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|j d �D ]}|�qqS )rl )r� )r- �s1�s2r! r! r" �
<listcomp>< s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r! r! )r- r� r! r! r" r� > s �=zbad query field: %rr �+� )r) r* )rf zeThe default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for a The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.)r8 r4 r� r, r5 rO �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� ry �countr� r� r� r )r� r� r� r) r* r� rL rq Z_legacyZ envvar_nameZ
config_sourcer r� �configr� �
num_fieldsr� �rZ
name_valueZnvr� r� r! r! r" r
� s�
c C s | j dd�} t| ||�S )Nr� r� )r� r )r� r) r* r! r! r" r V s sA ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-c @ s$ e Zd Zdd� Zdd� Zdd� ZdS )�Quoterc C s t j|�| _d S )N)� _ALWAYS_SAFE�union�safe)r; r� r! r! r" �__init__n s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__r< �dict)r; r! r! r" �__repr__r s zQuoter.__repr__c C s( || j krt|�ndj|�}|| |< |S )Nz%{:02X})r� �chr�format)r; r� r� r! r! r" � __missing__v s zQuoter.__missing__N)r< r= r> r� r� r� r! r! r! r" r� f s r� ru c C sb t | t�r8| s| S |d kr d}|d kr*d}| j||�} n |d k rHtd��|d k rXtd��t| |�S )Nzutf-8r% z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r4 r5 r( r6 r
)r� r� r) r* r! r! r" r | s
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | jdd�S )Nr� � r� )r4 r5 r� r r� )r� r� r) r* Zspacer! r! r" r � s
c s� t | ttf�std��| s dS t |t�r6|jdd�}ntdd� |D ��}| jt| �s^| j� S y t | � W n& t
k
r� t |�j t |< � Y nX dj
� fdd�| D ��S )Nz!quote_from_bytes() expected bytesr r$ �ignorec S s g | ]}|d k r|�qS )� r! )r- r} r! r! r" r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r! r! )r- �char)�quoterr! r" r� � s )r4 r� � bytearrayr6 r5 r( �rstrip�_ALWAYS_SAFE_BYTESr, r r� r� � __getitem__r� )Zbsr� r! )r� r" r
� s
c C s t | d�r| j� } nRy t| �r2t| d t� r2t�W n0 tk
rd tj� \}}}td�j|��Y nX g } |s�xr| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | j |
d | � qtW �n,�x(| D �] \}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rL|| |�} | j |
d | � q�t| t
��rz|| |||�} | j |
d | � q�y t| �} W n: tk
�r� |t
| �|||�} | j |
d | � Y q�X xJ| D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| j |
d |
� �q�W q�W dj | �S )N�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� ry r4 r0 r6 �sys�exc_info�with_tracebackr� r5 r� r� )rr Zdoseqr� r) r* Z quote_viaZtyZva�tb�l�kr� r. Zeltr! r! r" r � sP
c C sJ t | t�rFy| jd�j� } W n( tk
rD tdt| � d ��Y nX | S )N�ASCIIzURL z contains non-ASCII characters)r4 r5 r( r, � UnicodeError�repr)rh r! r! r" �to_bytes s
r� c C s` t | �j� } | d d� dkr<| dd � dkr<| dd� j� } | d d� dkr\| dd � j� } | S )Nr3 �<�>� zURL:r� r� )r5 r� )rh r! r! r" �unwrap, s r c C sD t d krtjdtj�a t j| �}|r<|j� \}}|j� |fS d | fS )Nz
([^/:]+):(.*))� _typeprogr� �compile�DOTALLr� �groupsrJ )rh r� ro �datar! r! r" � splittype5 s
r c C sX t d krtjdtj�a t j| �}|rP|j� \}}|rH|d dkrHd| }||fS d | fS )Nz//([^/#?]*)(.*)r ru )� _hostprogr� r r r� r )rh r� Z host_portr� r! r! r" � splithostB s
r c C s | j d�\}}} |r|nd | fS )NrS )rV )�host�userr| r! r! r" � splituserP s r c C s | j d�\} }}| |r|nd fS )NrT )rI )r
r| Zpasswdr! r! r" � splitpasswdU s r c C sD t d krtjdtj�a t j| �}|r<|j� \} }|r<| |fS | d fS )Nz(.*):([0-9]*)$)� _portprogr� r r r� r )r r� rP r! r! r" � splitport\ s
r r3 c C sT | j d�\} }}|s|} n2|rLy t|�}W n tk
rB d }Y nX | |fS | |fS )NrT )rV rN rO )r Zdefportr| rP Znportr! r! r" �
splitnporti s
r c C s$ | j d�\}}}|r ||fS | d fS )Nr� )rV )rh r� r| rr r! r! r" �
splitqueryy s r c C s$ | j d�\}}}|r ||fS | d fS )Nrf )rV )rh r� r| �tagr! r! r" �splittag� s r c C s | j d�}|d |dd � fS )Nrl r r3 )r� )rh Zwordsr! r! r" � splitattr� s
r c C s | j d�\} }}| |r|nd fS )Nr� )rI )�attrr| r� r! r! r" �
splitvalue� s r )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )ru NN)r NN)ru r� )r� )dr� r� r� � collectionsr� �__all__r� r� rm Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r# Z_implicit_encodingZ_implicit_errorsr' r+ r2 r8 r� r9 r@ rB rR r` re Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBase�__doc__rh rg ro rU r� rr rs Z
ResultBaser r r r r r rk r rn r~ r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r � defaultdictr� r r r
r r� r r r r r r r r
r r r r r r r! r! r! r" �<module>" s
!
C
E
&
y
,
O
PK (�Z�甖2� 2� ( __pycache__/request.cpython-36.opt-2.pycnu �[��� 3
�\dh~� � ) @ s� d dl Z d dlZd dlZd dlZd dlZd dlZd dlZd dlZd dl Z d dl
Z
d dl Z d dl Z d dl
Z
d dlZd dlZd dlZd dlZd dlmZmZmZ d dlmZmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( d dl)m*Z*m+Z+ y d dl,Z,W n e-k
�r" dZ.Y nX dZ.ddd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'g!Z/d(e j0dd)� Z1da2de
j3fddddd*�d+d �Z4d,d � Z5g Z6d}d-d$�Z7d.d%� Z8e j9d/e j:�Z;d0d1� Z<G d2d� d�Z=G d3d� d�Z>d4d � Z?G d5d � d �Z@G d6d � d e@�ZAG d7d
� d
e@�ZBG d8d � d e@�ZCd9d:� ZDG d;d
� d
e@�ZEG d<d� d�ZFG d=d� deF�ZGG d>d� deG�ZHG d?d� d�ZIG d@d� deIe@�ZJG dAd� deIe@�ZKejLZMG dBd� d�ZNG dCd� de@eN�ZOG dDd� de@eN�ZPG dEdF� dFe@�ZQG dGd� deQ�ZReSejTdH��r.G dIdJ� dJeQ�ZUe/jVdJ� G dKd � d e@�ZWG dLd � d e@�ZXdMdN� ZYdOdP� ZZG dQd� de@�Z[dRdS� Z\G dTd� de@�Z]G dUd� de]�Z^G dVd� de@�Z_dWZ`ejadXk�r�d dYlbmcZcmdZd ndZd"� Zcd[d!� Zdi ZeG d\d&� d&�ZfG d]d'� d'ef�Zgdahd^d_� Zidajd`da� Zkdaldbdc� Zmdanddde� ZoG dfdg� dg�Zpdhdi� Zqd~djdk�Zrdldm� Zse jtdnk�r�d dolumvZvmwZw dpdq� Zxdrds� Zydtdu� Zzdvd#� Z{n6ejadXk�r�dwdx� Z|dyd#� Z{dzd{� Z}d|du� ZzneqZ{erZzdS )� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote� splittype� splithost� splitport� splituser� splitpasswd� splitattr�
splitquery�
splitvalue�splittag�to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfdd l }|jdtd� |d k r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt d kr�t
� a } nt } | j | ||�S )Nr zJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.6/urllib/request.pyr0 � s* <
c C s | a d S )N)rF )rK rL rL rM r1 � s c C s4 t | �\}}tjt| |����}|j� }|dkrD| rDtjj|�|fS |rTt|d�}n t j
dd�}|j }t j
|� |�� ||f} d }
d
} d} d}
d |kr�t|d
�} |r�||
|
| � xB|j|
�}|s�P | t|�7 } |j|� |
d7 }
|r�||
|
| � q�W W d Q R X W d Q R X | dk�r0| | k �r0td | | f | ��| S )N�file�wbF)�deletei � � r zcontent-lengthzContent-Lengthz1retrieval incomplete: got only %i out of %i bytesi ���)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typerX �fp�headers�tfp�result�bs�sizer_ �blocknum�blockrL rL rM r6 � sD
$c C sH x0t D ](} ytj| � W q tk
r, Y qX qW t d d �= trDd ad S )N)r\ rW �unlink�OSErrorrF )Z temp_filerL rL rM r7 % s
z:\d+$c C s< | j }t|�d }|dkr&| jdd�}tjd|d�}|j� S )NrR � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host4 s rw c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sp || _ i | _i | _d | _|| _d | _x |j� D ]\}}| j||� q.W |d krVt| �}|| _ || _
|rl|| _ d S )N) rp re �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerrw �origin_req_host� unverifiable�method) �selfrH rI re r} r~ r �key�valuerL rL rM �__init__F s zRequest.__init__c C s | j rdj| j| j �S | jS )Nz{}#{})�fragment�format� _full_url)r� rL rL rM rp X s zRequest.full_urlc C s( t |�| _t| j�\| _| _| j� d S )N)r r� r r� �_parse)r� rH rL rL rM rp ^ s
c C s d | _ d | _d| _d S )Nrn )r� r� �selector)r� rL rL rM rp e s c C s | j S )N)ry )r� rL rL rM rI k s z Request.datac C s( || j kr$|| _ | jd�r$| jd� d S )NzContent-length)ry �
has_header�
remove_header)r� rI rL rL rM rI o s
c C s
d | _ d S )N)rI )r� rL rL rM rI y s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rp r rv r� r
)r� �restrL rL rM r� } s
zRequest._parsec C s | j d k rdnd}t| d|�S )N�POST�GETr )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S )N)rp )r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s4 | j dkr | j r | j| _n|| _ | j| _|| _d S )N�https)r� rz rv rp r� )r� rv r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS )N)r� rp )r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |j� < d S )N)re �
capitalize)r� r� �valrL rL rM r| � s zRequest.add_headerc C s || j |j� < d S )N)rx r� )r� r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS )N)re rx )r� � header_namerL rL rM r� � s
zRequest.has_headerc C s | j j|| jj||��S )N)re �getrx )r� r� �defaultrL rL rM rq � s zRequest.get_headerc C s | j j|d � | jj|d � d S )N)re �poprx )r� r� rL rL rM r� � s zRequest.remove_headerc C s" | j j� }|j| j� t|j� �S )N)rx �copy�updatere �listr{ )r� �hdrsrL rL rM � header_items� s
zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrp �setter�deleterrI r� r� r� r� r� r| r� r� rq r� r� rL rL rL rM r D s(
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )NzPython-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sZ t |d�stdt|� ��d}�xt|�D �]}|dkr:q*|jd�}|d |� }||d d � }|jd �r�|jd�| d }||d d � }y t|�}W n tk
r� Y nX | jj |i �} | | j|< n>|d
kr�|}| j
} n*|d kr�|}| j } n|d kr*|}| j } nq*| j
|g �}
|
�r&tj|
|� n
|
j|� d
}q*W |�rVtj| j|� |j| � d S )N�
add_parentz%expected BaseHandler instance, got %rF�redirect_request�do_open�
proxy_open�_rR �errorrG �responseru T)r� r� r� )�hasattr� TypeErrorr� �dir�find�
startswithr^ rB r� r� r� r� r� �
setdefault�bisectZinsortr] r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sJ
zOpenerDirector.add_handlerc C s d S )NrL )r� rL rL rM �close� s zOpenerDirector.closec G s< |j |f �}x*|D ]"}t||�}||� }|d k r|S qW d S )N)r� r� ) r� �chainr� � meth_name�argsr� r� �funcrg rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }x(| jj|g �D ]}t||�}||�}qLW | j ||�} |d }x*| j
j|g �D ]}t||�}||| �} q�W | S )NZ_requestZ _response) �
isinstance�strr rI rJ r� r� r� r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s"
zOpenerDirector.openc C sP | j | jdd|�}|r|S |j}| j | j||d |�}|r>|S | j | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rg r� rL rL rM r� s
zOpenerDirector._openc G s~ |d
kr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S ) N�httpr� r: z
http_error_%srR Z_errorr r� �http_error_default)r� r� )r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrg rL rL rM r� ' s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|j
t� t� }xN|D ]F}x@| D ]8}t|t�rlt||�r�|j|� qHt||�rH|j|� qHW q>W x|D ]}|j|� q�W x|D ]}|j|� � q�W x&| D ] }t|t�r�|� }|j|� q�W |S )N�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientr] rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 @ s0
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r i� c C s
|| _ d S )N)�parent)r� r� rL rL rM r� g s zBaseHandler.add_parentc C s d S )NrL )r� rL rL rM r� j s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__n s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r d s c @ s e Zd ZdZdd� ZeZdS )r/ i� c C sJ |j |j|j� }}}d| ko*dk n sF| jjd|||||�}|S )N�� i, r� )�code�msgrV r� r� )r� ru r� r� r� r� rL rL rM �
http_response{ s
z HTTPErrorProcessor.http_responseN)r� r� r� r� r� �https_responserL rL rL rM r/ w s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S )N)r rp )r� r� rd r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c sx |j � }|dkr|dkp&|dko&|dks:t|j||||��|jdd �}d� t� fd d
�|jj� D ��}t|||jdd�S )N�- �. �/ �3 r� �HEADr� � z%20�content-length� content-typec 3 s& | ] \}}|j � � kr||fV qd S )N)rt )�.0�k�v)�CONTENT_HEADERSrL rM � <genexpr>� s z7HTTPRedirectHandler.redirect_request.<locals>.<genexpr>T)re r} r~ )r� r� r� r� )r� r� )r� r� r� )r� r� ) r� r rp �replacer� re r{ r r} ) r� r� rd r� r� re �newurl�mZ
newheadersrL )r� rM r� � s
z$HTTPRedirectHandler.redirect_requestc
C sN d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|j rp|jrpt|�}d|d < t|�}t|d
tj d �}t
|j |�}| j ||||||�}|d kr�d S t
|d ��r|j } |_| j|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| j|d
�d | |< |j� |j� | jj||jd�S )N�location�urir� r� �ftprn z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rR )rJ )r� r� r� rn )r �schemer rX Znetlocr� r r �stringZ punctuationr rp r� r� r r� � max_repeatsr` �max_redirections�inf_msgr_ r� r� rG rJ )
r� r� rd r� r� re r� �urlparts�newZvisitedrL rL rM �http_error_302� s@
z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r �http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c C s� t | �\}}|jd�s d }| }n:|jd�s6td| ��|jdd�}|dkrNd }|d|� }t|�\}}|d k r|t|�\}}nd }}||||fS )Nr� z//z proxy URL with no authority: %rr: rR rS )r r� rB r� r r ) �proxyr Zr_scheme� authority�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s
r c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C sL |d krt � }|| _x2|j� D ]&\}}t| d| ||| jfdd�� q W d S )Nz%s_openc S s || ||�S )NrL )�rr
r� r� rL rL rM �<lambda>% s z'ProxyHandler.__init__.<locals>.<lambda>)r5 �proxiesr{ �setattrr� )r� r r� rH rL rL rM r� s
zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } tj| j� �jd�}
|j dd|
� t|�}|j
||� ||ks�|dkr�d S | j j ||j
d�S d S )Nz%s:%s�asciizProxy-authorizationzBasic r� )rJ )r� r rv � proxy_bypassr
�base64� b64encode�encode�decoder| r� r� rG rJ ) r� r� r
r� Z orig_typeZ
proxy_typer r r Z user_passZcredsrL rL rM r� ( s zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S )N)�passwd)r� rL rL rM r� F s zHTTPPasswordMgr.__init__c s` t |t�r|g}|�jkr$i �j|< x6dD ].� t� �fdd�|D ��}||f�j| |< q*W d S )NTFc s g | ]}�j |� ��qS rL )�
reduce_uri)r� �u)� default_portr� rL rM �
<listcomp>Q s z0HTTPPasswordMgr.add_password.<locals>.<listcomp>)TF)r� r� r �tuple)r� �realmr� r r � reduced_urirL )r" r� rM � add_passwordI s
z HTTPPasswordMgr.add_passwordc C s` | j j|i �}xLdD ]D}| j||�}x2|j� D ]&\}}x |D ]}| j||�r<|S q<W q.W qW dS )NTF)TF)NN)r r� r r{ � is_suburi) r� r% �authuriZdomainsr" �reduced_authuriZurisZauthinfor� rL rL rM �find_user_passwordT s
z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d }|}d}t|�\}}|r~|d kr~|d k r~ddd�j|�} | d k r~d|| f }||fS ) NrR r r: r� �P i� )r� r� z%s:%d)r r
r� )
r� r� r" �partsr r rX rv �portZdportrL rL rM r ^ s zHTTPPasswordMgr.reduce_uric C sR ||kr dS |d |d kr dS t j|d |d f�}t|�t|d �krNdS dS )NTr FrR )� posixpath� commonprefixr` )r� �base�test�commonrL rL rM r( u s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r' r+ r r( rL rL rL rM r D s
c @ s e Zd Zdd� ZdS )r! c C s0 t j| ||�\}}|d k r"||fS t j| d |�S )N)r r+ )r� r% r) r r rL rL rM r+ � s
z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� r+ rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S )N)�
authenticated�superr� )r� r� �kwargs)� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | j ||� |d k r&t� jd |||� t� j||||� d S )N)�update_authenticatedr5 r' )r� r% r� r r �is_authenticated)r7 rL rM r' � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C sF t |t�r|g}x0dD ](}x"|D ]}| j||�}|| j|< q W qW d S )NTF)TF)r� r� r r4 )r� r� r9 r" r! r& rL rL rM r8 � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD x>dD ]6}| j ||�}x$| jD ]}| j||�r | j| S q W qW d S )NTF)TF)r r4 r( )r� r) r" r* r� rL rL rM r9 � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r' r8 r9 �
__classcell__rL rL )r7 rM r" � s
c @ sT e Zd Zejdej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S )N)r r r' )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c st d}xFt jj|�D ]6}|j� \}}}|d kr:tjdtd� ||fV d}qW |sp|rb|j� d }nd}|d fV d S )
NF�"�'z Basic Auth Realm was unquoted� Tr rn )r; r< )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r% rL rL rM � _parse_realm� s
z%AbstractBasicAuthHandler._parse_realmc C s~ |j |�}|sd S d }xL|D ]D}x>| j|�D ]0\}}|j� dkrF|}q,|d k r,| j|||�S q,W q W |d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allrD rt �retry_http_basic_authrB ) r� �authreqrv r� re Z unsupportedrC r r% rL rL rM �http_error_auth_reqed� s
z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j j||�\}}|d k rtd||f }dtj|j� �jd� }|j| jd �|krTd S |j| j|� | j j
||j d�S d S d S )Nz%s:%szBasic r )rJ ) r r+ r r r r rq � auth_headerr� r� rG rJ )r� rv r� r% r �pw�raw�authrL rL rM rF � s z.AbstractBasicAuthHandler.retry_http_basic_authc C sx t | jd� s | jj|j� r"|S |jd�st| jjd |j�\}}dj||�j� }tj |�j
� }|j ddj|j � �� |S )Nr9 �
Authorizationz{0}:{1}zBasic {})
r� r r9 rp r� r+ r� r r Zstandard_b64encoder r� �strip)r� r� r r Z credentialsZauth_strrL rL rM � http_request s
z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j ko dk n r8| jj|jd� n| jj|jd� |S )Nr9 r� i, TF)r� r r� r8 rp )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�Ir> r� rD rH rF rO r� �
https_requestr� rL rL rL rM r# � s
c @ s e Zd ZdZdd� ZdS )r$ rM c C s |j }| jd|||�}|S )Nzwww-authenticate)rp rH )r� r� rd r� r� re rH r� rL rL rM �http_error_401 s
z#HTTPBasicAuthHandler.http_error_401N)r� r� r� rI rT rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% zProxy-authorizationc C s |j }| jd|||�}|S )Nzproxy-authenticate)rv rH )r� r� rd r� r� re r r� rL rL rM �http_error_407+ s
z$ProxyBasicAuthHandler.http_error_407N)r� r� r� rI rU rL rL rL rM r% ' s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S )Nr )r r r' �retried� nonce_count�
last_nonce)r� r rL rL rM r� E s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S )Nr )rV )r� rL rL rM �reset_retry_countN s z+AbstractDigestAuthHandler.reset_retry_countc C s| |j |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|j� d }|j� dkr`| j||�S |j� dkrxtd| ��d S ) N� i� zdigest auth failedrR r ZdigestrE zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rV r rp rB rt �retry_http_digest_authrB )r� rI rv r� re rG r rL rL rM rH Q s
z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |j dd�\}}ttd t|���}| j||�}|rvd| }|jj| jd �|krRd S |j| j|� | j j
||j d�}|S d S )Nr� rR z Digest %s)rJ ) rB �parse_keqv_list�filter�parse_http_list�get_authorizationre r� rI r� r� rG rJ )r� r� rL �tokenZ challenge�chalZauth_valZresprL rL rM r[ e s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |tj� f }|jd�td� }tj|�j� }|d d� S )Nz %s:%s:%s:r rQ � )rW �timeZctimer � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceq s z$AbstractDigestAuthHandler.get_cnoncec C s� y6|d }|d }|j d�}|j dd�}|j dd �}W n tk
rJ d S X | j|�\}} |d krfd S | jj||j�\}
} |
d kr�d S |jd k r�| j|j|�} nd } d|
|| f }
d|j� |j f }|d k�r.|| j
kr�| j d
7 _ n d
| _ || _
d | j }| j |�}d ||||||�f }| ||
�|�}n2|d k�rT| ||
�d|||�f �}n t
d
| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr% rh �qop� algorithm�MD5�opaquez%s:%s:%sz%s:%srL rR z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr r+ rp rI �get_entity_digestr� r� rX rW rl r )r� r� ra r% rh rm rn rp �H�KDr rJ ZentdigZA1ZA2ZncvalueZcnonceZnoncebitZrespdigr1 rL rL rM r_ | sV
z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nro c S s t j| jd��j� S )Nr )re Zmd5r rg )�xrL rL rM r � s z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t j| jd��j� S )Nr )re rf r rg )rv rL rL rM r � s z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nz%s:%srL )ri �d)rt rL rM r � s )rB )r� rn ru rL )rt rM rr � s
z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S )NrL )r� rI ra rL rL rM rs � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� rY rH r[ rl r_ rr rs rL rL rL rM r& : s
<
c @ s e Zd ZdZdZdd� ZdS )r' rM i� c C s* t |j�d }| jd|||�}| j� |S )NrR zwww-authenticate)r rp rH rY )r� r� rd r� r� re rv �retryrL rL rM rT � s
z$HTTPDigestAuthHandler.http_error_401N)r� r� r� rI r� rT rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( zProxy-Authorizationi� c C s" |j }| jd|||�}| j� |S )Nzproxy-authenticate)rv rH rY )r� r� rd r� r� re rv rx rL rL rM rU � s
z%ProxyDigestAuthHandler.http_error_407N)r� r� r� rI r� rU rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S )N)� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S )N)rz )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jjj|j|j� �S )N)r� r� �HTTPConnection�_get_content_lengthrI r� )r� ru rL rL rM r � s z'AbstractHTTPHandler._get_content_lengthc C s
|j }|std��|jd k r�|j}t|t�r8d}t|��|jd�sN|jdd� |jd� r�|jd� r�| j|�}|d k r�|jdt|�� n |jdd� |}|j � r�t
|j �\}}t |�\}} |jd�s�|jd|� x2| j
jD ]&\}
} |
j� }
|j|
�s�|j|
| � q�W |S ) Nz
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-typez!application/x-www-form-urlencodedzContent-lengthzTransfer-encodingZchunkedro )rv r rI r� r� r� r� r� r r� r r� r r� r� r� ) r� ru rv rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr[ r� rL rL rM � do_request_� s>
z AbstractHTTPHandler.do_request_c
s\ |j }|std��||fd|ji|��}|j| j� t|j�� � jt� fdd�|jj � D ��� d� d< tdd� � j � D ��� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � y`y&|j |j
� |j|j� |jd
�d � W n, tk
�r
} zt|��W Y d d }~X nX |j� } W n |j� � Y nX |j�rF|jj� d |_|j� | _| j| _| S ) Nz
no host givenrJ c 3 s" | ]\}}|� kr||fV qd S )NrL )r� r� r� )re rL rM r� ) s z.AbstractHTTPHandler.do_open.<locals>.<genexpr>r� �
Connectionc s s | ]\}}|j � |fV qd S )N)�title)r� r[ r� rL rL rM r� 6 s zProxy-Authorization)re zTransfer-encoding)Zencode_chunked)rv r rJ Zset_debuglevelrz r� rx r� re r{ rz Z
set_tunnelru r� r� rI r� rm � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrv r� Ztunnel_headersZproxy_auth_hdr�errr rL )re rM r� s@
"
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r} r r� r� rL rL rL rM ry � s
&ry c @ s e Zd Zdd� ZejZdS )r) c C s | j tjj|�S )N)r� r� r� r~ )r� r� rL rL rM � http_open` s zHTTPHandler.http_openN)r� r� r� r� ry r� rO rL rL rL rM r) ^ s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t j| |� || _|| _d S )N)ry r� �_context�_check_hostname)r� r{ r> �check_hostnamerL rL rM r� i s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� )r� r� rL rL rM �
https_openn s zHTTPSHandler.https_open)r NN)r� r� r� r� r� ry r� rS rL rL rL rM rE g s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|jj� }|| _d S )Nr )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� w s
z HTTPCookieProcessor.__init__c C s | j j|� |S )N)r� Zadd_cookie_header)r� ru rL rL rM rO } s z HTTPCookieProcessor.http_requestc C s | j j||� |S )N)r� Zextract_cookies)r� ru r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� rO r� rS r� rL rL rL rM r v s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sR i }xH| D ]@}|j dd�\}}|d dkrB|d dkrB|dd� }|||< q
W |S )N�=rR r r; rS rS )rB )�lZparsedZeltr� r� rL rL rM r\ � s
r\ c C s� g }d}d }}xt| D ]l}|r,||7 }d}q|rV|dkr@d}qn |dkrLd}||7 }q|dkrn|j |� d}q|dkrzd}||7 }qW |r�|j |� dd� |D �S ) Nrn F�\Tr; �,c S s g | ] }|j � �qS rL )rN )r� �partrL rL rM r# � s z#parse_http_list.<locals>.<listcomp>)r] )ri �resr� �escaper ZcurrL rL rM r^ � s4
r^ c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| j� krXtd��n
| j|�S d S )Nr: z//r= r� � localhostz-file:// scheme is supported only on localhost)r� rv � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &
zFileHandler.file_openNc C s` t jd krZy*ttjd�d tjtj� �d �t _W n$ tjk
rX tjd�ft _Y nX t jS )Nr� r: )r* �namesr$ r� �gethostbyname_ex� gethostname�gaierror�
gethostbyname)r� rL rL rM r� � s
zFileHandler.get_namesc C s dd l }dd l}|j}|j}t|�}y�tj|�}|j}|jj |j
dd�} |j |�d }
|j d|
pbd|| f �} |r~t
|�\}} | s�| r�t|�| j� kr�|r�d| | }
nd| }
tt|d�| |
�S W n* tk
r� } zt|��W Y d d }~X nX td��d S ) Nr T)�usegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
z
text/plainzfile://�rbzfile not on local host)� email.utils� mimetypesrv r� r4 rW �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rm r )r� r� �emailr� rv rb Z localfile�statsri �modified�mtypere r. Zorigurl�exprL rL rM r� � s0
zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s& y
t j| �S t jk
r d S X d S )N)r� r� r� )rv rL rL rM r� � s
r� c @ s e Zd Zdd� Zdd� ZdS )r+ c C s. dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}yt
j |�}W n* t k
r� } zt|��W Y d d }~X nX t
|j�\} }
| jd�} ttt | ��} | d d� | d } } | �r| d �r| dd � } y�| j||||| |j�}
| �r8d�p:d}x:|
D ]2}t|�\}}|j� dk�rB|dk�rB|j� }�qBW |
j| |�\}}d}|j|j�d }|�r�|d
| 7 }|d k �r�|dk�r�|d| 7 }tj|�}t |||j�S |j k
�r( } z$td| �}|j t j � d ��W Y d d }~X nX d S )Nr zftp error: no host givenrn r� rR rR �Dr� �a�Ar� rw zContent-type: %s
zContent-length: %d
z
ftp error: %rr: rS rS )r� r� r� rR rw r� )!�ftplibr� rv r r
�FTP_PORTr^ r r r
r� r� rm r r� rB r� �map� connect_ftprJ r rt �upper�retrfiler� rp r� r� r �
all_errors�with_traceback�sys�exc_info)r� r� r� r� rv r. r r r� rX �attrs�dirsrN �fwr� �attrr� rd �retrlenre r� r� �excrL rL rM �ftp_open� s\
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r rv r. r� rJ rL rL rM r� 1 s zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ � s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< rb )�cacherJ �soonest�delay� max_conns)r� rL rL rM r� 8 s
zCacheFTPHandler.__init__c C s
|| _ d S )N)r� )r� �trL rL rM �
setTimeout? s zCacheFTPHandler.setTimeoutc C s
|| _ d S )N)r� )r� r� rL rL rM � setMaxConnsB s zCacheFTPHandler.setMaxConnsc C sr |||dj |�|f}|| jkr4tj� | j | j|< n,t||||||�| j|< tj� | j | j|< | j� | j| S )Nr� )�joinr� rc r� rJ r� � check_cache)r� r r rv r. r� rJ r� rL rL rM r� E s
zCacheFTPHandler.connect_ftpc C s� t j � }| j|krTx@t| jj� �D ].\}}||k r"| j| j� | j|= | j|= q"W tt| jj� ��| _t | j�| j
kr�x6t| jj� �D ]$\}}|| jkr�| j|= | j|= P q�W tt| jj� ��| _d S )N) rc r� r� rJ r{ r� r� �min�valuesr` r� )r� r� r� r� rL rL rM r� P s
zCacheFTPHandler.check_cachec C s4 x| j j� D ] }|j� q W | j j� | jj� d S )N)r� r� r� �clearrJ )r� �connrL rL rM � clear_cached s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r� r� rL rL rL rM r, 5 s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|jdd�\}}|jdd�\}}t|�}|jd�rNtj|�}|d d� }|sVd}tjd|t|�f �}t t
j |�||�S ) N�:rR r� z;base64� ztext/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
i����) rp rB r �endswithr � decodebytesr� r� r` r �io�BytesIO)r� r� rH r rI Z mediatypere rL rL rM � data_openk s
zDataHandler.data_openN)r� r� r� r� rL rL rL rM r- j s r� �nt)r4 r3 c C s t | �S )N)r
)�pathnamerL rL rM r4 � s c C s t | �S )N)r )r� rL rL rM r3 � s c @ s� e Zd ZdZde Zd)dd�Zdd� Zdd� Zd d
� Z d d � Z
d*d
d�Z d+dd�Z d,dd�Z
d-dd�Zdd� Zd.dd�Zd/dd�Zdd � Zer�d d � Zd0d d �Zd!d"� Zd#d$� Zd%d&� Zd1d'd(�ZdS )2r8 NzPython-urllib/%sc K sz dd| j ji }tj|tdd� |d kr.t� }|| _|jd�| _|jd�| _ d| j
fd
g| _ g | _ t
j| _d | _t| _d S ) NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classr= )�
stacklevel�key_file� cert_filez
User-Agent�Accept�*/*)r� r� )r7 r� r? r@ rA r5 r r� r� r� �versionr� �_URLopener__tempfilesrW rl �_URLopener__unlink� tempcache�ftpcache)r� r Zx509r� rL rL rM r� � s zURLopener.__init__c C s | j � d S )N)r� )r� rL rL rM �__del__� s zURLopener.__del__c C s | j � d S )N)�cleanup)r� rL rL rM r� � s zURLopener.closec C sZ | j rFx2| j D ](}y| j|� W q tk
r4 Y qX qW | j d d �= | jrV| jj� d S )N)r� r� rm r� r� )r� rN rL rL rM r� � s
zURLopener.cleanupc G s | j j|� d S )N)r� r] )r� r� rL rL rM � addheader� s zURLopener.addheaderc C sn t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd }d| } || _ | j
dd�} t | | � s�| dkr�|r�| j |||�S | j
||�S y,|d k�r t| | �|�S t| | �||�S W nV ttfk
�r. � Y n< tk
�rh }
z td |
�jtj� d
��W Y d d }
~
X nX d S ) Nz%/:=&?~#+!$,;'@()*[]|)r r� rN Zopen_�-r� r� z socket errorr: )r r r r� rG r r r r r� r� r� �open_unknown_proxy� open_unknownr� r r rm r� r� r� )r� r� rI rb re rd �urltyperH r
� proxyhostrv r� r[ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��d S )Nz url errorzunknown url type)r rm )r� r� rI r� rH rL rL rM r� s zURLopener.open_unknownc C s t |�\}}tdd| |��d S )Nz url errorzinvalid proxy for %s)r rm )r� r
r� rI r� rH rL rL rM r� s z URLopener.open_unknown_proxyc C s& t t|��}| jr&|| jkr&| j| S t|�\}}|d kr�| sH|dkr�y.| j|�}|j� }|j� tt|�d �|fS t k
r� } zW Y d d } ~ X nX | j
||�}�zH|j� }
|r�t
|d�} n|dd l } t|�\}
}t|p�d�\}
}t |p�d�\}}
t
|�p d�\}}
tjj|�d }| j|�\}}| jj|� tj|d�} z�||
f}| jd k �r^|| j|< d }d }d}d}d|
k�r�t|
d �}|�r�||||� xH|j|�}|�s�P |t|�7 }| j|� |d7 }|�r�||||� �q�W W d | j� X W d |j� X |dk�r"||k �r"td
||f |��|S )
NrN rR rO r rn i rQ zcontent-lengthzContent-Lengthz1retrieval incomplete: got only %i out of %i bytesi rS )r r r� r r� rV r� r4 r rm rG rZ r r rW rX �splitextZmkstempr� r] �fdopenr^ r_ r` ra r )r� rH rb rc rI r� Zurl1rd r� r� re rf rZ ZgarbagerX �suffix�fdrg rh ri r_ rj rk rL rL rM �retrieve sl
zURLopener.retrievec C s( d }d }t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d }| j� dkrvd }n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t j
|j � �j d�} nd } |�rt|�}t j
|j � �j d�} nd } ||�}
i }| �r*d| |d< | �r<d| |d< |�rJ||d < d
|d < x | j
D ]\}}|||< �qZW |d k �r�d |d
< |
jd|||� n|
jd||d� y |
j� }W n" tjjk
�r� td��Y nX d|j k�o�dk n �rt||jd| |j�S | j||j|j|j|j|�S d S )Nr� z %s://%s%sz
http errorz
no host givenr zBasic %szProxy-AuthorizationrM ro r� r� z!application/x-www-form-urlencodedz Content-Typer� r� )re z$http protocol error: bad status liner� i, zhttp:)r� r� r r r
r rt r rm r r r r r� ru r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrd r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrv r� Zrealhostr� r� Z
proxy_authrL Z http_connre rC r� r� rL rL rM �_open_generic_httpQ sr
z URLopener._open_generic_httpc C s | j tjj||�S )N)r� r� r� r~ )r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|d kr6||||||�} n|||||||�} | rP| S | j|||||�S )Nz
http_error_%d)r� r� r� )
r� rH rd �errcode�errmsgre rI r[ r rg rL rL rM r� � s
zURLopener.http_errorc C s |j � t||||d ��d S )N)r� r )r� rH rd r� r� re rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r� r� )r� r� r� r� r� )r� rv rL rL rM �_https_connection� s zURLopener._https_connectionc C s | j | j||�S )N)r� r� )r� rH rI rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|d d� dkrP|dd� dkrP|dd� j� dkrPtd��n
| j|�S d S ) NzEfile error: proxy support for file protocol currently not implementedr: z//r= r� � z
localhost/z-file:// scheme is supported only on localhost)r� r� r rt rB r� )r� rH rL rL rM � open_file� s
4
zURLopener.open_filec C s\ dd l }dd l}t|�\}}t|�}ytj|�}W n0 tk
rb } zt|j|j ��W Y d d }~X nX |j
} |j j |j
dd�}
|j|�d } |jd| p�d| |
f �} |s�|}
|d d� dkr�d| }
tt|d �| |
�S t|�\}}| o�tj|�t� ft� k�rP|}
|d d� dk�r d| }
n |d d
� d k�r>td | ��tt|d �| |
�S td
��d S )Nr T)r� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
z
text/plainrR r� zfile://r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 rW r� rm r �strerrorrb r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rv rN Z localnamer� �eri r� r� re Zurlfiler. rL rL rM r� � s:
zURLopener.open_local_filec C s� t |t�std��dd l}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd }t|�}t|ppd�}t|p|d�}t j
|�}|s�dd l }|j }nt
|�}t|�\}} t|�}|jd�}
|
d d� |
d }
} |
o�|
d � r�|
dd � }
|
�r|
d �rd|
d< |||dj|
�f} t| j�tk�rlx8t| j�D ]*}
|
| k�r>| j|
}| j|
= |j� �q>W y�| | jk�r�t|||||
�| j| < | �s�d}nd}x:| D ]2}t|�\}}|j� d k�r�|dk�r�|j� }�q�W | j| j| |�\}}|jd| �d }d}|�r|d| 7 }|d k �r:|dk�r:|d| 7 }t j |�}t ||d| �S t � k
�r� } z td| �j t!j"� d ��W Y d d }~X nX d S )NzCftp error: proxy support for ftp protocol currently not implementedr zftp error: no host givenrn r� rR r� rR r� r� r� r� rw zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: rS rS )r� r� r� rR rw r� )#r� r� r r� r r
r r r
r� r� r� r� r^ r rB r� r` r� � MAXFTPCACHEr� r� r� r rt r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rv rX r. r r r� r� r� rN r� r� r� r� r� r� rd r� r� re r� rL rL rM �open_ftp� sp
zURLopener.open_ftpc C s< t |t�std��y|jdd�\}}W n tk
rD tdd��Y nX |sNd}|jd�}|dkr�d ||d � kr�||d d � }|d |� }nd
}g }|jd tj d tj
tj� �� � |jd
| � |dkr�t j |j
d��jd�}nt|�}|jdt|� � |jd
� |j|� dj|�}tj|�}tj|�}t|||�S )NzEdata error: proxy support for data protocol currently not implementedr� rR z
data errorz bad data URLztext/plain;charset=US-ASCII�;r r� rn zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr r zlatin-1zContent-Length: %d�
)r� r� r rB rB rm �rfindr] rc ZstrftimeZgmtimer r� r r r
r` r� r� r� r� �StringIOr ) r� rH rI r� Zsemir� r� re �frL rL rM � open_data3 s6
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r� r� r� r� r� r� r� r� rG r� r� r� r� r� r� r� rC r� r� r� r� r r rL rL rL rM r8 � s,
$
B\
:c @ s� e Zd Zdd� Zdd� Zd"dd�Zdd � Zd#d
d �Zd$d d
�Zd%dd�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd �Zd,d d �Zd d!� ZdS )-r9 c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtries)r� r� r6 rL rL rM r� ` s zFancyURLopener.__init__c C s t ||d| |�S )Nzhttp:)r )r� rH rd r� r� re rL rL rM r� f s z!FancyURLopener.http_error_defaultNc
C sn | j d7 _ zR| jrJ| j | jkrJt| d�r4| j}n| j}|||dd|�S | j||||||�}|S d| _ X d S )NrR �http_error_500i� z)Internal Server Error: Redirect Recursionr )r r
r� r r� �redirect_internal) r� rH rd r� r� re rI r� rg rL rL rM r j s
z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |j � t| jd | |�}t|�}|jd krnt|||d| ||��| j|�S )
Nr� r� r� r� r� r� rn z( Redirection to url '%s' is not allowed.)r� r� r� rn )r� r r� r r r rG ) r� rH rd r� r� re rI r� r rL rL rM r | s
z FancyURLopener.redirect_internalc C s | j ||||||�S )N)r )r� rH rd r� r� re rI rL rL rM r
� s z FancyURLopener.http_error_301c C s | j ||||||�S )N)r )r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_303c C s2 |d kr | j ||||||�S | j|||||�S d S )N)r r� )r� rH rd r� r� re rI rL rL rM r � s z FancyURLopener.http_error_307Fc
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |d kr�t| | �|| �S t| | �|| |�S d S )Nzwww-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rE Zretry_� _basic_auth)r8 r� rP �matchr@ rt r� r� )
r� rH rd r� r� re rI rx �stuffr r r% r[ rL rL rM rT � s&
z FancyURLopener.http_error_401c
C s� d|kr t j| |||||� |d }tjd|�} | sHt j| |||||� | j� \}
} |
j� dkrtt j| |||||� |s�t j| |||||� d| j d } |d kr�t| | �|| �S t| | �|| |�S d S )Nzproxy-authenticatez![ ]*([^ ]+)[ ]+realm="([^"]*)"rE Z retry_proxy_r
)r8 r� rP r r@ rt r� r� )
r� rH rd r� r� re rI rx r r r r% r[ rL rL rM rU � s&
z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttp://r� �@rR z%s:%s@%srn )r )r r r r� �get_user_passwdr rG )r� rH r% rI rv r� r� r
r� r� �
proxyselectorr� r r rL rL rM �retry_proxy_http_basic_auth� s
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| jd�d } | | d � } | j| || �\} }
| pl|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| j|�S | j||�S d S )Nzhttps://r� r rR z%s:%s@%srn )r )r r r r� r r rG )r� rH r% rI rv r� r� r
r� r� r r� r r rL rL rM � retry_proxy_https_basic_auth� s
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttp://)r r� r r rG )
r� rH r% rI rv r� r� r r r� rL rL rM rF � s
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|jd�d }||d � }| j|||�\}}|p>|sDd S dt|dd�t|dd�|f }d| | } |d kr�| j| �S | j| |�S d S )Nr rR z%s:%s@%srn )r zhttps://)r r� r r rG )
r� rH r% rI rv r� r� r r r� rL rL rM �retry_https_basic_auth s
z%FancyURLopener.retry_https_basic_authr c C s` |d |j � }|| jkr2|r(| j|= n
| j| S | j||�\}}|sJ|rX||f| j|< ||fS )Nr )rt r �prompt_user_passwd)r� rv r% r� r� r r rL rL rM r s
z FancyURLopener.get_user_passwdc C sT dd l }y,td||f �}|j d|||f �}||fS tk
rN t� dS X d S )Nr z Enter username for %s at %s: z#Enter password for %s in %s at %s: )NN)�getpass�input�KeyboardInterrupt�print)r� rv r% r r r rL rL rM r $ s z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r r r
r r rT rU r r rF r r r rL rL rL rM r9 ] s"
c C s t d krtjd�a t S )Nr� )�
_localhostr� r� rL rL rL rM r� 4 s
r� c C sP t d krLyttjtj� �d �a W n( tjk
rJ ttjd�d �a Y nX t S )Nr: r� )� _thishostr$ r� r� r� r� rL rL rL rM r� < s r� c C s t d krdd l} | ja t S )Nr )�
_ftperrorsr� r� )r� rL rL rM r G s r c C s t d krtjd�a t S )Nrn )�
_noheadersr� r� rL rL rL rM � noheadersP s
r c @ sF e Zd Zddd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Zdd� Z dS )r� NTc C sX || _ || _|| _|| _|| _|| _d| _|| _y | j� W n | j � � Y nX d S )Nr )
r r rv r. r� rJ �refcount� keepalive�initr� )r� r r rv r. r� rJ r� rL rL rM r� ] s zftpwrapper.__init__c C s\ dd l }d| _|j� | _| jj| j| j| j� | jj| j | j
� dj | j �}| jj
|� d S )Nr r� )r� �busyZFTPr� Zconnectrv r. rJ Zloginr r r� r� �cwd)r� r� Z_targetrL rL rM r" m s
zftpwrapper.initc - C s� dd l }| j� |dkr"d}d}n d| }d}y| jj|� W n* |jk
rh | j� | jj|� Y nX d }|r�| r�y d| }| jj|�\}}W nR |jk
r� } z4t|�d d� d kr�t d
| �j
t j � d ��W Y d d }~X nX |�s�| jjd� |�rn| jj
� } zJy| jj|� W n4 |jk
�rP } zt d
| �|�W Y d d }~X nX W d | jj| � X d | }nd
}| jj|�\}}d| _t|jd�| j�}
| jd7 _|j� |
|fS )Nr rw r� zTYPE ArR zTYPE zRETR r= Z550z
ftp error: %rr: zLIST ZLISTr� )rw r� )r� � endtransferr� Zvoidcmdr� r" Z ntransfercmdZ
error_permr� r r� r� r� �pwdr$ r# r �makefile�
file_closer r� ) r� rN r� r� �cmd�isdirr� r� r� r& ZftpobjrL rL rM r� v sN
$
zftpwrapper.retrfilec C s
d| _ d S )Nr )r# )r� rL rL rM r% � s zftpwrapper.endtransferc C s d| _ | jdkr| j� d S )NFr )r! r �
real_close)r� rL rL rM r� � s
zftpwrapper.closec C s4 | j � | jd8 _| jdkr0| j r0| j� d S )NrR r )r% r r! r+ )r� rL rL rM r( � s zftpwrapper.file_closec C s2 | j � y| jj� W n t� k
r, Y nX d S )N)r% r� r� r )r� rL rL rM r+ � s
zftpwrapper.real_close)NT)
r� r� r� r� r" r� r% r� r( r+ rL rL rL rM r� Z s
-r� c C s� i } xBt jj� D ]4\}}|j� }|r|dd � dkr|| |d d� < qW dt jkr^| jdd � xXt jj� D ]J\}}|dd � dkrj|j� }|r�|| |d d� < qj| j|d d � d � qjW | S )
N� �_proxyZREQUEST_METHODr� i����i����i����i����i����)rW �environr{ rt r� )r r[ r� rL rL rM �getproxies_environment� s
r/ c
C s� |d krt � }y |d }W n tk
r. dS X |dkr<dS t| �\}}dd� |jd�D �}xP|D ]H}|rb|jd�}tj|�}d | }tj||tj�s�tj|| tj�rbdS qbW dS )
N�nor �*rR c S s g | ] }|j � �qS rL )rN )r� r
rL rL rM r# � s z,proxy_bypass_environment.<locals>.<listcomp>r� �.z
(.+\.)?%s$) r/ rq r
rB �lstriprP r� r rR )rv r Zno_proxy�hostonlyr. Z
no_proxy_listr[ �patternrL rL rM �proxy_bypass_environment� s&
r6 c
C s ddl m } t| �\}}dd� }d| kr4|d r4dS d }x�|jdf �D ]�}|sPqFtjd |�}|d k �r|d kr�ytj|�}||�}W n tk
r� wFY nX ||jd
��} |jd �}
|
d kr�d |jd
�j d�d
}
nt
|
d
d � �}
d
|
}
||
? | |
? k�rdS qF|| |�rFdS qFW dS )Nr )�fnmatchc S sh | j d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nr2 r� r � rR rb r: rQ r= )rB r� r� r^ r` )ZipAddrr- rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numr2 Zexclude_simpleT�
exceptionsz(\d+(?:\.\d+)*)(/\d+)?rR r: rQ � F) r7 r
r� rP r r� r� rm �group�countr^ ) rv �proxy_settingsr7 r4 r. r9 ZhostIPr� r� r1 �maskrL rL rM � _proxy_bypass_macosx_sysconf� s:
r@ �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S )N)rB r@ )rv r> rL rL rM �proxy_bypass_macosx_sysconf:
s rD c C s t � S )N)rC rL rL rL rM �getproxies_macosx_sysconf>
s rE c C s t � }|rt| |�S t| �S d S )N)r/ r6 rD )rv r rL rL rM r H
s
r c C s t � p
t� S )N)r/ rE rL rL rL rM r5 U
s c C s i } y dd l }W n tk
r$ | S X y�|j|jd�}|j|d�d }|r�t|j|d�d �}d|kr�x�|jd�D ]4}|jdd�\}}tjd|�s�d ||f }|| |< qrW n>|d d
� d kr�|| d < n$d
| | d < d| | d< d| | d< |j � W n t
t t fk
�r Y nX | S )Nr z;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r rR z ^([^/:]+)://z%s://%srZ zhttp:r� z http://%sz
https://%sr� zftp://%sr� )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� rB rP r ZCloserm rB r� )r rG �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryZ
s8
rO c C s t � p
t� S )N)r/ rO rL rL rL rM r5 �
s c & C s~ y dd l }W n tk
r dS X y6|j|jd�}|j|d�d }t|j|d�d �}W n tk
rl dS X | sz| r~dS t| �\}}|g} y tj |�}||kr�| j
|� W n tk
r� Y nX y tj |�}||kr�| j
|� W n tk
� r� Y nX |j d�}xp|D ]h} | dk�r*d|k�r*dS | j
dd �} | j
d
d �} | j
d d�} x$| D ] }
tj| |
tj��rTdS �qTW �qW dS )
Nr z;Software\Microsoft\Windows\CurrentVersion\Internet SettingsrF Z
ProxyOverrider z<local>r2 rR z\.r1 z.*�?)rG rH rI rJ rK r� rm r
r� r� r] ZgetfqdnrB r� rP r rR ) rv rG rL rM Z
proxyOverrideZrawHostr. ZaddrZfqdnr2 r� rL rL rM �proxy_bypass_registry�
sR
rQ c C s t � }|rt| |�S t| �S d S )N)r/ r6 rQ )rv r rL rL rM r �
s
)NNN)N)~r r� r� re Z http.clientr� r� rW r/ rP r� r r� rc � collectionsrZ rT r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD rH rC �__all__� version_infor� rF r� r0 r1 r\ r6 r7 rQ �ASCIIrr rw r r r2 r r/ r r r r r r! r" r# r$ r% �urandomrd r& r' r( ry r) r� r� rE r] r r. r\ r^ r* r� r+ r, r- r� r[ Z
nturl2pathr4 r3 r� r8 r9 r r� r r� r r r r r� r/ r6 r@ �platformZ_scproxyrB rC rD rE r r5 rO rQ rL rL rL rM �<module>T s� P
T
?n $q *@
o v
+3:5! A W
_
#<
- 2
PK (�Z3<�Z
Z
) __pycache__/response.cpython-36.opt-2.pycnu �[��� 3
\� � @ sZ d dl Z ddddgZG dd� de j�ZG dd� de�ZG dd� de�ZG d d� de�ZdS )
� N�addbase� addclosehook�addinfo�
addinfourlc s4 e Zd Z� fdd�Zdd� Zdd� Zdd� Z� ZS ) r c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr )� __class__� �'/usr/lib64/python3.6/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file)r
r r r
�__repr__ s zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueError)r
r r r
� __enter__ s zaddbase.__enter__c C s | j � d S )N)�close)r
�type�value� tracebackr r r
�__exit__! s zaddbase.__exit__)r �
__module__� __qualname__r r r r �
__classcell__r r )r r
r s c s( e Zd Z� fdd�Z� fdd�Z� ZS )r c s t t| �j|� || _|| _d S )N)r r r � closehook�hookargs)r
r r r )r r r
r ( s zaddclosehook.__init__c s> z(| j }| j}|r&d | _ d | _||� W d tt| �j� X d S )N)r r r r r )r
r r )r r r
r - s zaddclosehook.close)r r r r r r r r )r r
r % s c s$ e Zd Z� fdd�Zdd� Z� ZS )r c s t t| �j|� || _d S )N)r r r �headers)r
r r )r r r
r < s zaddinfo.__init__c C s | j S )N)r )r
r r r
�info@ s z addinfo.info)r r r r r r r r )r r
r 9 s c s. e Zd Zd� fdd� Zdd� Zdd� Z� ZS ) r Nc s" t t| �j||� || _|| _d S )N)r r r �url�code)r
r r r! r" )r r r
r G s zaddinfourl.__init__c C s | j S )N)r" )r
r r r
�getcodeL s zaddinfourl.getcodec C s | j S )N)r! )r
r r r
�geturlO s zaddinfourl.geturl)N)r r r r r# r$ r r r )r r
r D s )Ztempfile�__all__Z_TemporaryFileWrapperr r r r r r r r
�<module> s
PK (�Z�s/�l� l� __pycache__/parse.cpython-36.pycnu �[��� 3
�\dhɨ � @ s� d Z ddlZddlZddlZddlZddlZddddddd d
d d d
ddddddddddgZddddd d d d d d!d"d#d$d%d&d'd(d)d*gZddddd d+d d d d"d d!d,d#d$d%d-d'd(d&d.d/d0d)d*gZddd1d#dd d d!d$d%d2d3d"d&d4gZ dd1d5d6d+d d d,d2d3g
Z
ddd d d d!d"dd$d%d2d3g Z ddd1ddd6d d d d!d,d d#g
Z d7Z
d8Zd9d:d;gZd<Zi Zd=d>� Zd?Zd@ZdAdB� ZeefdCdD�ZeefdEdF�ZdGdH� ZG dIdJ� dJe�ZG dKdL� dLe�ZG dMdN� dNe�Z G dOdP� dPe e�Z G dQdR� dRe e�Z ddSlm Z e ddT�Z e ddU�Z!e ddV�Z"dWe _ dXe j#_ dYe j$_ dZe!_ d[e!j%_ d\e!j&_ d]e!j'_ d^e!j(_ d_e!j$_ d`e"_ e!j%j e"j%_ e!j&j e"j&_ e!j'j e"j'_ dae"j)_ e!j(j e"j(_ e!j$j e"j$_ e Z*G dbd� de e�Z+G dcd� de!e �Z,G ddd� de"e �Z-G ded� de e�Z.G dfd� de!e �Z/G dgd� de"e �Z0dhdi� Z1e1� [1d�dkd�Z2dldm� Z3d�dndo�Z4dpdq� Z5drds� Z6dtdu� Z7d�dvd�Z8dwd� Z9dxd� Z:d�dyd�Z;dzd� Z<d{Z=da>d|d� Z?ej@d}�ZAd�d�d�ZBd�d�d
�ZCG d�d�� d�eD�ZEd�ZFdaGd�d�d �ZHd�d�d�ZIeJd��ZKeLeK�ZMi ZNG d�d�� d�ejO�ZPd�d�d �ZQd�d�d
�ZRd�d�d�ZSd�dddeRfd�d �ZTd�d�� ZUd�d�� ZVdaWd�d�� ZXdaYd�d�� ZZd�d�� Z[d�d�� Z\da]d�d�� Z^d�d�d��Z_d�d�� Z`d�d�� Zad�d�� Zbd�d�� ZcdS )�a3 Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t j� tj� dS )z,Clear the parse cache and the quoters cache.N)� _parse_cache�clear�
_safe_quoters� r! r! �$/usr/lib64/python3.6/urllib/parse.py� clear_cache` s r# �ascii�strictc C s | S )Nr! )�objr! r! r" �_noopo s r' c C s | j ||�S )N)�encode)r& �encoding�errorsr! r! r" �_encode_resultr s r+ c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|j � ��nd V qdS )r N)�decode)�.0�x)r) r* r! r" � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr) r* r! )r) r* r" � _decode_argsv s r2 c G sZ t | d t�}x.| dd � D ] }|r t |t�|kr td��q W |rL| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr' r2 r+ )r1 Z str_input�argr! r! r" � _coerce_argsz s
r8 c @ s e Zd ZdZf Zddd�ZdS )�_ResultMixinStrz>Standard approach to encoding parsed results from str to bytesr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r( )r- r. )r) r* r! r" r/ � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart)�selfr) r* r! )r) r* r" r( � s z_ResultMixinStr.encodeN)r$ r% )�__name__�
__module__� __qualname__�__doc__� __slots__r( r! r! r! r" r9 � s r9 c @ s e Zd ZdZf Zddd�ZdS )�_ResultMixinBytesz>Standard approach to decoding parsed results from bytes to strr$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|j � ��V qd S )N)r, )r- r. )r) r* r! r" r/ � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpart)r; r) r* r! )r) r* r" r, � s z_ResultMixinBytes.decodeN)r$ r% )r< r= r> r? r@ r, r! r! r! r" rA � s rA c @ sD e Zd ZdZf Zedd� �Zedd� �Zedd� �Zedd � �Z d
S ) �_NetlocResultMixinBasezHShared methods for the parsed result objects containing a netloc elementc C s
| j d S )Nr )� _userinfo)r; r! r! r" �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr3 )rD )r; r! r! r" �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|j|�\}}}|j� | | S )Nr �%� %)� _hostinfor4 r5 � partition�lower)r; �hostname� separatorZpercentZzoner! r! r" rL � s
z _NetlocResultMixinBase.hostnamec C s@ | j d }|d k r<t|d�}d| ko.dkn s<td��|S )Nr3 �
r i�� zPort out of range 0-65535)rI �int�
ValueError)r; �portr! r! r" rQ � s
z_NetlocResultMixinBase.portN)
r< r= r> r? r@ �propertyrE rF rL rQ r! r! r! r" rC � s rC c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinStrc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N�@�:)�netloc�
rpartitionrJ )r; rV �userinfo� have_info�hostinforE �
have_passwordrF r! r! r" rD � s z _NetlocResultMixinStr._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )NrT �[�]rU )rV rW rJ )r; rV �_rZ � have_open_br� bracketedrL rQ r! r! r" rI � s z _NetlocResultMixinStr._hostinfoN)r< r= r> r@ rR rD rI r! r! r! r" rS � s rS c @ s( e Zd Zf Zedd� �Zedd� �ZdS )�_NetlocResultMixinBytesc C sD | j }|jd�\}}}|r4|jd�\}}}|s<d }nd }}||fS )N� @� :)rV rW rJ )r; rV rX rY rZ rE r[ rF r! r! r" rD � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|jd�\}}}|jd�\}}}|rL|jd�\}}}|jd�\}}}n|jd�\}}}|sdd }||fS )Nrb � [� ]rc )rV rW rJ )r; rV r^ rZ r_ r` rL rQ r! r! r" rI � s z!_NetlocResultMixinBytes._hostinfoN)r< r= r> r@ rR rD rI r! r! r! r" ra � s ra )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zr
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N�#)�fragment�url)r; r! r! r" �geturlE s zDefragResult.geturlN)r< r= r> r@ rj r! r! r! r" r C s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj M s zSplitResult.geturlN)r< r= r> r@ rj r! r! r! r" r K s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj R s zParseResult.geturlN)r< r= r> r@ rj r! r! r! r" r P s c @ s e Zd Zf Zdd� ZdS )r c C s | j r| jd | j S | jS d S )N� #)rh ri )r; r! r! r" rj X s zDefragResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r V s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj ` s zSplitResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r ^ s c @ s e Zd Zf Zdd� ZdS )r c C s t | �S )N)r )r; r! r! r" rj e s zParseResultBytes.geturlN)r< r= r> r@ rj r! r! r! r" r c s c C s8 t tfttfttff} x | D ]\}}||_||_q W d S )N)r r r r r r r: rB )Z
_result_pairsZ_decodedZ_encodedr! r! r" �_fix_result_transcodingi s
rl Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )a# Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.�;r )r8 r � uses_params� _splitparamsr )
ri �scheme�allow_fragments�_coerce_resultZ splitresultrV �queryrh �params�resultr! r! r" r v s c C sR d| kr,| j d| jd��}|dk r6| dfS n
| j d�}| d |� | |d d � fS )N�/rm r r r3 )�find�rfind)ri �ir! r! r" ro � s
ro c C sL t | �}x*dD ]"}| j||�}|dkrt||�}qW | ||� | |d � fS )Nz/?#r )�lenrw �min)ri �start�delim�cZwdelimr! r! r" � _splitnetloc� s
r c C s� | st dd� | D �� r d S dd l}| jdd�}|jdd�}|jdd�}|jdd�}|jd |�}||krnd S x(d
D ] }||krttd | d d
��qtW d S )Nc s s | ]}t |�d kV qdS )� N)�ord)r- r~ r! r! r" r/ � s z _checknetloc.<locals>.<genexpr>r rT r rU rg �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�any� unicodedata�replace� normalizerP )rV r� �nZnetloc2r~ r! r! r" � _checknetloc� s
r� c C s xt D ]}| j|d�} qW | S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )ri �br! r! r" � _remove_unsafe_bytes_from_url� s
r� c C sB | j d�r tjd| �s>td��n tj| �}t|tj�r>td��d S )N�vz\Av[a-fA-F0-9]+\..+\Zz IPvFuture address is invalidz%An IPv4 address cannot be in brackets)�
startswith�re�matchrP � ipaddressZ
ip_addressr4 Z IPv4Address)rL Zipr! r! r" �_check_bracketed_host� s
r� c C s� t | |�\} }}t| �} t|�}| jt�} |jt�}t|�}| ||t| �t|�f}tj|d�}|rj||�S t t�t
kr|t � d } }}| j d�} | dk�r�| d| � dk�r~| d| � j
� }| | d d� } | dd� dk�r t| d�\}} d |ko�d
|k�sd
|k�r d |k�r td ��|�r<d | k�r<| jd d�\} }d
| k�rV| jd
d�\} }t|� t||| ||�}
|
t|< ||
�S xd| d| � D ]} | tk�r�P �q�W | | d d� } | �s�tdd� | D ���r�| d| � j
� | }} | dd� dk�rht| d�\}} d |k�rd
|k�s,d
|k�r4d |k�r4td ��d |k�rhd
|k�rh|jd �d jd
�d }
t|
� |�r�d | k�r�| jd d�\} }d
| k�r�| jd
d�\} }t|� t||| ||�}
|
t|< ||
�S )a Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.Nr rU r r r3 � z//r\ r] zInvalid IPv6 URLrg r� c s s | ]}|d kV qdS )�
0123456789Nr! )r- r~ r! r! r" r/ � s zurlsplit.<locals>.<genexpr>)r8 r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getrz �MAX_CACHE_SIZEr# rw rK r rP �splitr� r � scheme_charsr� rJ r� )ri rp rq rr �key�cachedrV rs rh ry r� r~ �restZbracketed_hostr! r! r" r � sj
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )z�Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent).z%s;%s)r8 r )�
componentsrp rV ri rt rs rh rr r! r! r" r � s c C s� t | � \}}}}}}|s4|r`|tkr`|dd� dkr`|rP|dd� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S )
ak Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent).Nr� z//r3 rv r rU r� rg )r8 � uses_netloc)r� rp rV ri rs rh rr r! r! r" r s c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | r�|
r�|} |}
|s�|}|t|
| | |
||f��S |jd�}|d dkr�|d= | dd� dk� r�| jd�}n(|| jd� }td|dd � �|dd
�< g }xX|D ]P}|dk�rdy |j� W n tk
�r` Y nX n|dk�rt�q0n
|j |� �q0W |d d k�r�|j d� |t|
| dj
|��p�d|
||f��S )
zaJoin a base URL and a possibly relative URL to form an absolute
interpretation of the latter.r rv r3 N�..�.���r� r� r� r� )r� r� ) r8 r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baseri rq rr ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentrp rV �pathrt rs rh Z
base_partsZsegmentsZ
resolved_pathZsegr! r! r" r sT
c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )z�Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
rg r )r8 r r r ) ri rr �sr� �p�a�qZfragZdefragr! r! r" r _ s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| jd�} | j d�}t|�dkr<| S |d g}|j}tdkrbdd� tD �axb|dd� D ]R}y(|t|dd � � ||d d� � W qp tk
r� |d� ||� Y qpX qpW dj |�S )
z,unquote_to_bytes('abc%20def') -> b'abc def'.� zutf-8rH r3 r Nc S s4 i | ],}t D ]"}tt|| d �g�|| j� �q qS )� )�_hexdig�bytesrO r( )r- r� r� r! r! r" �
<dictcomp>� s z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r4 r5 r( rz r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr! r! r" r r s*
z([ -]+)�utf-8r� c C s� d| kr| j | S |dkr d}|dkr*d}tj | �}|d g}|j}x@tdt|�d�D ],}|t|| �j||�� |||d � qVW dj|�S ) a� Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
rG Nzutf-8r� r r3 r� r )r� �_asciirer� �rangerz r r, r� )r� r) r* r� r� r� ry r! r! r" r � s
Fc C sR i }t | ||||||d�}x2|D ]*\} }
| |kr@|| j|
� q |
g|| < q W |S )a� Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError if there
are more than n fields read by parse_qsl().
Returns a dictionary.
)r) r* �max_num_fieldsrM )r
r� ) �qs�keep_blank_values�strict_parsingr) r* r� rM Z
parsed_result�pairs�name�valuer! r! r" r � s c @ s e Zd ZdZdS )� _QueryStringSeparatorWarningz>Warning for using default `separator` in parse_qs or parse_qslN)r< r= r> r? r! r! r! r" r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |jd�}| s6t|ttf� rF|dk rFtd��t� }|dk�rVt}d} |dkrvtj j
| �}d}
|dkr�y t t �} W n t
k
r� Y nJX | �: ddl} | jdd'd�}
|
j| � |
j
d | dd
�}|aW dQ R X t }
|dk�r d | k�rdd lm} |d-tdd� d}n:|dk�r,|}n*t|�dk�rVt| � d|
� d�d d ��|dk �r�||k�r�d| jd� | jd � }nd| j|� }||k �r�td ��||k�r�d d � | jd�D �}nd d � | j|�D �}g }x�|D ]�}| �r�| �r��q�|jd!d�}t|�dk�r>|�r(td"|f ��|�r�|jd#� n�q�t|d ��sR|�r�|d jd$d%�}t|||d&�}||�}|d jd$d%�}t|||d&�}||�}|j||f� �q�W |S ).a� Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError
if there are more than n fields read by parse_qsl().
Returns a list, as G-d intended.
r$ Nz*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler rg )Z
interpolationZcomment_prefixesr )Zfallbackrm )�warnz4The default separator of urllib.parse.parse_qsl and z1parse_qs was changed to '&' to avoid a web cache z"poisoning issue (CVE-2021-23336). z4By default, semicolons no longer act as query field z separators. z3See https://access.redhat.com/articles/5860431 for z
more details.r� )�
stacklevel�&Zlegacyr3 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|j d �D ]}|�qqS )rm )r� )r- �s1�s2r! r! r" �
<listcomp>< s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r! r! )r- r� r! r! r" r� > s �=zbad query field: %rr �+� )r) r* )rg zeThe default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. z�The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for a The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.)r8 r4 r� r, r5 rP �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� rz �countr� r� r� r )r� r� r� r) r* r� rM rr Z_legacyZ envvar_nameZ
config_sourcer r� �configr� �
num_fieldsr� �rZ
name_valueZnvr� r� r! r! r" r
� s�
c C s | j dd�} t| ||�S )z�Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
r� r� )r� r )r� r) r* r! r! r" r V s sA ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) �Quoterz�A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
c C s t j|�| _dS )zsafe: bytes object.N)� _ALWAYS_SAFE�union�safe)r; r� r! r! r" �__init__n s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__r< �dict)r; r! r! r" �__repr__r s zQuoter.__repr__c C s( || j krt|�ndj|�}|| |< |S )Nz%{:02X})r� �chr�format)r; r� r� r! r! r" � __missing__v s zQuoter.__missing__N)r< r= r> r? r� r� r� r! r! r! r" r� f s r� rv c C sb t | t�r8| s| S |dkr d}|dkr*d}| j||�} n |dk rHtd��|dk rXtd��t| |�S )a� quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted.
RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists
the following reserved characters.
reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" |
"$" | ","
Each of these characters is reserved in some component of a URL,
but not necessarily in all of them.
By default, the quote function is intended for quoting the path
section of a URL. Thus, it will not encode '/'. This character
is reserved, but in typical usage the quote function is being
called on a path where the existing slash characters are used as
reserved characters.
string and safe may be either str or bytes objects. encoding and errors
must not be specified if string is a bytes object.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
Nzutf-8r% z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r4 r5 r( r6 r
)r� r� r) r* r! r! r" r | s
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | jdd�S )z�Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
r� � r� )r4 r5 r� r r� )r� r� r) r* Zspacer! r! r" r � s
c s� t | ttf�std��| s dS t |t�r6|jdd�}ntdd� |D ��}| jt| �s^| j� S y t | � W n& t
k
r� t |�j t |< � Y nX dj
� fdd�| D ��S )z�Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def?') -> 'abc%20def%3f'
z!quote_from_bytes() expected bytesr r$ �ignorec S s g | ]}|d k r|�qS )� r! )r- r~ r! r! r" r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r! r! )r- �char)�quoterr! r" r� � s )r4 r� � bytearrayr6 r5 r( �rstrip�_ALWAYS_SAFE_BYTESr, r r� r� � __getitem__r� )Zbsr� r! )r� r" r
� s
c C s t | d�r| j� } nRy t| �r2t| d t� r2t�W n0 tk
rd tj� \}}}td�j|��Y nX g } |s�xr| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | j |
d | � qtW �n,�x(| D �] \}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rL|| |�} | j |
d | � q�t| t
��rz|| |||�} | j |
d | � q�y t| �} W n: tk
�r� |t
| �|||�} | j |
d | � Y q�X xJ| D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| j |
d |
� �q�W q�W dj | �S )a^ Encode a dict or sequence of two-element tuples into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The components of a query arg may each be either a string or a bytes type.
The safe, encoding, and errors parameters are passed down to the function
specified by quote_via (encoding and errors only if a component is a str).
�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� rz r4 r0 r6 �sys�exc_info�with_tracebackr� r5 r� r� )rs Zdoseqr� r) r* Z quote_viaZtyZva�tb�l�kr� r. Zeltr! r! r" r � sP
c C sJ t | t�rFy| jd�j� } W n( tk
rD tdt| � d ��Y nX | S )zto_bytes(u"URL") --> 'URL'.�ASCIIzURL z contains non-ASCII characters)r4 r5 r( r, � UnicodeError�repr)ri r! r! r" �to_bytes s
r� c C s` t | �j� } | dd� dkr<| dd� dkr<| dd� j� } | dd� dkr\| dd� j� } | S ) z8unwrap('<URL:type://host/path>') --> 'type://host/path'.Nr3 �<�>� zURL:r� r� )r5 r� )ri r! r! r" �unwrap, s r c C sD t dkrtjdtj�a t j| �}|r<|j� \}}|j� |fS d| fS )z:splittype('type:opaquestring') --> 'type', 'opaquestring'.Nz
([^/:]+):(.*))� _typeprogr� �compile�DOTALLr� �groupsrK )ri r� rp �datar! r! r" � splittype5 s
r c C sX t dkrtjdtj�a t j| �}|rP|j� \}}|rH|d dkrHd| }||fS d| fS )z;splithost('//host[:port]/path') --> 'host[:port]', '/path'.Nz//([^/#?]*)(.*)r rv )� _hostprogr� r r r� r )ri r� Z host_portr� r! r! r" � splithostB s
r c C s | j d�\}}} |r|nd| fS )zJsplituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.rT N)rW )�host�userr} r! r! r" � splituserP s r c C s | j d�\} }}| |r|ndfS )z/splitpasswd('user:passwd') -> 'user', 'passwd'.rU N)rJ )r r} Zpasswdr! r! r" � splitpasswdU s r
c C sD t dkrtjdtj�a t j| �}|r<|j� \} }|r<| |fS | dfS )z*splitport('host:port') --> 'host', 'port'.Nz(.*):([0-9]*)$)� _portprogr� r r r� r )r
r� rQ r! r! r" � splitport\ s
r r3 c C sT | j d�\} }}|s|} n2|rLy t|�}W n tk
rB d}Y nX | |fS | |fS )z�Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number.rU N)rW rO rP )r
Zdefportr} rQ Znportr! r! r" �
splitnporti s
r c C s$ | j d�\}}}|r ||fS | dfS )z/splitquery('/path?query') --> '/path', 'query'.r� N)rW )ri r� r} rs r! r! r" �
splitqueryy s r c C s$ | j d�\}}}|r ||fS | dfS )z)splittag('/path#tag') --> '/path', 'tag'.rg N)rW )ri r� r} �tagr! r! r" �splittag� s r c C s | j d�}|d |dd� fS )zksplitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...].rm r r3 N)r� )ri Zwordsr! r! r" � splitattr� s
r c C s | j d�\} }}| |r|ndfS )z-splitvalue('attr=value') --> 'attr', 'value'.r� N)rJ )�attrr} r� r! r! r" �
splitvalue� s r )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )rv NN)r NN)rv r� )r� )dr? r� r� r� � collectionsr� �__all__r� r� rn Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r# Z_implicit_encodingZ_implicit_errorsr' r+ r2 r8 r� r9 rA rC rS ra rf Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBaseri rh rp rV r� rs rt Z
ResultBaser r r r r r rl r ro r r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r � defaultdictr� r r r
r r� r r r r r r r
r r r r r r r r! r! r! r" �<module> s
!
C
E
&
y
,
O
PK (�Z��
z z # __pycache__/__init__.cpython-36.pycnu �[��� 3
�]dh � @ s d S )N� r r r �'/usr/lib64/python3.6/urllib/__init__.py�<module> s PK (�Z���;! ! & __pycache__/error.cpython-36.opt-2.pycnu �[��� 3
\Q
� @ sL d dl ZdddgZG dd� de�ZG dd� deejj�ZG dd� de�ZdS )� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S )N)�args�reason�filename)�selfr r � r �$/usr/lib64/python3.6/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r )r r r r
�__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r r r r
r s
c @ sT e Zd ZejjjZdd� Zdd� Zdd� Z e
dd� �Z e
d d
� �Z e j
d d
� �Z d S )
r c C s: || _ || _|| _|| _|| _|d k r6| j||||� d S )N)�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r r r
r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s)r r )r r r r
r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>)r r )r r r r
�__repr__7 s zHTTPError.__repr__c C s | j S )N)r )r r r r
r < s zHTTPError.reasonc C s | j S )N)r )r r r r
�headers@ s zHTTPError.headersc C s
|| _ d S )N)r )r r r r r
r D s N)r
r r �urllib�response�
addinfourlr r r r �propertyr r �setterr r r r
r # s
c @ s e Zd Zdd� ZdS )r c C s t j| |� || _d S )N)r r �content)r �messager r r r
r K s z ContentTooShortError.__init__N)r
r r r r r r r
r I s ) Zurllib.responser �__all__�OSErrorr r r r r r r r r
�<module> s
&PK (�Z��
z z ) __pycache__/__init__.cpython-36.opt-1.pycnu �[��� 3
�]dh � @ s d S )N� r r r �'/usr/lib64/python3.6/urllib/__init__.py�<module> s PK (�Zw��3 3 , __pycache__/robotparser.cpython-36.opt-2.pycnu �[��� 3
\�" � @ sX d dl Z d dlZd dlZdgZe jdd�ZG dd� d�ZG dd� d�ZG dd � d �Z dS )
� N�RobotFileParser� RequestRatezrequests secondsc @ sf e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dd� Z dd� Z dd� Z
dS )r � c C s, g | _ d | _d| _d| _| j|� d| _d S )NFr )�entries�
default_entry� disallow_all� allow_all�set_url� last_checked)�self�url� r
�*/usr/lib64/python3.6/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S )N)r
)r r
r
r �mtime$ s zRobotFileParser.mtimec C s dd l }|j � | _d S )Nr )�timer
)r r r
r
r �modified- s zRobotFileParser.modifiedc C s& || _ tjj|�dd� \| _| _d S )N� � )r �urllib�parse�urlparse�host�path)r r r
r
r r 5 s zRobotFileParser.set_urlc C s� yt jj| j�}W nR t jjk
rd } z2|jdkr:d| _n|jdkrT|jdk rTd| _W Y d d }~X n X |j � }| j
|j d�j � � d S )N� � Ti� i� zutf-8)r r )
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r �f�err�rawr
r
r r : s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | jj|� d S )N�*)�
useragentsr r �append)r �entryr
r
r �
_add_entryG s
zRobotFileParser._add_entryc C s6 d}t � }| j� �x|D �]�}|sT|dkr8t � }d}n |dkrT| j|� t � }d}|jd�}|dkrr|d |� }|j� }|s�q|jdd�}t|�dkr|d j� j� |d< tj j
|d j� �|d< |d dk�r |dkr�| j|� t � }|j j |d � d}q|d dk�r4|dk�r|j
j t|d d�� d}q|d d k�rh|dk�r|j
j t|d d
�� d}q|d d k�r�|dk�r|d j� j� �r�t|d �|_d}q|d d kr|dkr|d jd
�}t|�dk�r|d j� j� �r|d j� j� �rtt|d �t|d ��|_d}qW |dk�r2| j|� d S )Nr r � �#�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/)�Entryr r( �find�strip�split�len�lowerr r �unquoter% r& � rulelines�RuleLine�isdigit�int�delayr �req_rate)r �lines�stater' �line�iZnumbersr
r
r r P sd
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tjjtjj|��}tjjdd|j|j |j
|j f�}tjj |�}|sfd}x"| j
D ]}|j|�rn|j|�S qnW | jr�| jj|�S dS )NFTr r, )r r r
r r r r3 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r � useragentr Z
parsed_urlr' r
r
r � can_fetch� s$
zRobotFileParser.can_fetchc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r8 r )r rB r' r
r
r � crawl_delay� s
zRobotFileParser.crawl_delayc C s4 | j � s d S x | jD ]}|j|�r|jS qW | jjS )N)r r r@ r9 r )r rB r' r
r
r � request_rate� s
z RobotFileParser.request_ratec C s0 | j }| jd k r || jg }djtt|��d S )N�
)r r �join�map�str)r r r
r
r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__r r r r r r( r rC rD rE rJ r
r
r
r r s
C c @ s$ e Zd Zdd� Zdd� Zdd� ZdS )r5 c C s> |dkr| rd}t jjt jj|��}t jj|�| _|| _d S )Nr T)r r r> r r? r rA )r r rA r
r
r r � s
zRuleLine.__init__c C s | j dkp|j| j �S )Nr$ )r �
startswith)r �filenamer
r
r r@ � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rA r )r r
r
r rJ � s zRuleLine.__str__N)rK rL rM r r@ rJ r
r
r
r r5 � s r5 c @ s, e Zd Zdd� Zdd� Zdd� Zdd� Zd S )
r- c C s g | _ g | _d | _d | _d S )N)r% r4 r8 r9 )r r
r
r r � s zEntry.__init__c C s� g }x | j D ]}|jd|� �� q W | jd k r@|jd| j� �� | jd k rj| j}|jd|j� d|j� �� |jtt| j �� |jd� dj
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r, r rF ) r% r& r8 r9 ZrequestsZseconds�extendrH rI r4 rG )r Zret�agentZrater
r
r rJ � s
z
Entry.__str__c C sF |j d�d j� }x.| jD ]$}|dkr*dS |j� }||krdS qW dS )Nr, r r$ TF)r0 r2 r% )r rB rQ r
r
r r@ � s zEntry.applies_toc C s$ x | j D ]}|j|�r|jS qW dS )NT)r4 r@ rA )r rO r< r
r
r rA � s
zEntry.allowanceN)rK rL rM r rJ r@ rA r
r
r
r r- � s
r- )
� collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r5 r- r
r
r
r �<module>
s 2PK (�Z���QH
H
error.pynu �[��� """Exception classes raised by urllib.
The base exception class is URLError, which inherits from OSError. It
doesn't define any behavior of its own, but is the base class for all
exceptions defined in this package.
HTTPError is an exception class that is also a valid HTTP response
instance. It behaves this way because HTTP protocol errors are valid
responses, with a status code, headers, and a body. In some contexts,
an application may want to handle an exception like a regular
response.
"""
import urllib.response
__all__ = ['URLError', 'HTTPError', 'ContentTooShortError']
class URLError(OSError):
# URLError is a sub-type of OSError, but it doesn't share any of
# the implementation. need to override __init__ and __str__.
# It sets self.args for compatibility with other OSError
# subclasses, but args doesn't have the typical format with errno in
# slot 0 and strerror in slot 1. This may be better than nothing.
def __init__(self, reason, filename=None):
self.args = reason,
self.reason = reason
if filename is not None:
self.filename = filename
def __str__(self):
return '<urlopen error %s>' % self.reason
class HTTPError(URLError, urllib.response.addinfourl):
"""Raised when HTTP error occurs, but also acts like non-error return"""
__super_init = urllib.response.addinfourl.__init__
def __init__(self, url, code, msg, hdrs, fp):
self.code = code
self.msg = msg
self.hdrs = hdrs
self.fp = fp
self.filename = url
# The addinfourl classes depend on fp being a valid file
# object. In some cases, the HTTPError may not have a valid
# file object. If this happens, the simplest workaround is to
# not initialize the base classes.
if fp is not None:
self.__super_init(fp, hdrs, url, code)
def __str__(self):
return 'HTTP Error %s: %s' % (self.code, self.msg)
def __repr__(self):
return '<HTTPError %s: %r>' % (self.code, self.msg)
# since URLError specifies a .reason attribute, HTTPError should also
# provide this attribute. See issue13211 for discussion.
@property
def reason(self):
return self.msg
@property
def headers(self):
return self.hdrs
@headers.setter
def headers(self, headers):
self.hdrs = headers
class ContentTooShortError(URLError):
"""Exception raised when downloaded size does not match content-length."""
def __init__(self, message, content):
URLError.__init__(self, message)
self.content = content
PK (�Z��@� � response.pynu �[��� """Response classes used by urllib.
The base class, addbase, defines a minimal file-like interface,
including read() and readline(). The typical response object is an
addinfourl instance, which defines an info() method that returns
headers and a geturl() method that returns the url.
"""
import tempfile
__all__ = ['addbase', 'addclosehook', 'addinfo', 'addinfourl']
class addbase(tempfile._TemporaryFileWrapper):
"""Base class for addinfo and addclosehook. Is a good idea for garbage collection."""
# XXX Add a method to expose the timeout on the underlying socket?
def __init__(self, fp):
super(addbase, self).__init__(fp, '<urllib response>', delete=False)
# Keep reference around as this was part of the original API.
self.fp = fp
def __repr__(self):
return '<%s at %r whose fp = %r>' % (self.__class__.__name__,
id(self), self.file)
def __enter__(self):
if self.fp.closed:
raise ValueError("I/O operation on closed file")
return self
def __exit__(self, type, value, traceback):
self.close()
class addclosehook(addbase):
"""Class to add a close hook to an open file."""
def __init__(self, fp, closehook, *hookargs):
super(addclosehook, self).__init__(fp)
self.closehook = closehook
self.hookargs = hookargs
def close(self):
try:
closehook = self.closehook
hookargs = self.hookargs
if closehook:
self.closehook = None
self.hookargs = None
closehook(*hookargs)
finally:
super(addclosehook, self).close()
class addinfo(addbase):
"""class to add an info() method to an open file."""
def __init__(self, fp, headers):
super(addinfo, self).__init__(fp)
self.headers = headers
def info(self):
return self.headers
class addinfourl(addinfo):
"""class to add info() and geturl() methods to an open file."""
def __init__(self, fp, headers, url, code=None):
super(addinfourl, self).__init__(fp, headers)
self.url = url
self.code = code
def getcode(self):
return self.code
def geturl(self):
return self.url
PK *(�ZyR� � " __pycache__/request.cpython-38.pycnu �[��� U
e5d�� � ! @ s� d Z ddlZddlZddlZddlZddlZddlZddlZddl Z ddl
Z
ddl Z ddl Z ddl
Z
ddlZddlZddlZddlZddlmZmZmZ ddlmZmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( ddl)m*Z*m+Z+ z ddl,Z,W n e-k
�r dZ.Y nX dZ.dd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'd(g!Z/d)e
j0dd*� Z1da2de j3fddddd+�d,d �Z4d-d � Z5g Z6d~d.d%�Z7d/d&� Z8e
�9d0e
j:�Z;d1d2� Z<G d3d� d�Z=G d4d � d �Z>d5d!� Z?G d6d
� d
�Z@G d7d � d e@�ZAG d8d � d e@�ZBG d9d � d e@�ZCd:d;� ZDG d<d� de@�ZEG d=d� d�ZFG d>d� deF�ZGG d?d� deG�ZHG d@d� d�ZIG dAd� deIe@�ZJG dBd� deIe@�ZKejLZMG dCd� d�ZNG dDd� de@eN�ZOG dEd� de@eN�ZPG dFdG� dGe@�ZQG dHd� deQ�ZReSejTdI��r*G dJdK� dKeQ�ZUe/�VdK� G dLd
� d
e@�ZWG dMd � d e@�ZXdNdO� ZYdPdQ� ZZG dRd� de@�Z[dSdT� Z\G dUd� de@�Z]G dVd� de]�Z^G dWd � d e@�Z_dXZ`ejadYk�r�ddZlbmcZcmdZd nd[d#� Zcd\d"� Zdi ZeG d]d'� d'�ZfG d^d(� d(ef�Zgdahd_d`� Zidajdadb� Zkdaldcdd� Zmdandedf� ZoG dgdh� dh�Zpdidj� Zqddkdl�Zrdmdn� Zse
jtdok�r�ddplumvZvmwZw dqdr� Zxdsdt� Zydudv� Zzdwd$� Z{n6ejadYk�r�dxdy� Z|dzd$� Z{d{d|� Z}d}dv� ZzneqZ{erZzdS )�a�
An extensible library for opening URLs using a variety of protocols
The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below). It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.
The OpenerDirector manages a collection of Handler objects that do
all the actual work. Each Handler implements a particular protocol or
option. The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL. For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns. The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.
urlopen(url, data=None) -- Basic usage is the same as original
urllib. pass the url and optionally data to post to an HTTP URL, and
get a file-like object back. One difference is that you can also pass
a Request instance instead of URL. Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.
build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers. Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate. If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.
install_opener -- Installs a new opener as the default opener.
objects of interest:
OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.
Request -- An object that encapsulates the state of a request. The
state can be as simple as the URL. It can also include extra HTTP
headers, e.g. a User-Agent.
BaseHandler --
internals:
BaseHandler and parent
_call_chain conventions
Example usage:
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
uri='https://mahler:8092/site-updates.py',
user='klem',
passwd='geheim$parole')
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote�
_splittype�
_splithost�
_splitport�
_splituser� _splitpasswd�
_splitattr� _splitquery� _splitvalue� _splittag� _to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfddl }|�dtd� |dk r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt dkr�t
� a } nt } | � | ||�S ) a$
Open the URL url, which can be either a string or a Request object.
*data* must be an object specifying additional data to be sent to
the server, or None if no such data is needed. See Request for
details.
urllib.request module uses HTTP/1.1 and includes a "Connection:close"
header in its HTTP requests.
The optional *timeout* parameter specifies a timeout in seconds for
blocking operations like the connection attempt (if not specified, the
global default timeout setting will be used). This only works for HTTP,
HTTPS and FTP connections.
If *context* is specified, it must be a ssl.SSLContext instance describing
the various SSL options. See HTTPSConnection for more details.
The optional *cafile* and *capath* parameters specify a set of trusted CA
certificates for HTTPS requests. cafile should point to a single file
containing a bundle of CA certificates, whereas capath should point to a
directory of hashed certificate files. More information can be found in
ssl.SSLContext.load_verify_locations().
The *cadefault* parameter is ignored.
This function always returns an object which can work as a context
manager and has methods such as
* geturl() - return the URL of the resource retrieved, commonly used to
determine if a redirect was followed
* info() - return the meta-information of the page, such as headers, in the
form of an email.message_from_string() instance (see Quick Reference to
HTTP Headers)
* getcode() - return the HTTP status code of the response. Raises URLError
on errors.
For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse
object slightly modified. In addition to the three new methods above, the
msg attribute contains the same information as the reason attribute ---
the reason phrase returned by the server --- instead of the response
headers as it is specified in the documentation for HTTPResponse.
For FTP, file, and data URLs and requests explicitly handled by legacy
URLopener and FancyURLopener classes, this function returns a
urllib.response.addinfourl object.
Note that None may be returned if no handler handles the request (though
the default installed global OpenerDirector uses UnknownHandler to ensure
this never happens).
In addition, if proxy settings are detected (for example, when a *_proxy
environment variable like http_proxy is set), ProxyHandler is default
installed and makes sure the requests are handled through the proxy.
r NzJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.8/urllib/request.pyr0 � s2 < ��
�
c C s | a d S �N)rF )rK rL rL rM r1 � s c
C s: t | �\}}t�t| |����}|�� }|dkrN|sNtj�|�|fW 5 Q R � S |r^t|d�}n t j
dd�}|j }t �
|� |�� ||f} d}
d} d} d}
d|kr�t|d �} |r�||
|
| � |�|
�}|s�q�| t|�7 } |�|� |
d
7 }
|r�||
|
| � q�W 5 Q R X W 5 Q R X | dk�r6| | k �r6td | | f | ��| S ) aW
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
�file�wbF)�delete� ���r �content-length�Content-Length� �1retrieval incomplete: got only %i out of %i bytes)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typer\ �fp�headers�tfp�result�bs�sizerc �blocknum�blockrL rL rM r6 � sH
"��c C sD t D ](} zt�| � W q tk
r* Y qX qt dd�= tr@dadS )z0Clean up temporary files from urlretrieve calls.N)r` r[ �unlink�OSErrorrF )Z temp_filerL rL rM r7 $ s
z:\d+$c C s< | j }t|�d }|dkr&| �dd�}t�d|d�}|�� S )z�Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
rV � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host3 s r{ c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sl || _ i | _i | _d | _|| _d | _|�� D ]\}}| �||� q,|d krRt| �}|| _ || _
|rh|| _ d S rN ) rt ri �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerr{ �origin_req_host� unverifiable�method) �selfrH rI ri r� r� r� �key�valuerL rL rM �__init__E s zRequest.__init__c C s | j rd�| j| j �S | jS )Nz{}#{})�fragment�format� _full_url�r� rL rL rM rt W s zRequest.full_urlc C s( t |�| _t| j�\| _| _| �� d S rN )r r� r r� �_parse�r� rH rL rL rM rt ] s
c C s d | _ d | _d| _d S )Nrr )r� r� �selectorr� rL rL rM rt d s c C s | j S rN )r} r� rL rL rM rI j s z Request.datac C s( || j kr$|| _ | �d�r$| �d� d S )N�Content-length)r} �
has_header�
remove_header)r� rI rL rL rM rI n s
c C s
d | _ d S rN )rI r� rL rL rM rI x s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rt r rz r� r
)r� �restrL rL rM r� | s
zRequest._parsec C s | j dk rdnd}t| d|�S )z3Return a string indicating the HTTP request method.N�POST�GETr� )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S rN )rt r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s2 | j dkr| js| j| _n|| _ | j| _|| _d S )N�https)r� r~ rz rt r� )r� rz r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS rN )r� rt r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |�� < d S rN )ri �
capitalize�r� r� �valrL rL rM r� � s zRequest.add_headerc C s || j |�� < d S rN )r| r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS rN )ri r| �r� � header_namerL rL rM r� � s
�zRequest.has_headerc C s | j �|| j�||��S rN )ri �getr| )r� r� �defaultrL rL rM ru � s �zRequest.get_headerc C s | j �|d � | j�|d � d S rN )ri �popr| r� rL rL rM r� � s zRequest.remove_headerc C s | j | j�}t|�� �S rN )r| ri �listr )r� �hdrsrL rL rM � header_items� s zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrt �setter�deleterrI r� r� r� r� r� r� r� r� ru r� r� rL rL rL rM r C s8 �
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )N�Python-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sT t |d�stdt|� ��d}t|�D �]}|dkr6q&|�d�}|d |� }||d d � }|�d�r�|�d�| d }||d d � }z t|�}W n tk
r� Y nX | j� |i �} | | j|< n>|dkr�|}| j
} n*|d kr�|}| j } n|d
kr&|}| j } nq&| �
|g �}
|
�r"t�|
|� n
|
�|� d }q&|�rPt�| j|� |�| � d S ) N�
add_parentz%expected BaseHandler instance, got %rF)�redirect_request�do_open�
proxy_open�_rV �errorrG �responsery T)�hasattr� TypeErrorr� �dir�find�
startswithrb rB r� r� r� r� r� �
setdefault�bisectZinsortra r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sL
�
zOpenerDirector.add_handlerc C s d S rN rL r� rL rL rM �close� s zOpenerDirector.closec G s< |� |d�}|D ]&}t||�}||� }|d k r| S qd S )NrL )r� r� ) r� �chainr� � meth_name�argsr� r� �funcrk rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }| j�|g �D ]}t||�}||�}qJt �
d|j |j|j |�
� � | �||�} |d }| j�|g �D ]}t||�}||| �} q�| S )NZ_requestzurllib.RequestZ _response)�
isinstance�strr rI rJ r� r� r� r� �sys�auditrt ri r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s$
zOpenerDirector.openc C sP | � | jdd|�}|r|S |j}| � | j||d |�}|r>|S | � | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rk r� rL rL rM r� s$
� ��
�zOpenerDirector._openc G s~ |dkr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S )
N��httpr� r� r: z
http_error_%srV Z_errorr r� �http_error_default)r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrk rL rL rM r� & s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|�
t� t� }|D ]B}| D ]8}t|t�rht||�r||�|� qDt||�rD|�|� qDq<|D ]}|�|� q�|D ]}|�|� � q�| D ] }t|t�r�|� }|�|� q�|S )a* Create an opener object from a list of handlers.
The opener will use several default handlers, including support
for HTTP, FTP and when applicable HTTPS.
If any of the handlers passed as arguments are subclasses of the
default handlers, the default handlers will not be used.
�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientra rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 ? s8 �
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r �� c C s
|| _ d S rN )�parent)r� r� rL rL rM r� f s zBaseHandler.add_parentc C s d S rN rL r� rL rL rM r� i s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__m s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r c s c @ s e Zd ZdZdZdd� ZeZdS )r/ z Process HTTP error responses.i� c C sH |j |j|�� }}}d| kr,dk sDn | j�d|||||�}|S )N�� �, r� )�code�msgrZ r� r� )r� ry r� r� r� r� rL rL rM �
http_responsez s �z HTTPErrorProcessor.http_responseN)r� r� r� �__doc__r� r� �https_responserL rL rL rM r/ v s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S rN )r rt )r� r� rh r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c st |� � }|dkr|dks:|dkr(|dks:t|j||||��|�dd�}d� � fdd �|j�� D �}t|||jd
d �S ) a� Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
)�- �. �/ i3 )r� ZHEAD)r� r� r� r� � z%20)rT z content-typec s" i | ]\}}|� � � kr||�qS rL )rx ��.0�k�v�ZCONTENT_HEADERSrL rM �
<dictcomp>� s � z8HTTPRedirectHandler.redirect_request.<locals>.<dictcomp>T)ri r� r� )r� r rt �replaceri r r r� ) r� r� rh r� r� ri �newurl�mZ
newheadersrL r rM r� � s
�� �z$HTTPRedirectHandler.redirect_requestc
C sL d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|jsn|jrnt|�}d|d< t|�}t|dtj d�}t
|j |�}| � ||||||�}|d kr�d S t
|d ��r|j } |_| �|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| �|d
�d | |< |�� |�� | jj||jd �S )
N�location�uri�r� r� �ftprr z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rV �rJ )r �schemer r\ Znetlocr� r r �stringZ punctuationr rt r� r� r
r� � max_repeatsrd �max_redirections�inf_msgrc r� r� rG rJ )
r� r� rh r� r� ri r �urlparts�newZvisitedrL rL rM �http_error_302� sT
� � � �z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r �http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c
C s� t | �\}}|�d�s d}| }nZ|�d�s6td| ��d|krV|�d�}|�d|�}n |�dd�}|dkrnd}|d|� }t|�\}}|dk r�t|�\}} nd }} ||| |fS )a Return (scheme, user, password, host/port) given a URL or an authority.
If a URL is supplied, it must have an authority (host:port) component.
According to RFC 3986, having an authority component means the URL must
have two slashes after the scheme.
r
N�//z proxy URL with no authority: %r�@r: rS )r r� rB r� r r )
�proxyr Zr_scheme� authorityZhost_separator�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s$
r" c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C sb |d krt � }t|d�s td��|| _|�� D ].\}}|�� }t| d| ||| jfdd�� q.d S )N�keys�proxies must be a mappingz%s_openc S s || ||�S rN rL )�rr r� r� rL rL rM �<lambda>) s z'ProxyHandler.__init__.<locals>.<lambda>)r5 r� �AssertionError�proxiesr rx �setattrr� )r� r) r� rH rL rL rM r� ! s
�zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } t�| �� ��d�}
|� dd|
� t|�}|�
||� ||ks�|dkr�d S | j j ||j
d�S d S )N�%s:%s�ascii�Proxy-authorization�Basic r� r )r� r" rz � proxy_bypassr
�base64� b64encode�encode�decoder� r� r� rG rJ ) r� r� r r� Z orig_typeZ
proxy_typer r! r Z user_passZcredsrL rL rM r� , s" � zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S rN )�passwdr� rL rL rM r� J s zHTTPPasswordMgr.__init__c s\ t |t�r|g}|�jkr$i �j|< dD ].� t� �fdd�|D ��}||f�j| |< q(d S )N�TFc 3 s | ]}�� |� �V qd S rN )�
reduce_uri)r� �u�� default_portr� rL rM � <genexpr>T s z/HTTPPasswordMgr.add_password.<locals>.<genexpr>)r� r� r4 �tuple)r� �realmr r r4 � reduced_urirL r8 rM � add_passwordM s
�z HTTPPasswordMgr.add_passwordc C s` | j �|i �}dD ]H}| �||�}|�� D ].\}}|D ] }| �||�r6| S q6q*qdS )Nr5 �NN)r4 r� r6 r � is_suburi) r� r< �authuriZdomainsr9 �reduced_authuriZurisZauthinfor rL rL rM �find_user_passwordX s z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d}|}d}t|�\}}|r~|dkr~|dk r~ddd��|�} | dk r~d || f }||fS )
z@Accept authority or URI and extract only the authority and path.rV r r: r
N�P i� r� z%s:%d)r r
r� )
r� r r9 �partsr r r\ rz �portZdportrL rL rM r6 b s$ �� zHTTPPasswordMgr.reduce_uric C sN ||kr dS |d |d kr dS |d }|dd� dkr@|d7 }|d � |�S )zcCheck if test is below base in a URI tree
Both args must be URIs in reduced form.
Tr FrV rS Nr
)r� )r� �base�test�prefixrL rL rM r@ y s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r> rC r6 r@ rL rL rL rM r H s
c @ s e Zd Zdd� ZdS )r! c C s0 t �| ||�\}}|d k r"||fS t �| d |�S rN )r rC )r� r< rA r r! rL rL rM rC � s �z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� rC rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S rN )�
authenticated�superr� �r� r� �kwargs�� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | � ||� |d k r&t� �d |||� t� �||||� d S rN )�update_authenticatedrK r> )r� r< r r r4 �is_authenticatedrN rL rM r> � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C s> t |t�r|g}dD ]$}|D ]}| �||�}|| j|< q qd S �Nr5 )r� r� r6 rJ )r� r rQ r9 r7 r= rL rL rM rP � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD dD ]:}| � ||�}| jD ]"}| �||�r| j| S qqd S rR )r6 rJ r@ )r� rA r9 rB r rL rL rM rQ � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r> rP rQ �
__classcell__rL rL rN rM r" � s
c @ sT e Zd Ze�dej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S rN )r r4 r> )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c sp d}t j�|�D ]6}|�� \}}}|dkr8t�dtd� ||fV d}q|sl|r^|�� d }nd}|d fV d S )NF)�"�'z Basic Auth Realm was unquoted� Tr rr )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r< rL rL rM � _parse_realm� s �
z%AbstractBasicAuthHandler._parse_realmc C s~ |� |�}|sd S d }|D ]H}| �|�D ]8\}}|�� dkrB|}q(|d k r(| �|||� S q(q|d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allr] rx �retry_http_basic_authrB ) r� �authreqrz r� ri Z unsupportedr\ r r< rL rL rM �http_error_auth_reqed� s
�z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j �||�\}}|d k rtd||f }dt�|�� ��d� }|�| jd �|krTd S |�| j|� | j j
||j d�S d S d S )Nr+ r. r, r ) r4 rC r0 r1 r2 r3 ru � auth_headerr� r� rG rJ )r� rz r� r< r �pw�raw�authrL rL rM r_ � s z.AbstractBasicAuthHandler.retry_http_basic_authc C st t | jd�r| j�|j�s |S |�d�sp| j�d |j�\}}d�||��� }t� |��
� }|� dd�|� � �� |S )NrQ �
Authorizationz{0}:{1}zBasic {})
r� r4 rQ rt r� rC r� r2 r0 Zstandard_b64encoder3 r� �strip)r� r� r r4 Z credentialsZauth_strrL rL rM � http_request s �
�z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j kr"dk r8n n| j�|jd� n| j�|jd� |S )NrQ r� r� TF)r� r4 r� rP rt )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�IrW r� r] ra r_ rh r� �
https_requestr� rL rL rL rM r# � s �
c @ s e Zd ZdZdd� ZdS )r$ rf c C s |j }| �d|||�}|S )N�www-authenticate)rt ra )r� r� rh r� r� ri rH r� rL rL rM �http_error_401$ s �z#HTTPBasicAuthHandler.http_error_401N)r� r� r� rb rn rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% r- c C s |j }| �d|||�}|S �N�proxy-authenticate)rz ra )r� r� rh r� r� ri r r� rL rL rM �http_error_407/ s �z$ProxyBasicAuthHandler.http_error_407N)r� r� r� rb rq rL rL rL rM r% + s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S �Nr )r r4 r> �retried� nonce_count�
last_nonce)r� r4 rL rL rM r� I s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S rr )rs r� rL rL rM �reset_retry_countR s z+AbstractDigestAuthHandler.reset_retry_countc C s| |� |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|�� d }|�� dkr`| �||�S |�� dkrxtd| ��d S ) N� i� zdigest auth failedrV r Zdigestr^ zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rs r rt r[ rx �retry_http_digest_authrB )r� rb rz r� ri r` r rL rL rM ra U s
� �z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |� dd�\}}ttd t|���}| �||�}|rvd| }|j�| jd �|krRd S |�| j|� | j j
||j d�}|S d S )Nr� rV z Digest %sr ) r[ �parse_keqv_list�filter�parse_http_list�get_authorizationri r� rb r� r� rG rJ )r� r� re �tokenZ challenge�chalZauth_valZresprL rL rM rx i s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |t�� f }|�d�td� }t�|��� }|d d� S )Nz %s:%s:%s:r, � � )rt �time�ctimer2 � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceu s z$AbstractDigestAuthHandler.get_cnoncec C s� z6|d }|d }|� d�}|� dd�}|� dd �}W n tk
rL Y d S X | �|�\}} |d krhd S | j�||j�\}
} |
d kr�d S |jd k r�| �|j|�} nd } d|
|| f }
d|�� |j f }|d kr�| ||
�d|||�f �}n~d |�
d
�k�r\|| j k�r| j d 7 _ n d | _ || _ d | j }| �
|�}d
|||d ||�f }| ||
�|�}n td| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr< r� �qop� algorithm�MD5�opaquez%s:%s:%sr+ re �,rV z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr4 rC rt rI �get_entity_digestr� r� r[ ru rt r� r )r� r� r~ r< r� r� r� r� �H�KDr rc ZentdigZA1ZA2ZrespdigZncvalueZcnonceZnoncebitrG rL rL rM r| � s\
�
�� z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nr� c S s t �| �d���� S �Nr, )r� Zmd5r2 r� ��xrL rL rM r' � � z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t �| �d���� S r� )r� r� r2 r� r� rL rL rM r' � r� z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nr+ rL )r� �d�r� rL rM r' � r� )rB )r� r� r� rL r� rM r� � s
� z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S rN rL )r� rI r~ rL rL rM r� � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� rv ra rx r� r| r� r� rL rL rL rM r& > s
>
c @ s e Zd ZdZdZdZdd� ZdS )r' z�An authentication protocol defined by RFC 2069
Digest authentication improves on basic authentication because it
does not transmit passwords in the clear.
rf �� c C s* t |j�d }| �d|||�}| �� |S )NrV rm )r rt ra rv �r� r� rh r� r� ri rz �retryrL rL rM rn � s �z$HTTPDigestAuthHandler.http_error_401N)r� r� r� r� rb r� rn rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( �Proxy-Authorizationr� c C s" |j }| �d|||�}| �� |S ro )rz ra rv r� rL rL rM rq � s �z%ProxyDigestAuthHandler.http_error_407N)r� r� r� rb r� rq rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S rN �� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S rN r� )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jj�|j|�� �S rN )r� r� �HTTPConnection�_get_content_lengthrI r� �r� ry rL rL rM r� � s �z'AbstractHTTPHandler._get_content_lengthc C s |j }|std��|jd k r�|j}t|t�r8d}t|��|�d�sN|�dd� |�d�s�|�d�s�| �|�}|d k r�|�dt|�� n |�dd� |}|� � r�t
|j �\}}t |�\}} |�d�s�|�d|� | j
jD ]&\}
} |
�� }
|�|
�s�|�|
| � q�|S ) N�
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-type�!application/x-www-form-urlencodedr� �Transfer-encodingZchunkedrs )rz r rI r� r� r� r� r� r� r� r r� r r� r� r� ) r� ry rz rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr_ r� rL rL rM � do_request_� sJ
�
�
� �
z AbstractHTTPHandler.do_request_c
sT |j }|std��||fd|ji|��}|�| j� t|j�� � �� fdd�|j� � D �� d� d< dd� � � � D �� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � z`z&|j |�
� |j|j� |�d
�d � W n, tk
�r } z t|��W 5 d }~X Y nX |�� } W n |�� � Y nX |j�r>|j�� d |_|�� | _| j| _| S )
z�Return an HTTPResponse object for the request, using http_class.
http_class must implement the HTTPConnection API from http.client.
r� rJ c s i | ]\}}|� kr||�qS rL rL r� �ri rL rM r / s � z/AbstractHTTPHandler.do_open.<locals>.<dictcomp>r� �
Connectionc S s i | ]\}}|� � |�qS rL )�title)r� r_ r� rL rL rM r < s r� r� r� )Zencode_chunkedN)rz r rJ Zset_debuglevelr� r� r| �updateri r r~ Z
set_tunnelry r� r� rI r� rq � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrz r� Ztunnel_headersZproxy_auth_hdr�errr& rL r� rM r� ! sB
�
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r� r� r� r� rL rL rL rM r� � s
&r� c @ s e Zd Zdd� ZejZdS )r) c C s | � tjj|�S rN )r� r� r� r� �r� r� rL rL rM � http_openf s zHTTPHandler.http_openN)r� r� r� r� r� r� rh rL rL rL rM r) d s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t �| |� || _|| _d S rN )r� r� �_context�_check_hostname)r� r� r> �check_hostnamerL rL rM r� o s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� r� rL rL rM �
https_opent s �zHTTPSHandler.https_open)r NN)r� r� r� r� r� r� r� rl rL rL rL rM rE m s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|j�� }|| _d S rr )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� } s
z HTTPCookieProcessor.__init__c C s | j �|� |S rN )r� Zadd_cookie_headerr� rL rL rM rh � s z HTTPCookieProcessor.http_requestc C s | j �||� |S rN )r� Zextract_cookies)r� ry r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� rh r� rl r� rL rL rL rM r | s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sN i }| D ]@}|� dd�\}}|d dkr@|d dkr@|dd� }|||< q|S )z>Parse list of key=value strings where keys are not duplicated.�=rV r rT rS )r[ )�lZparsedZeltr� r rL rL rM ry � s
ry c C s� g }d}d }}| D ]l}|r*||7 }d}q|rT|dkr>d}qn |dkrJd}||7 }q|dkrl|� |� d}q|dkrxd}||7 }q|r�|� |� dd� |D �S ) ap Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Neither commas nor quotes count if they are escaped.
Only double-quotes count, not single-quotes.
rr F�\TrT r� c S s g | ] }|� � �qS rL )rg )r� �partrL rL rM �
<listcomp>� s z#parse_http_list.<locals>.<listcomp>)ra )r� �resr� �escaper ZcurrL rL rM r{ � s4
r{ c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| �� krXtd��n
| �|�S d S )Nr: r rV r
� localhost�-file:// scheme is supported only on localhost)r� rz � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &�
zFileHandler.file_openNc C s` t jd krZz*tt�d�d t�t�� �d �t _W n$ tjk
rX t�d�ft _Y nX t jS )Nr� r: )r* �namesr; r� �gethostbyname_ex� gethostname�gaierror�
gethostbynamer� rL rL rM r� � s
��
zFileHandler.get_namesc
C s� dd l }dd l}|j}|j}t|�}z�t�|�}|j}|jj |j
dd�} |� |�d }
|� d|
pbd|| f �} |r~t
|�\}} |r�| s�t|�| �� kr�|r�d| | }
nd| }
tt|d�| |
�W S W n* tk
r� } z t|��W 5 d }~X Y nX td��d S ) Nr T�Zusegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
�
text/plain�file://�rbzfile not on local host)� email.utils� mimetypesrz r� r4 r[ �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rq r )r� r� �emailr� rz rf Z localfile�statsrm �modified�mtyperi rF Zorigurl�exprL rL rM r� � s:
�� ��zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s* z t �| �W S t jk
r$ Y d S X d S rN )r� r� r� )rz rL rL rM r� � s r� c @ s e Zd Zdd� Zdd� ZdS )r+ c
C s* dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}zt
� |�}W n* t k
r� } z t|��W 5 d }~X Y nX t
|j�\} }
| �d�} ttt | ��} | d d� | d } } | �r| d �s| dd � } z�| �||||| |j�}
| �r6d�p8d}|
D ]2}t|�\}}|�� d k�r>|d
k�r>|�� }�q>|
�| |�\}}d}|�|j�d }|�r�|d | 7 }|d k �r�|dk�r�|d | 7 }t�|�}t |||j�W S |j k
�r$ } z"td
| �}|� t � � d ��W 5 d }~X Y nX d S )Nr �ftp error: no host givenrr r
rS rV rk �Dr� ��a�Ar� rk r� r� zContent-type: %s
zContent-length: %d
�
ftp error: %rr: )!�ftplibr� rz r r
�FTP_PORTrb r r r
r� r� rq r r� r[ r� �map� connect_ftprJ r rx �upper�retrfiler� rt r� r� r �
all_errors�with_tracebackr� �exc_info)r� r� r� r� rz rF r r4 r� r\ �attrs�dirsrO �fwr� �attrr� rh �retrlenri r� r� �excrL rL rM �ftp_open s^
�
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r4 rz rF r� rJ rL rL rM r� 7 s �zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< r� )�cacherJ �soonest�delay� max_connsr� rL rL rM r� > s
zCacheFTPHandler.__init__c C s
|| _ d S rN )r� )r� �trL rL rM �
setTimeoutE s zCacheFTPHandler.setTimeoutc C s
|| _ d S rN )r� )r� r rL rL rM � setMaxConnsH s zCacheFTPHandler.setMaxConnsc C sr |||d� |�|f}|| jkr4t�� | j | j|< n,t||||||�| j|< t�� | j | j|< | �� | j| S )Nr
)�joinr� r� r� rJ r� � check_cache)r� r r4 rz rF r� rJ r� rL rL rM r� K s
�
zCacheFTPHandler.connect_ftpc C s� t � � }| j|krPt| j�� �D ].\}}||k r | j| �� | j|= | j|= q tt| j�� ��| _t | j�| j
kr�t| j�� �D ]&\}}|| jkr�| j|= | j|= q�q�tt| j�� ��| _d S rN ) r� r� r� rJ r r� r� �min�valuesrd r� )r� r� r� r rL rL rM r V s
zCacheFTPHandler.check_cachec C s0 | j �� D ] }|�� q
| j �� | j�� d S rN )r� r r� �clearrJ )r� �connrL rL rM � clear_cachej s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r r rL rL rL rM r, ; s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|�dd�\}}|�dd�\}}t|�}|�d�rNt�|�}|d d� }|sVd}t�d|t|�f �}t t
� |�||�S )N�:rV r� z;base64i�����text/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
) rt r[ r �endswithr0 � decodebytesr� r� rd r �io�BytesIO)r� r� rH r rI Z mediatyperi rL rL rM � data_openq s
�zDataHandler.data_openN)r� r� r� r rL rL rL rM r- p s r� �nt)r4 r3 c C s t | �S )zOS-specific conversion from a relative URL of the 'file' scheme
to a file system path; not recommended for general use.)r
��pathnamerL rL rM r4 � s c C s t | �S )zOS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use.)r r rL rL rM r3 � s c @ s� e Zd ZdZdZde Zd*dd�Zdd� Zdd � Z d
d � Z
d d
� Z d+dd�Z d,dd�Z
d-dd�Zd.dd�Zdd� Zd/dd�Zd0dd�Zd d � Zer�d d � Zd1d d!�Zd"d#� Zd$d%� Zd&d'� Zd2d(d)�ZdS )3r8 a, Class to open URLs.
This is a class rather than just a subroutine because we may need
more than one set of global protocol-specific options.
Note -- this is a base class for those who don't want the
automatic handling of errors type 302 (relocated) and 401
(authorization needed).Nr� c K s� dd| j ji }tj|tdd� |d kr.t� }t|d�s@td��|| _|� d�| _
|� d�| _ d | j fd
g| _
g | _tj| _d | _t| _d S ) NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classrV )�
stacklevelr$ r% �key_file� cert_filez
User-Agent)ZAcceptz*/*)rO r� r? r@ rA r5 r� r( r) r� r r �versionr� �_URLopener__tempfilesr[ rp �_URLopener__unlink� tempcache�ftpcache)r� r) Zx509r� rL rL rM r� � s
� zURLopener.__init__c C s | � � d S rN )r� r� rL rL rM �__del__� s zURLopener.__del__c C s | � � d S rN )�cleanupr� rL rL rM r� � s zURLopener.closec C sV | j rB| j D ](}z| �|� W q tk
r2 Y q X q | j d d �= | jrR| j�� d S rN )r r rq r r )r� rO rL rL rM r � s
zURLopener.cleanupc G s | j �|� dS )zdAdd a header to be used by the HTTP interface only
e.g. u.addheader('Accept', 'sound/basic')N)r� ra )r� r� rL rL rM � addheader� s zURLopener.addheaderc
C sp t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd}d| } || _ | �
dd�} t | | �r�| d kr�|r�| � |||�S | �
||�S z0|dk�r t| | �|�W S t| | �||�W S W nV ttfk
�r0 � Y n< tk
�rj }
z td
|
��t�� d ��W 5 d}
~
X Y nX dS ) z6Use URLopener().open(file) instead of open(file, 'r').z%/:=&?~#+!$,;'@()*[]|�r r� rO NZopen_�-r� r� z socket errorr: )r r r r rG r r r) r r� r r� �open_unknown_proxy� open_unknownr� r r rq r� r� r� )r� r� rI rf ri rh �urltyperH r � proxyhostrz r� r_ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��dS )�/Overridable interface to open unknown URL type.� url errorzunknown url typeN�r rq )r� r� rI r� rH rL rL rM r
s zURLopener.open_unknownc C s t |�\}}tdd| |��dS )r" r# zinvalid proxy for %sNr$ )r� r r� rI r� rH rL rL rM r s z URLopener.open_unknown_proxyc
C s t t|��}| jr&|| jkr&| j| S t|�\}}|dkr�|rF|dkr�z0| �|�}|�� }|�� tt|�d �|fW S t k
r� } zW 5 d} ~ X Y nX | �
||�}�z<|�� }
|r�t
|d�} nrt|�\} }
t|
p�d�\} }
t |
p�d�\}
} t |
p�d�\}
} t
j�|
�d }t�|�\}}| j�|� t
�|d�} z�||
f}| jdk �rT|| j|< d}d}d}d}d |
k�rzt|
d
�}|�r�||||� |�|�}|�s��q�|t|�7 }| �|� |d7 }|�r�||||� �q�W 5 | �� X W 5 |�� X |dk�r||k �rtd ||f |��|S ) ztretrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object.NrO rV rP rr rR rS r rT rU rW )r r r r r� rZ r� r4 r rq rG r r r[ r\ �splitextr^ Zmkstempr ra �fdopenrb rc rd re r )r� rH rf rg rI r� Zurl1rh r� r� ri rj Zgarbager\ �suffix�fdrk rl rm rc rn ro rL rL rM �retrieve sn
��zURLopener.retrievec C s$ d}d}t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d}| �� dkrvd}n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t �
|� � �� d�} nd} |�rt|�}t �
|� � �� d�} nd} ||�}
i }| �r*d| |d< | �r<d| |d < |�rJ||d
< d |d < | j
D ]\}}|||< �qX|dk �r�d
|d< |
�d|||� n|
jd||d� z |
�� }W n" tjjk
�r� td��Y nX d|j k�r�dk �rn nt||jd| |j�S | �||j|j|j|j|�S dS )a� Make an HTTP connection using connection_class.
This is an internal method that should be called from
open_http() or open_https().
Arguments:
- connection_factory should take a host name and return an
HTTPConnection instance.
- url is the url to retrieval or a host, relative-path pair.
- data is payload for a POST request or None.
Nr� z %s://%s%sz
http errorr� r, zBasic %sr� rf rs r� r� r� z Content-Typer� r� r� z$http protocol error: bad status liner� r� �http:)r� r� r r r
r rx r/ rq r0 r1 r2 r3 r� ry r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrh r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrz r� Zrealhostr r� Z
proxy_authre Z http_connri r\ r� r� rL rL rM �_open_generic_httpV s~
� �z URLopener._open_generic_httpc C s | � tjj||�S )zUse HTTP protocol.)r, r� r� r� �r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|dkr6||||||�} n|||||||�} | rP| S | �|||||�S )z�Handle http errors.
Derived class can override this, or provide specific handlers
named http_error_DDD where DDD is the 3-digit error code.z
http_error_%dN)r� r� r� )
r� rH rh �errcode�errmsgri rI r_ r� rk rL rL rM r+ � s
zURLopener.http_errorc C s |� � t||||d��dS )z>Default error handler: close the connection and raise OSError.N)r� r �r� rH rh r/ r0 ri rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r r )r� r� r� r r )r� rz rL rL rM �_https_connection� s �zURLopener._https_connectionc C s | � | j||�S )zUse HTTPS protocol.)r, r2 r- rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|dd� dkrP|dd� dkrP|dd� �� dkrPtd ��n
| �|�S dS )
z/Use local file or FTP depending on form of URL.zEfile error: proxy support for file protocol currently not implementedNr: r rV r
� z
localhost/r� )r� r� r rx rB r� r� rL rL rM � open_file� s
4
zURLopener.open_filec
C s\ ddl }ddl}t|�\}}t|�}zt�|�}W n0 tk
rb } zt|j|j ��W 5 d}~X Y nX |j
} |j j |j
dd�}
|�|�d } |�d| p�d| |
f �} |s�|}
|dd� dkr�d | }
tt|d
�| |
�S t|�\}}|�sPt�|�t� ft� k�rP|}
|dd� dk�r d | }
n |dd � d k�r>td
| ��tt|d
�| |
�S td��dS )zUse local file.r NTr� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
r� rV r
r� r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 r[ r� rq r �strerrorrf r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rz rO Z localnamer� �erm r� r� ri ZurlfilerF rL rL rM r� � s@ �� �
zURLopener.open_local_filec
C s� t |t�std��ddl}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd}t|�}t|ppd�}t|p|d�}t �
|�}|s�ddl }|j }nt
|�}t|�\}} t|�}|�d�}
|
dd� |
d }
} |
r�|
d s�|
dd� }
|
�r
|
d �s
d|
d< |||d�|
�f} t| j�tk�rbt| j�D ]*}
|
| k�r6| j|
}| j|
= |�� �q6z�| | jk�r�t|||||
�| j| < | �s�d }nd
}| D ]2}t|�\}}|�� d k�r�|d k�r�|�� }�q�| j| �| |�\}}|�d
| �d }d}|�r |d| 7 }|dk �r,|dk�r,|d| 7 }t � |�}t ||d
| �W S t � k
�r� } z td| �� t!�"� d ��W 5 d}~X Y nX dS )zUse FTP protocol.zCftp error: proxy support for ftp protocol currently not implementedr Nr� rr r
rS rV r� rk r� r� zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: )#r� r� r r� r r
r r r
r� r� r� r� rb r r[ r� rd r � MAXFTPCACHEr� r� r� r rx r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rz r\ rF r r4 r� r� r� rO r� r� r r� r� r� rh r� r� ri r� rL rL rM �open_ftp� st
� �
zURLopener.open_ftpc
C s< t |t�std��z|�dd�\}}W n tk
rD tdd��Y nX |sNd}|�d�}|dkr�d ||d
� kr�||d d
� }|d
|� }nd }g }|�d t� d
t�
t�� �� � |�d| � |dkr�t � |�
d���d�}nt|�}|�dt|� � |�d � |�|� d�|�}t�|�}t�|�}t|||�S )zUse "data" URL.zEdata error: proxy support for data protocol currently not implementedr� rV z
data errorz bad data URLr �;r r� Nrr zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr0 r, zlatin-1zContent-Length: %d�
)r� r� r r[ rB rq �rfindra r� �strftime�gmtimer0 r r2 r3 r
rd r� r� r� r
�StringIOr ) r� rH rI r� Zsemir r� ri �frL rL rM � open_data8 s8
�
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r� r r� r r� r r� r r rG r r r) r, r. r+ r� rC r2 r3 r5 r� r; rC rL rL rL rM r8 � s.
$
A\
:c @ s� e Zd ZdZdd� Zdd� Zd#dd�Zd d
� Zd$d d �Zd%d
d�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd�Zd,d d �Zd-d d �Zd!d"� ZdS ).r9 z?Derived class with handlers for errors we can handle (perhaps).c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtriesrL rL rL rM r� e s zFancyURLopener.__init__c C s t ||d| |�S )z3Default error handling -- don't raise an exception.r* )r r1 rL rL rM r� k s z!FancyURLopener.http_error_defaultNc C sv | j d7 _ zZ| jrN| j | jkrNt| d�r4| j}n| j}|||dd|�W � S | �||||||�}|W �S d| _ X dS )z%Error 302 -- relocated (temporarily).rV r �http_error_500r� z)Internal Server Error: Redirect RecursionN)rE rF r� rG r� �redirect_internal) r� rH rh r/ r0 ri rI r� rk rL rL rM r o s
� �z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |� � t| jd | |�}t|�}|jdkrnt|||d| ||��| �|�S )Nr r r r z( Redirection to url '%s' is not allowed.)r� r r� r r r rG ) r� rH rh r/ r0 ri rI r r rL rL rM rH � s"
� �z FancyURLopener.redirect_internalc C s | � ||||||�S )z*Error 301 -- also relocated (permanently).�r �r� rH rh r/ r0 ri rI rL rL rM r � s z FancyURLopener.http_error_301c C s | � ||||||�S )z;Error 303 -- also relocated (essentially identical to 302).rI rJ rL rL rM r � s z FancyURLopener.http_error_303c C s2 |dkr | � ||||||�S | �|||||�S dS )z1Error 307 -- relocated, but turn POST into error.N)r r� rJ rL rL rM r � s z FancyURLopener.http_error_307Fc
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )z_Error 401 -- authentication required.
This function supports Basic authentication only.rm �![ ]*([^ ]+)[ ]+realm="([^"]*)"r^ Zretry_� _basic_authN�r8 r� ri �matchrY rx r� r� �
r� rH rh r/ r0 ri rI r� ZstuffrN r r< r_ rL rL rM rn � s:
�
�
��z FancyURLopener.http_error_401c
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )zeError 407 -- proxy authentication required.
This function supports Basic authentication only.rp rK r^ Z retry_proxy_rL NrM rO rL rL rM rq � s:
�
�
��z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�http://r� r rV �%s:%s@%srr r �r r) r r� �get_user_passwdr rG �r� rH r< rI rz r� r r r r! Z
proxyselectorr� r r4 rL rL rM �retry_proxy_http_basic_auth� s$
�
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�https://r� r rV rQ rr r rR rT rL rL rM � retry_proxy_https_basic_auth� s$
�
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rQ rr r rP �r r� rS r rG �
r� rH r< rI rz r� r� r r4 r rL rL rM r_ s
�
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rQ rr r rV rX rY rL rL rM �retry_https_basic_auth s
�
z%FancyURLopener.retry_https_basic_authr c C s` |d |� � }|| jkr2|r(| j|= n
| j| S | �||�\}}|sJ|rX||f| j|< ||fS )Nr )rx rD �prompt_user_passwd)r� rz r< r r� r r4 rL rL rM rS s
z FancyURLopener.get_user_passwdc C sX ddl }z.td||f �}|� d|||f �}||fW S tk
rR t� Y dS X dS )z#Override this in a GUI environment!r Nz Enter username for %s at %s: z#Enter password for %s in %s at %s: r? )�getpass�input�KeyboardInterrupt�print)r� rz r< r\ r r4 rL rL rM r[ ) s �
z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r� r rH r r r rn rq rU rW r_ rZ rS r[ rL rL rL rM r9 b s(
�
�
c C s t dkrt�d�a t S )z8Return the IP address of the magic hostname 'localhost'.Nr� )�
_localhostr� r� rL rL rL rM r� 9 s
r� c C sP t dkrLztt�t�� �d �a W n( tjk
rJ tt�d�d �a Y nX t S )z,Return the IP addresses of the current host.Nr: r� )� _thishostr; r� r� r� r� rL rL rL rM r7 A s r7 c C s t dkrddl} | ja t S )z1Return the set of errors raised by the FTP class.Nr )�
_ftperrorsr� r� )r� rL rL rM r: L s r: c C s t dkrt�d�a t S )z%Return an empty email Message object.Nrr )�
_noheadersr� r� rL rL rL rM � noheadersU s
rd c @ sJ e Zd ZdZddd�Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r� z;Class used by open_ftp() for cache of open FTP connections.NTc C sX || _ || _|| _|| _|| _|| _d| _|| _z | �� W n | � � � Y nX d S rr )
r r4 rz rF r� rJ �refcount� keepalive�initr� )r� r r4 rz rF r� rJ r� rL rL rM r� b s zftpwrapper.__init__c C s\ dd l }d| _|�� | _| j�| j| j| j� | j�| j | j
� d� | j �}| j�
|� d S )Nr r
)r� �busyZFTPr Zconnectrz rF rJ Zloginr r4 r� r� �cwd)r� r� Z_targetrL rL rM rg r s
zftpwrapper.initc
C s� dd l }| �� |dkr"d}d}n d| }d}z| j�|� W n* |jk
rh | �� | j�|� Y nX d }|r�|s�z d| }| j�|�\}}W nR |jk
r� } z2t|�d d� dkr�t d | ��
t � � d
��W 5 d }~X Y nX |�s�| j�d� |�rl| j�
� } zJz| j�|� W n4 |jk
�rN } zt d | �|�W 5 d }~X Y nX W 5 | j�| � X d | }nd }| j�|�\}}d| _t|�d
�| j�}
| jd7 _|�� |
|fS )Nr )r� r� zTYPE ArV zTYPE zRETR rV Z550r� r: zLIST ZLISTr� )r� � endtransferr Zvoidcmdr� rg Z ntransfercmdZ
error_permr� r r� r� r� �pwdri rh r Zmakefile�
file_closere r� ) r� rO r� r� �cmd�isdirr r� r� rk ZftpobjrL rL rM r� { sP
�
$
zftpwrapper.retrfilec C s
d| _ d S rr )rh r� rL rL rM rj � s zftpwrapper.endtransferc C s d| _ | jdkr| �� d S )NFr )rf re �
real_closer� rL rL rM r� � s
zftpwrapper.closec C s2 | � � | jd8 _| jdkr.| js.| �� d S )NrV r )rj re rf ro r� rL rL rM rl � s zftpwrapper.file_closec C s2 | � � z| j�� W n t� k
r, Y nX d S rN )rj r r� r: r� rL rL rM ro � s
zftpwrapper.real_close)NT) r� r� r� r� r� rg r� rj r� rl ro rL rL rL rM r� _ s �
-r� c C s� i } t j�� D ]4\}}|�� }|r|dd� dkr|| |dd� < qdt jkrZ| �dd� t j�� D ]J\}}|dd� dkrd|�� }|r�|| |dd� < qd| �|dd� d� qd| S )a Return a dictionary of scheme -> proxy server URL mappings.
Scan the environment for variables named <scheme>_proxy;
this seems to be the standard convention. If you need a
different way, you can pass a proxies dictionary to the
[Fancy]URLopener constructor.
i����N�_proxyZREQUEST_METHODr� )r[ �environr rx r� )r) r_ r� rL rL rM �getproxies_environment� s
rr c C s� |dkrt � }z |d }W n tk
r0 Y dS X |dkr>dS | �� } t| �\}}|�d�D ]Z}|�� }|r\|�d�}|�� }||ks�| |kr� dS d| }|�|�s�| �|�r\ dS q\dS )z�Test if proxies should not be used for a particular host.
Checks the proxy dict for the value of no_proxy, which should
be a list of comma separated DNS suffixes, or '*' for all hosts.
NZnoF�*Tr� �.)rr r� rx r
r[ rg �lstripr )rz r) Zno_proxy�hostonlyrF r_ rL rL rM �proxy_bypass_environment� s*
rw c C s0 ddl m } t| �\}}dd� }d| kr4|d r4dS d}|�d d
�D ]�}|sNqDt�d |�}|dk �r|dkr�zt�|�}||�}W n tk
r� Y qDY nX ||�d ��} |�d
�}
|
dkr�d|�d �� d�d }
nt
|
d d� �}
|
dk sD|
dkr�qDd|
}
||
? | |
? k�r* dS qD|| |�rD dS qDdS )aj
Return True iff this host shouldn't be accessed using a proxy
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
{ 'exclude_simple': bool,
'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
}
r )�fnmatchc S sh | � d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nrt r� r � rV r� r: r rV )r[ r� r� rb rd )ZipAddrrE rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numrt Zexclude_simpleTN�
exceptionsrL z(\d+(?:\.\d+)*)(/\d+)?rV r: r � F) rx r
r� ri rN r� r� rq �group�countrb ) rz �proxy_settingsrx rv rF rz ZhostIPr� r rG �maskrL rL rM � _proxy_bypass_macosx_sysconf
s>
r� �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S rN )r� r� )rz r rL rL rM �proxy_bypass_macosx_sysconfF
s r� c C s t � S )z�Return a dictionary of scheme -> proxy server URL mappings.
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
)r� rL rL rL rM �getproxies_macosx_sysconfJ
s r� c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or from the MacOSX framework SystemConfiguration.
N)rr rw r� �rz r) rL rL rM r/ T
s
r/ c C s t � p
t� S rN )rr r� rL rL rL rM r5 a
s c
C s i } z ddl }W n tk
r( | Y S X z�|�|jd�}|�|d�d }|r�t|�|d�d �}d|kr�|�d�D ]4}|�dd�\}}t�d |�s�d
||f }|| |< qtn>|dd � d kr�|| d
< n$d| | d
< d| | d< d| | d< |� � W n t
t t fk
�r Y nX | S )zxReturn a dictionary of scheme -> proxy server URL mappings.
Win32 uses the registry to store proxies.
r N�;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r< rV z
(?:[^/:]+)://z%s://%srw r* r� z http://%sz
https://%sr� zftp://%sr )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� r[ ri rN ZCloserq rB r� )r) r� �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryf
sF
�����
r� c C s t � p
t� S )z�Return a dictionary of scheme -> proxy server URL mappings.
Returns settings gathered from the environment, if specified,
or the registry.
)rr r� rL rL rL rM r5 �
s c C s| z dd l }W n tk
r" Y dS X z6|�|jd�}|�|d�d }t|�|d�d �}W n tk
rp Y dS X |rz|s~dS t| �\}}|g} z t� |�}||kr�| �
|� W n tk
r� Y nX z t� |�}||kr�| �
|� W n tk
� r� Y nX |� d�}|D ]j} | dk�r*d|k�r* dS | �
dd �} | �
d
d �} | �
d d�} | D ] }
t�| |
tj��rR dS �qR�q dS )
Nr r� r� Z
ProxyOverrider< z<local>rt rV z\.rs z.*�?)r� r� r� r� r� r� rq r
r� r� ra Zgetfqdnr[ r ri rN rk ) rz r� r� r� Z
proxyOverrideZrawHostrF ZaddrZfqdnrH r� rL rL rM �proxy_bypass_registry�
s` �����
r� c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
N)rr rw r� r� rL rL rM r/ �
s
)NNN)N)~r� r0 r� r� r� Z http.clientr� r
r[ � posixpathri r� r r� r� r^ rX r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD r� rC �__all__� version_infor� rF r� r0 r1 r` r6 r7 rj �ASCIIrv r{ r r r2 r r/ r r r" r r r! r" r# r$ r% �urandomr� r& r' r( r� r) r� r� rE ra r r. ry r{ r* r� r+ r, r- r9 r_ Z
nturl2pathr4 r3 r r8 r9 r` r� ra r7 rb r: rc rd r� rr rw r� �platformZ_scproxyr� r� r� r� r/ r5 r� r� rL rL rL rM �<module> s SP
� � U
?m $q!+@
o v
+3:5! @ W
_
%A
- 2
PK *(�ZSC^��
�
__pycache__/error.cpython-38.pycnu �[��� U
e5dH
� @ sP d Z ddlZdddgZG dd� de�ZG dd� deejj�ZG dd� de�Z dS ) a� Exception classes raised by urllib.
The base exception class is URLError, which inherits from OSError. It
doesn't define any behavior of its own, but is the base class for all
exceptions defined in this package.
HTTPError is an exception class that is also a valid HTTP response
instance. It behaves this way because HTTP protocol errors are valid
responses, with a status code, headers, and a body. In some contexts,
an application may want to handle an exception like a regular
response.
� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S �N)�args�reason�filename)�selfr r � r
�$/usr/lib64/python3.8/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r �r r
r
r �__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r
r
r
r r s
c @ sX e Zd ZdZejjjZdd� Zdd� Z dd� Z
e dd � �Z e d
d � �Z
e
jd d � �Z
d
S )r zBRaised when HTTP error occurs, but also acts like non-error returnc C s: || _ || _|| _|| _|| _|d k r6| �||||� d S r )�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r
r
r r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s�r r r
r
r
r r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>r r
r
r
r �__repr__7 s zHTTPError.__repr__c C s | j S r )r r
r
r
r r < s zHTTPError.reasonc C s | j S r �r r
r
r
r �headers@ s zHTTPError.headersc C s
|| _ d S r r )r r r
r
r r D s N)r r r �__doc__�urllib�response�
addinfourlr r r r �propertyr r �setterr
r
r
r r # s
c @ s e Zd ZdZdd� ZdS )r zDException raised when downloaded size does not match content-length.c C s t �| |� || _d S r )r r �content)r �messager! r
r
r r K s z ContentTooShortError.__init__N)r r r r r r
r
r
r r I s )
r Zurllib.responser �__all__�OSErrorr r r r r r
r
r
r �<module> s
&PK *(�Z ��� � ) __pycache__/response.cpython-38.opt-1.pycnu �[��� U
e5d� � @ s^ d Z ddlZddddgZG dd� dej�ZG dd� de�ZG d d� de�ZG d
d� de�ZdS ) a Response classes used by urllib.
The base class, addbase, defines a minimal file-like interface,
including read() and readline(). The typical response object is an
addinfourl instance, which defines an info() method that returns
headers and a geturl() method that returns the url.
� N�addbase� addclosehook�addinfo�
addinfourlc s8 e Zd ZdZ� fdd�Zdd� Zdd� Zdd � Z� ZS )
r zOBase class for addinfo and addclosehook. Is a good idea for garbage collection.c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr �� __class__� �'/usr/lib64/python3.8/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file�r
r
r
r �__repr__ s �zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueErrorr r
r
r � __enter__ s zaddbase.__enter__c C s | � � d S �N)�close)r
�type�value� tracebackr
r
r �__exit__! s zaddbase.__exit__) r �
__module__� __qualname__�__doc__r r r r �
__classcell__r
r
r r r s
c s, e Zd ZdZ� fdd�Z� fdd�Z� ZS )r z*Class to add a close hook to an open file.c s t t| ��|� || _|| _d S r )r r r � closehook�hookargs)r
r r! r" r r
r r ( s zaddclosehook.__init__c s> z(| j}| j}|r&d | _d | _||� W 5 t t| ��� X d S r )r r r r! r" )r
r! r" r r
r r - s zaddclosehook.close)r r r r r r r r
r
r r r % s c s( e Zd ZdZ� fdd�Zdd� Z� ZS )r z.class to add an info() method to an open file.c s t t| ��|� || _d S r )r r r �headers)r
r r# r r
r r < s zaddinfo.__init__c C s | j S r )r# r r
r
r �info@ s z addinfo.info)r r r r r r$ r r
r
r r r 9 s c s2 e Zd ZdZd � fdd� Zdd� Zdd� Z� ZS )
r z9class to add info() and geturl() methods to an open file.Nc s" t t| ��||� || _|| _d S r )r r r �url�code)r
r r# r% r& r r
r r G s zaddinfourl.__init__c C s | j S r )r& r r
r
r �getcodeL s zaddinfourl.getcodec C s | j S r )r% r r
r
r �geturlO s zaddinfourl.geturl)N)r r r r r r' r( r r
r
r r r D s )r Ztempfile�__all__Z_TemporaryFileWrapperr r r r r
r
r
r �<module> s PK *(�Z ��� � # __pycache__/response.cpython-38.pycnu �[��� U
e5d� � @ s^ d Z ddlZddddgZG dd� dej�ZG dd� de�ZG d d� de�ZG d
d� de�ZdS ) a Response classes used by urllib.
The base class, addbase, defines a minimal file-like interface,
including read() and readline(). The typical response object is an
addinfourl instance, which defines an info() method that returns
headers and a geturl() method that returns the url.
� N�addbase� addclosehook�addinfo�
addinfourlc s8 e Zd ZdZ� fdd�Zdd� Zdd� Zdd � Z� ZS )
r zOBase class for addinfo and addclosehook. Is a good idea for garbage collection.c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr �� __class__� �'/usr/lib64/python3.8/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file�r
r
r
r �__repr__ s �zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueErrorr r
r
r � __enter__ s zaddbase.__enter__c C s | � � d S �N)�close)r
�type�value� tracebackr
r
r �__exit__! s zaddbase.__exit__) r �
__module__� __qualname__�__doc__r r r r �
__classcell__r
r
r r r s
c s, e Zd ZdZ� fdd�Z� fdd�Z� ZS )r z*Class to add a close hook to an open file.c s t t| ��|� || _|| _d S r )r r r � closehook�hookargs)r
r r! r" r r
r r ( s zaddclosehook.__init__c s> z(| j}| j}|r&d | _d | _||� W 5 t t| ��� X d S r )r r r r! r" )r
r! r" r r
r r - s zaddclosehook.close)r r r r r r r r
r
r r r % s c s( e Zd ZdZ� fdd�Zdd� Z� ZS )r z.class to add an info() method to an open file.c s t t| ��|� || _d S r )r r r �headers)r
r r# r r
r r < s zaddinfo.__init__c C s | j S r )r# r r
r
r �info@ s z addinfo.info)r r r r r r$ r r
r
r r r 9 s c s2 e Zd ZdZd � fdd� Zdd� Zdd� Z� ZS )
r z9class to add info() and geturl() methods to an open file.Nc s" t t| ��||� || _|| _d S r )r r r �url�code)r
r r# r% r& r r
r r G s zaddinfourl.__init__c C s | j S r )r& r r
r
r �getcodeL s zaddinfourl.getcodec C s | j S r )r% r r
r
r �geturlO s zaddinfourl.geturl)N)r r r r r r' r( r r
r
r r r D s )r Ztempfile�__all__Z_TemporaryFileWrapperr r r r r
r
r
r �<module> s PK *(�ZSC^��
�
& __pycache__/error.cpython-38.opt-1.pycnu �[��� U
e5dH
� @ sP d Z ddlZdddgZG dd� de�ZG dd� deejj�ZG dd� de�Z dS ) a� Exception classes raised by urllib.
The base exception class is URLError, which inherits from OSError. It
doesn't define any behavior of its own, but is the base class for all
exceptions defined in this package.
HTTPError is an exception class that is also a valid HTTP response
instance. It behaves this way because HTTP protocol errors are valid
responses, with a status code, headers, and a body. In some contexts,
an application may want to handle an exception like a regular
response.
� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S �N)�args�reason�filename)�selfr r � r
�$/usr/lib64/python3.8/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r �r r
r
r �__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r
r
r
r r s
c @ sX e Zd ZdZejjjZdd� Zdd� Z dd� Z
e dd � �Z e d
d � �Z
e
jd d � �Z
d
S )r zBRaised when HTTP error occurs, but also acts like non-error returnc C s: || _ || _|| _|| _|| _|d k r6| �||||� d S r )�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r
r
r r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s�r r r
r
r
r r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>r r
r
r
r �__repr__7 s zHTTPError.__repr__c C s | j S r )r r
r
r
r r < s zHTTPError.reasonc C s | j S r �r r
r
r
r �headers@ s zHTTPError.headersc C s
|| _ d S r r )r r r
r
r r D s N)r r r �__doc__�urllib�response�
addinfourlr r r r �propertyr r �setterr
r
r
r r # s
c @ s e Zd ZdZdd� ZdS )r zDException raised when downloaded size does not match content-length.c C s t �| |� || _d S r )r r �content)r �messager! r
r
r r K s z ContentTooShortError.__init__N)r r r r r r
r
r
r r I s )
r Zurllib.responser �__all__�OSErrorr r r r r r
r
r
r �<module> s
&PK *(�ZH� �� �� __pycache__/parse.cpython-38.pycnu �[��� U
&�.e�� � @ s� d Z ddlZddlZddlZddlZddlZddddddd d
d d d
ddddddddddgZddddd d d d d d!d"d#d$d%d&d'd(d)d*gZddddd d+d d d d"d d!d,d#d$d%d-d'd(d&d.d/d0d)d*gZddd1d#dd d d!d$d%d2d3d"d&d4gZ dd1d5d6d+d d d,d2d3g
Z
ddd d d d!d"dd$d%d2d3g Z ddd1ddd6d d d d!d,d d#g
Z d7Z
d8Zd9d:d;gZd<Zi Zd=d>� Zd?Zd@ZdAdB� ZeefdCdD�ZeefdEdF�ZdGdH� ZG dIdJ� dJe�ZG dKdL� dLe�ZG dMdN� dNe�Z G dOdP� dPe e�Z G dQdR� dRe e�Z ddSlm Z e ddT�Z e ddU�Z!e ddV�Z"dWe _ dXe j#_ dYe j$_ dZe!_ d[e!j%_ d\e!j&_ d]e!j'_ d^e!j(_ d_e!j$_ d`e"_ e!j%j e"j%_ e!j&j e"j&_ e!j'j e"j'_ dae"j)_ e!j(j e"j(_ e!j$j e"j$_ e Z*G dbd� de e�Z+G dcd� de!e �Z,G ddd� de"e �Z-G ded� de e�Z.G dfd� de!e �Z/G dgd� de"e �Z0dhdi� Z1e1� [1d�dkd�Z2dldm� Z3d�dndo�Z4dpdq� Z5drds� Z6d�dtd�Z7dud� Z8dvd� Z9d�dwd�Z:dxd� Z;dyZ<da=dzd� Z>e�?d{�Z@d�d~d�ZAd�d�d
�ZBG d�d�� d�eC�ZDd�ZEdaFd�d�d �ZGd�d�d�ZHeId��ZJeKeJ�ZLi ZMG d�d�� d�ejN�ZOd�d�d �ZPd�d�d
�ZQd�d�d�ZRddddeQfd�d �ZSd�d�� ZTd�d�� ZUd�d�� ZVd�d�� ZWdaXd�d�� ZYd�d�� ZZda[d�d�� Z\d�d�� Z]d�d�� Z^d�d�� Z_d�d�� Z`d�d�� Zadabd�d�� Zcd�d�d��Zdd�d�d��Zed�d�� Zfd�d�� Zgd�d�� Zhd�d�� Zid�d�� Zjd�d�� Zkd�d�� Zld�d�� ZmdS )�a3 Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t �� t�� dS )z,Clear the parse cache and the quoters cache.N)� _parse_cache�clear�
_safe_quoters� r! r! �$/usr/lib64/python3.8/urllib/parse.py� clear_cache` s r# �ascii�strictc C s | S �Nr! )�objr! r! r" �_noopo s r( c C s | � ||�S r& ��encode)r' �encoding�errorsr! r! r" �_encode_resultr s r- c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|� � ��nd V qdS )r N��decode��.0�x�r+ r, r! r" � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr+ r, r! r3 r" � _decode_argsv s r7 c G sV t | d t�}| dd � D ] }|rt |t�|krtd��q|rH| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr( r7 r- )r6 Z str_input�argr! r! r" � _coerce_argsz s
r= c @ s e Zd ZdZdZddd�ZdS ) �_ResultMixinStrz>Standard approach to encoding parsed results from str to bytesr! r$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r& r) r0 r3 r! r" r4 � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart��selfr+ r, r! r3 r" r* � s z_ResultMixinStr.encodeN)r$ r% )�__name__�
__module__� __qualname__�__doc__� __slots__r* r! r! r! r" r> � s r> c @ s e Zd ZdZdZddd�ZdS ) �_ResultMixinBytesz>Standard approach to decoding parsed results from bytes to strr! r$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r& r. r0 r3 r! r" r4 � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpartr@ r! r3 r" r/ � s z_ResultMixinBytes.decodeN)r$ r% )rB rC rD rE rF r/ r! r! r! r" rG � s rG c @ sD e Zd ZdZdZedd� �Zedd� �Zedd� �Zed d
� �Z d S ) �_NetlocResultMixinBasezHShared methods for the parsed result objects containing a netloc elementr! c C s
| j d S )Nr �� _userinfo�rA r! r! r" �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr8 rJ rL r! r! r" �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|�|�\}}}|�� | | S )Nr �%� %)� _hostinfor9 r: � partition�lower)rA �hostname� separatorZpercentZzoner! r! r" rT � s
z _NetlocResultMixinBase.hostnamec C sl | j d }|d k rhzt|d�}W n( tk
rH d|��}t|�d �Y nX d| kr^dkshn td��|S )Nr8 �
z+Port could not be cast to integer value as r i�� zPort out of range 0-65535)rQ �int�
ValueError)rA �port�messager! r! r" rY � s
z_NetlocResultMixinBase.portN)
rB rC rD rE rF �propertyrM rN rT rY r! r! r! r" rI � s
rI c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinStrr! c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N�@�:��netloc�
rpartitionrR �rA r` ZuserinfoZ have_info�hostinforM Z
have_passwordrN r! r! r" rK � s z _NetlocResultMixinStr._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nr] �[�]r^ r_ �rA r` �_rc Z have_open_brZ bracketedrT rY r! r! r" rQ � s z _NetlocResultMixinStr._hostinfoN�rB rC rD rF r[ rK rQ r! r! r! r" r\ � s
r\ c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinBytesr! c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N� @� :r_ rb r! r! r" rK � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nrj � [� ]rk r_ rf r! r! r" rQ � s z!_NetlocResultMixinBytes._hostinfoNrh r! r! r! r" ri � s
ri )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zq
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd ZdZdd� ZdS )r r! c C s | j r| jd | j S | jS d S )N�#��fragment�urlrL r! r! r" �geturlI s zDefragResult.geturlN�rB rC rD rF rs r! r! r! r" r G s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& �r rL r! r! r" rs Q s zSplitResult.geturlNrt r! r! r! r" r O s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& �r rL r! r! r" rs V s zParseResult.geturlNrt r! r! r! r" r T s c @ s e Zd ZdZdd� ZdS )r r! c C s | j r| jd | j S | jS d S )N� #rp rL r! r! r" rs \ s zDefragResultBytes.geturlNrt r! r! r! r" r Z s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& ru rL r! r! r" rs d s zSplitResultBytes.geturlNrt r! r! r! r" r b s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& rv rL r! r! r" rs i s zParseResultBytes.geturlNrt r! r! r! r" r g s c C s4 t tfttfttff} | D ]\}}||_||_qd S r& )r r r r r r r? rH )Z
_result_pairsZ_decodedZ_encodedr! r! r" �_fix_result_transcodingm s � rx Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )a# Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.�;r )r= r � uses_params� _splitparamsr )
rr �scheme�allow_fragments�_coerce_resultZ splitresultr` �queryrq �params�resultr! r! r" r z s c C sR d| kr,| � d| �d��}|dk r6| dfS n
| � d�}| d |� | |d d � fS )N�/ry r r r8 )�find�rfind)rr �ir! r! r" r{ � s
r{ c C sH t | �}dD ]"}| �||�}|dkr t||�}q | ||� | |d � fS )Nz/?#r )�lenr� �min)rr �start�delim�cZwdelimr! r! r" � _splitnetloc� s r� c C s� | r | � � rd S dd l}| �dd�}|�dd�}|�dd�}|�dd�}|�d|�}||kr`d S dD ] }||krdtd | d
d ��qdd S ) Nr r] r r^ ro �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�isascii� unicodedata�replace� normalizerX )r` r� �nZnetloc2r� r! r! r" � _checknetloc� s �r� c C s t D ]}| �|d�} q| S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )rr �br! r! r" � _remove_unsafe_bytes_from_url� s r� c
C s� t | |�\} }}t| �} t|�}| �t�} |�t�}t|�}| ||t| �t|�f}t�|d�}|rj||�S t t�t
kr|t � d } }}| � d�} | dk�r�| d| � dk�rn| | d d� } | dd� dk�r t
| d�\}} d |kr�d
|k�sd
|k�r d |k�r td ��|�r,d | k�r,| �d d�\} }d
| k�rF| �d
d�\} }t|� td|| ||�}
|
t|< ||
�S | d| � D ]} | tk�rz �qҐqz| | d d� } | �r�tdd� | D ���r�| d| � �� | }} | dd� dk�r"t
| d�\}} d |k�rd
|k�sd
|k�r"d |k�r"td ��|�rBd | k�rB| �d d�\} }d
| k�r\| �d
d�\} }t|� t||| ||�}
|
t|< ||
�S )a Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.Nr r^ r r r8 � �//rd re zInvalid IPv6 URLro r� c s s | ]}|d kV qdS )�
0123456789Nr! �r1 r� r! r! r" r4 � s zurlsplit.<locals>.<genexpr>)r= r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getr� �MAX_CACHE_SIZEr# r� r� rX �splitr� r � scheme_chars�anyrS )
rr r| r} r~ �key�cachedr` r rq r� �vr� �restr! r! r" r � sn
��
��
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )z�Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent).z%s;%s)r= r )�
componentsr| r` rr r� r rq r~ r! r! r" r � s
� c C s� t | � \}}}}}}|s4|r`|tkr`|dd� dkr`|rP|dd� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S )
ak Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent).Nr� r� r8 r� r r^ r� ro )r= � uses_netloc)r� r| r` rr r rq r~ r! r! r" r � s � c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | s�|
s�|} |}
|s�|}|t|
| | |
||f��S |�d�}|d dkr�|d= | dd� dkr�| �d�}n(|| �d� }td|dd� �|dd�< g }|D ]P}|dk�r\z |�� W n tk
�rX Y nX n|dk�rl�q(n
|� |� �q(|d dk�r�|� d� |t|
| d�
|��p�d|
||f��S ) zaJoin a base URL and a possibly relative URL to form an absolute
interpretation of the latter.r r� ���Nr8 �..�.)r� r� ) r= r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baserr r} r~ ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentr| r` �pathr� r rq Z
base_partsZsegmentsZ
resolved_pathZsegr! r! r" r sp
�
�
�
�
� �c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )z�Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
ro r )r= r r r ) rr r~ �sr� �p�a�qZfragZdefragr! r! r" r T s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| �d�} | � d�}t|�dkr<| S |d g}|j}tdkrbdd� tD �a|dd� D ]R}z(|t|dd � � ||d d� � W qn tk
r� |d� ||� Y qnX qnd� |�S )
z,unquote_to_bytes('abc%20def') -> b'abc def'.� �utf-8rP r8 r Nc S s. i | ]&}t D ] }|| �� t�|| ��q qS r! )�_hexdigr* �bytes�fromhex)r1 r� r� r! r! r" �
<dictcomp>z s
�
z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r9 r: r* r� r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr! r! r" r g s,
�z([ -]+)r� r� c C s� t | t�rtd��d| kr$| j | S |dkr0d}|dkr<d}t�| �}|d g}|j}tdt|�d�D ],}|t|| �� ||�� |||d � qfd �
|�S )
a� Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
zExpected str, got bytesrO Nr� r� r r8 r� r ) r9 r� r; r� �_asciirer� �ranger� r r/ r� )r� r+ r, r� r� r� r� r! r! r" r � s
Fc C sN i }t | ||||||d�}|D ]*\} }
| |kr>|| �|
� q |
g|| < q |S )aX Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError if there
are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a dictionary.
)r+ r, �max_num_fieldsrU )r
r� ) �qs�keep_blank_values�strict_parsingr+ r, r� rU Z
parsed_result�pairs�name�valuer! r! r" r � s � c @ s e Zd ZdZdS )� _QueryStringSeparatorWarningz>Warning for using default `separator` in parse_qs or parse_qslN)rB rC rD rE r! r! r! r" r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |�d�}|r2t|ttf�sB|dk rBtd��t� }|dk�rRt}d} |dkrrtj �
| �}d}
|dkr�z t t �} W n t
k
r� Y nJX | �: ddl} | jddd�}
|
�| � |
j
d | dd
�}|aW 5 Q R X t }
|dk�rd | k�rdd lm} |d
tdd� d}n:|dk�r(|}n*t|�dk�rRt| � d|
� d�d d ��|dk �r�||k�r�d| �d� | �d � }nd| �|� }||k �r�td��||k�r�dd� | �d�D �}ndd� | �|�D �}g }|D ]�}|�s�|�s�q�|�dd�}t|�dk�r4|�r td |f ��|�r�|�d � n�q�t|d ��sH|�r�|d �d d �}t|||d �}||�}|d �d d �}t|||d �}||�}|�||f� �q�|S )!aX Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError
if there are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a list, as G-d intended.
r$ Nz*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler )ro )Z
interpolationZcomment_prefixesr )Zfallbackry )�warna The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.r� ��
stacklevel�&Zlegacyr8 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|� d �D ]}|�qqS )ry �r� )r1 �s1�s2r! r! r" �
<listcomp>7 s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r! r! )r1 r� r! r! r" r� 9 s �=zbad query field: %rr �+� r3 )r= r9 r� r/ r: rX �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� r� �countr� r� r� r )r� r� r� r+ r, r� rU r~ Z_legacyZ envvar_nameZ
config_sourcer r� Zconfigr� �
num_fieldsr� �rZ
name_valueZnvr� r� r! r! r" r
� s�
�
�
���
c C s | � dd�} t| ||�S )z�Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
r� r� )r� r )r� r+ r, r! r! r" r Q s sB ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-~c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) �Quoterz�A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
c C s t �|�| _dS )zsafe: bytes object.N)� _ALWAYS_SAFE�union�safe)rA r� r! r! r" �__init__i s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__rB �dictrL r! r! r" �__repr__m s zQuoter.__repr__c C s( || j krt|�nd�|�}|| |< |S )Nz%{:02X})r� �chr�format)rA r� r� r! r! r" � __missing__q s zQuoter.__missing__N)rB rC rD rE r� r� r� r! r! r! r" r� a s r� r� c C sb t | t�r8| s| S |dkr d}|dkr*d}| �||�} n |dk rHtd��|dk rXtd��t| |�S )a� quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted. The
quote function offers a cautious (not minimal) way to quote a
string for most of these parts.
RFC 3986 Uniform Resource Identifier (URI): Generic Syntax lists
the following (un)reserved characters.
unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
reserved = gen-delims / sub-delims
gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
/ "*" / "+" / "," / ";" / "="
Each of the reserved characters is reserved in some component of a URL,
but not necessarily in all of them.
The quote function %-escapes all characters that are neither in the
unreserved chars ("always safe") nor the additional chars set via the
safe arg.
The default for the safe arg is '/'. The character is reserved, but in
typical usage the quote function is being called on a path where the
existing slash characters are to be preserved.
Python 3.7 updates from using RFC 2396 to RFC 3986 to quote URL strings.
Now, "~" is included in the set of unreserved characters.
string and safe may be either str or bytes objects. encoding and errors
must not be specified if string is a bytes object.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
Nr� r% z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r9 r: r* r; r
)r� r� r+ r, r! r! r" r w s '
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | �dd�S )z�Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
r� � r� )r9 r: r� r r� )r� r� r+ r, Zspacer! r! r" r � s ��
c s� t | ttf�std��| s dS t |t�r6|�dd�}ntdd� |D ��}| �t| �s^| �� S z t | � W n& t
k
r� t |�j t |< � Y nX d�
� fdd�| D ��S )z�Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def?') -> 'abc%20def%3f'
z!quote_from_bytes() expected bytesr r$ �ignorec S s g | ]}|d k r|�qS )� r! r� r! r! r" r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r! r! )r1 �char�Zquoterr! r" r� � s )r9 r� � bytearrayr; r: r* �rstrip�_ALWAYS_SAFE_BYTESr/ r r� r� � __getitem__r� )Zbsr� r! r� r" r
� s
c C s t | d�r| �� } nPz t| �r0t| d t�s0t�W n0 tk
rb t�� \}}}td��|��Y nX g } |s�| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | � |
d | � qp�n"| D �]\}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rB|| |�} | � |
d | � q�t| t
��rp|| |||�} | � |
d | � q�z t| �} W n: tk
�r� |t
| �|||�} | � |
d | � Y q�X | D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| � |
d |
� �q�q�d� | �S )a^ Encode a dict or sequence of two-element tuples into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The components of a query arg may each be either a string or a bytes type.
The safe, encoding, and errors parameters are passed down to the function
specified by quote_via (encoding and errors only if a component is a str).
�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� r� r9 r5 r; �sys�exc_info�with_tracebackr� r: r� r� )r Zdoseqr� r+ r, Z quote_viaZtyZva�tb�l�kr� r2 Zeltr! r! r" r � sR
�
c C s t jdtdd� t| �S )Nz/urllib.parse.to_bytes() is deprecated as of 3.8r� r� )r� r� �DeprecationWarning� _to_bytes�rr r! r! r" �to_bytes% s
�r c C sJ t | t�rFz| �d��� } W n( tk
rD tdt| � d ��Y nX | S )zto_bytes(u"URL") --> 'URL'.�ASCIIzURL z contains non-ASCII characters)r9 r: r* r/ � UnicodeError�reprr r! r! r" r + s
� r c C s` t | ��� } | dd� dkr<| dd� dkr<| dd� �� } | dd� dkr\| dd� �� } | S )z�Transform a string like '<URL:scheme://host/path>' into 'scheme://host/path'.
The string is returned unchanged if it's not a wrapped URL.
Nr8 �<r� �>� zURL:)r: r� r r! r! r" �unwrap9 s r
c C s t jdtdd� t| �S )NzUurllib.parse.splittype() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splittyper r! r! r" � splittypeF s
�r c C sD t dkrt�dtj�a t �| �}|r<|�� \}}|�� |fS d| fS )z:splittype('type:opaquestring') --> 'type', 'opaquestring'.Nz
([^/:]+):(.*))� _typeprog�re�compile�DOTALL�match�groupsrS )rr r r| �datar! r! r" r N s
r c C s t jdtdd� t| �S )NzUurllib.parse.splithost() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splithostr r! r! r" � splithost[ s
�r c C sX t dkrt�dtj�a t �| �}|rP|�� \}}|rH|d dkrHd| }||fS d| fS )z;splithost('//host[:port]/path') --> 'host[:port]', '/path'.Nz//([^/#?]*)(.*)r r� )� _hostprogr r r r r )rr r Z host_portr� r! r! r" r c s
r c C s t jdtdd� t| �S )NzUurllib.parse.splituser() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splituser��hostr! r! r" � splituserr s
�r c C s | � d�\}}} |r|nd| fS )zJsplituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.r] N�ra )r �userr� r! r! r" r y s r c C s t jdtdd� t| �S )NzWurllib.parse.splitpasswd() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitpasswd)r r! r! r" � splitpasswd s
�r! c C s | � d�\} }}| |r|ndfS )z/splitpasswd('user:passwd') -> 'user', 'passwd'.r^ N�rR )r r� Zpasswdr! r! r" r � s r c C s t jdtdd� t| �S )NzUurllib.parse.splitport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitportr r! r! r" � splitport� s
�r$ c C sD t dkrt�dtj�a t �| �}|r<|�� \} }|r<| |fS | dfS )z*splitport('host:port') --> 'host', 'port'.Nz
(.*):([0-9]*))� _portprogr r r � fullmatchr )r r rY r! r! r" r# � s
r# r� c C s t jdtdd� t| |�S )NzVurllib.parse.splitnport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitnport)r �defportr! r! r" �
splitnport� s
�r) c C sT | � d�\} }}|s|} n2|rLz t|�}W n tk
rB d}Y nX | |fS | |fS )z�Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number.r^ N)ra rW rX )r r( r� rY Znportr! r! r" r' � s
r' c C s t jdtdd� t| �S )NzVurllib.parse.splitquery() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitqueryr r! r! r" �
splitquery� s
�r+ c C s$ | � d�\}}}|r ||fS | dfS )z/splitquery('/path?query') --> '/path', 'query'.r� Nr )rr r� r� r r! r! r" r* � s r* c C s t jdtdd� t| �S )NzTurllib.parse.splittag() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splittagr r! r! r" �splittag� s
�r- c C s$ | � d�\}}}|r ||fS | dfS )z)splittag('/path#tag') --> '/path', 'tag'.ro Nr )rr r� r� �tagr! r! r" r, � s r, c C s t jdtdd� t| �S )NzUurllib.parse.splitattr() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitattrr r! r! r" � splitattr� s
�r0 c C s | � d�}|d |dd� fS )zksplitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...].ry r r8 Nr� )rr Zwordsr! r! r" r/ � s
r/ c C s t jdtdd� t| �S )NzWurllib.parse.splitvalue() is deprecated as of 3.8, use urllib.parse.parse_qsl() insteadr� r� )r� r� r � _splitvalue)�attrr! r! r" �
splitvalue� s
�r3 c C s | � d�\} }}| |r|ndfS )z-splitvalue('attr=value') --> 'attr', 'value'.r� Nr" )r2 r� r� r! r! r" r1 � s r1 )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )r� NN)r NN)r� )r� )r� )nrE r r� r� � collectionsr� �__all__r� r� rz Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r# Z_implicit_encodingZ_implicit_errorsr( r- r7 r= r� r> rG rI r\ ri rn Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBaserr rq r| r` r� r r� Z
ResultBaser r r r r r rx r r{ r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r � defaultdictr� r r r
r r r r
r r r r r r r r r! r r$ r% r# r) r' r+ r* r- r, r0 r/ r3 r1 r! r! r! r" �<module> s� ! � � � � � � �
�
�
%
� �
?
E
�
) �
}
6
�
Q
PK *(�Z�ͭ� � ) __pycache__/__init__.cpython-38.opt-1.pycnu �[��� U
��.e � @ s d S )N� r r r �'/usr/lib64/python3.8/urllib/__init__.py�<module> � PK *(�Z�ͭ� � ) __pycache__/__init__.cpython-38.opt-2.pycnu �[��� U
��.e � @ s d S )N� r r r �'/usr/lib64/python3.8/urllib/__init__.py�<module> � PK *(�ZH� �� �� & __pycache__/parse.cpython-38.opt-1.pycnu �[��� U
&�.e�� � @ s� d Z ddlZddlZddlZddlZddlZddddddd d
d d d
ddddddddddgZddddd d d d d d!d"d#d$d%d&d'd(d)d*gZddddd d+d d d d"d d!d,d#d$d%d-d'd(d&d.d/d0d)d*gZddd1d#dd d d!d$d%d2d3d"d&d4gZ dd1d5d6d+d d d,d2d3g
Z
ddd d d d!d"dd$d%d2d3g Z ddd1ddd6d d d d!d,d d#g
Z d7Z
d8Zd9d:d;gZd<Zi Zd=d>� Zd?Zd@ZdAdB� ZeefdCdD�ZeefdEdF�ZdGdH� ZG dIdJ� dJe�ZG dKdL� dLe�ZG dMdN� dNe�Z G dOdP� dPe e�Z G dQdR� dRe e�Z ddSlm Z e ddT�Z e ddU�Z!e ddV�Z"dWe _ dXe j#_ dYe j$_ dZe!_ d[e!j%_ d\e!j&_ d]e!j'_ d^e!j(_ d_e!j$_ d`e"_ e!j%j e"j%_ e!j&j e"j&_ e!j'j e"j'_ dae"j)_ e!j(j e"j(_ e!j$j e"j$_ e Z*G dbd� de e�Z+G dcd� de!e �Z,G ddd� de"e �Z-G ded� de e�Z.G dfd� de!e �Z/G dgd� de"e �Z0dhdi� Z1e1� [1d�dkd�Z2dldm� Z3d�dndo�Z4dpdq� Z5drds� Z6d�dtd�Z7dud� Z8dvd� Z9d�dwd�Z:dxd� Z;dyZ<da=dzd� Z>e�?d{�Z@d�d~d�ZAd�d�d
�ZBG d�d�� d�eC�ZDd�ZEdaFd�d�d �ZGd�d�d�ZHeId��ZJeKeJ�ZLi ZMG d�d�� d�ejN�ZOd�d�d �ZPd�d�d
�ZQd�d�d�ZRddddeQfd�d �ZSd�d�� ZTd�d�� ZUd�d�� ZVd�d�� ZWdaXd�d�� ZYd�d�� ZZda[d�d�� Z\d�d�� Z]d�d�� Z^d�d�� Z_d�d�� Z`d�d�� Zadabd�d�� Zcd�d�d��Zdd�d�d��Zed�d�� Zfd�d�� Zgd�d�� Zhd�d�� Zid�d�� Zjd�d�� Zkd�d�� Zld�d�� ZmdS )�a3 Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
1995.
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
McCahill, December 1994
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t �� t�� dS )z,Clear the parse cache and the quoters cache.N)� _parse_cache�clear�
_safe_quoters� r! r! �$/usr/lib64/python3.8/urllib/parse.py� clear_cache` s r# �ascii�strictc C s | S �Nr! )�objr! r! r" �_noopo s r( c C s | � ||�S r& ��encode)r' �encoding�errorsr! r! r" �_encode_resultr s r- c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|� � ��nd V qdS )r N��decode��.0�x�r+ r, r! r" � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr+ r, r! r3 r" � _decode_argsv s r7 c G sV t | d t�}| dd � D ] }|rt |t�|krtd��q|rH| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr( r7 r- )r6 Z str_input�argr! r! r" � _coerce_argsz s
r= c @ s e Zd ZdZdZddd�ZdS ) �_ResultMixinStrz>Standard approach to encoding parsed results from str to bytesr! r$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r& r) r0 r3 r! r" r4 � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart��selfr+ r, r! r3 r" r* � s z_ResultMixinStr.encodeN)r$ r% )�__name__�
__module__� __qualname__�__doc__� __slots__r* r! r! r! r" r> � s r> c @ s e Zd ZdZdZddd�ZdS ) �_ResultMixinBytesz>Standard approach to decoding parsed results from bytes to strr! r$ r% c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r& r. r0 r3 r! r" r4 � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpartr@ r! r3 r" r/ � s z_ResultMixinBytes.decodeN)r$ r% )rB rC rD rE rF r/ r! r! r! r" rG � s rG c @ sD e Zd ZdZdZedd� �Zedd� �Zedd� �Zed d
� �Z d S ) �_NetlocResultMixinBasezHShared methods for the parsed result objects containing a netloc elementr! c C s
| j d S )Nr �� _userinfo�rA r! r! r" �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr8 rJ rL r! r! r" �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|�|�\}}}|�� | | S )Nr �%� %)� _hostinfor9 r: � partition�lower)rA �hostname� separatorZpercentZzoner! r! r" rT � s
z _NetlocResultMixinBase.hostnamec C sl | j d }|d k rhzt|d�}W n( tk
rH d|��}t|�d �Y nX d| kr^dkshn td��|S )Nr8 �
z+Port could not be cast to integer value as r i�� zPort out of range 0-65535)rQ �int�
ValueError)rA �port�messager! r! r" rY � s
z_NetlocResultMixinBase.portN)
rB rC rD rE rF �propertyrM rN rT rY r! r! r! r" rI � s
rI c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinStrr! c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N�@�:��netloc�
rpartitionrR �rA r` ZuserinfoZ have_info�hostinforM Z
have_passwordrN r! r! r" rK � s z _NetlocResultMixinStr._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nr] �[�]r^ r_ �rA r` �_rc Z have_open_brZ bracketedrT rY r! r! r" rQ � s z _NetlocResultMixinStr._hostinfoN�rB rC rD rF r[ rK rQ r! r! r! r" r\ � s
r\ c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinBytesr! c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N� @� :r_ rb r! r! r" rK � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nrj � [� ]rk r_ rf r! r! r" rQ � s z!_NetlocResultMixinBytes._hostinfoNrh r! r! r! r" ri � s
ri )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zq
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd ZdZdd� ZdS )r r! c C s | j r| jd | j S | jS d S )N�#��fragment�urlrL r! r! r" �geturlI s zDefragResult.geturlN�rB rC rD rF rs r! r! r! r" r G s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& �r rL r! r! r" rs Q s zSplitResult.geturlNrt r! r! r! r" r O s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& �r rL r! r! r" rs V s zParseResult.geturlNrt r! r! r! r" r T s c @ s e Zd ZdZdd� ZdS )r r! c C s | j r| jd | j S | jS d S )N� #rp rL r! r! r" rs \ s zDefragResultBytes.geturlNrt r! r! r! r" r Z s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& ru rL r! r! r" rs d s zSplitResultBytes.geturlNrt r! r! r! r" r b s c @ s e Zd ZdZdd� ZdS )r r! c C s t | �S r& rv rL r! r! r" rs i s zParseResultBytes.geturlNrt r! r! r! r" r g s c C s4 t tfttfttff} | D ]\}}||_||_qd S r& )r r r r r r r? rH )Z
_result_pairsZ_decodedZ_encodedr! r! r" �_fix_result_transcodingm s � rx Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )a# Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.�;r )r= r � uses_params� _splitparamsr )
rr �scheme�allow_fragments�_coerce_resultZ splitresultr` �queryrq �params�resultr! r! r" r z s c C sR d| kr,| � d| �d��}|dk r6| dfS n
| � d�}| d |� | |d d � fS )N�/ry r r r8 )�find�rfind)rr �ir! r! r" r{ � s
r{ c C sH t | �}dD ]"}| �||�}|dkr t||�}q | ||� | |d � fS )Nz/?#r )�lenr� �min)rr �start�delim�cZwdelimr! r! r" � _splitnetloc� s r� c C s� | r | � � rd S dd l}| �dd�}|�dd�}|�dd�}|�dd�}|�d|�}||kr`d S dD ] }||krdtd | d
d ��qdd S ) Nr r] r r^ ro �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�isascii� unicodedata�replace� normalizerX )r` r� �nZnetloc2r� r! r! r" � _checknetloc� s �r� c C s t D ]}| �|d�} q| S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )rr �br! r! r" � _remove_unsafe_bytes_from_url� s r� c
C s� t | |�\} }}t| �} t|�}| �t�} |�t�}t|�}| ||t| �t|�f}t�|d�}|rj||�S t t�t
kr|t � d } }}| � d�} | dk�r�| d| � dk�rn| | d d� } | dd� dk�r t
| d�\}} d |kr�d
|k�sd
|k�r d |k�r td ��|�r,d | k�r,| �d d�\} }d
| k�rF| �d
d�\} }t|� td|| ||�}
|
t|< ||
�S | d| � D ]} | tk�rz �qҐqz| | d d� } | �r�tdd� | D ���r�| d| � �� | }} | dd� dk�r"t
| d�\}} d |k�rd
|k�sd
|k�r"d |k�r"td ��|�rBd | k�rB| �d d�\} }d
| k�r\| �d
d�\} }t|� t||| ||�}
|
t|< ||
�S )a Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes.Nr r^ r r r8 � �//rd re zInvalid IPv6 URLro r� c s s | ]}|d kV qdS )�
0123456789Nr! �r1 r� r! r! r" r4 � s zurlsplit.<locals>.<genexpr>)r= r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getr� �MAX_CACHE_SIZEr# r� r� rX �splitr� r � scheme_chars�anyrS )
rr r| r} r~ �key�cachedr` r rq r� �vr� �restr! r! r" r � sn
��
��
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )z�Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent).z%s;%s)r= r )�
componentsr| r` rr r� r rq r~ r! r! r" r � s
� c C s� t | � \}}}}}}|s4|r`|tkr`|dd� dkr`|rP|dd� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S )
ak Combine the elements of a tuple as returned by urlsplit() into a
complete URL as a string. The data argument can be any five-item iterable.
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent).Nr� r� r8 r� r r^ r� ro )r= � uses_netloc)r� r| r` rr r rq r~ r! r! r" r � s � c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | s�|
s�|} |}
|s�|}|t|
| | |
||f��S |�d�}|d dkr�|d= | dd� dkr�| �d�}n(|| �d� }td|dd� �|dd�< g }|D ]P}|dk�r\z |�� W n tk
�rX Y nX n|dk�rl�q(n
|� |� �q(|d dk�r�|� d� |t|
| d�
|��p�d|
||f��S ) zaJoin a base URL and a possibly relative URL to form an absolute
interpretation of the latter.r r� ���Nr8 �..�.)r� r� ) r= r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baserr r} r~ ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentr| r` �pathr� r rq Z
base_partsZsegmentsZ
resolved_pathZsegr! r! r" r sp
�
�
�
�
� �c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )z�Removes any existing fragment from URL.
Returns a tuple of the defragmented URL and the fragment. If
the URL contained no fragments, the second element is the
empty string.
ro r )r= r r r ) rr r~ �sr� �p�a�qZfragZdefragr! r! r" r T s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| �d�} | � d�}t|�dkr<| S |d g}|j}tdkrbdd� tD �a|dd� D ]R}z(|t|dd � � ||d d� � W qn tk
r� |d� ||� Y qnX qnd� |�S )
z,unquote_to_bytes('abc%20def') -> b'abc def'.� �utf-8rP r8 r Nc S s. i | ]&}t D ] }|| �� t�|| ��q qS r! )�_hexdigr* �bytes�fromhex)r1 r� r� r! r! r" �
<dictcomp>z s
�
z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r9 r: r* r� r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr! r! r" r g s,
�z([ -]+)r� r� c C s� t | t�rtd��d| kr$| j | S |dkr0d}|dkr<d}t�| �}|d g}|j}tdt|�d�D ],}|t|| �� ||�� |||d � qfd �
|�S )
a� Replace %xx escapes by their single-character equivalent. The optional
encoding and errors parameters specify how to decode percent-encoded
sequences into Unicode characters, as accepted by the bytes.decode()
method.
By default, percent-encoded sequences are decoded with UTF-8, and invalid
sequences are replaced by a placeholder character.
unquote('abc%20def') -> 'abc def'.
zExpected str, got bytesrO Nr� r� r r8 r� r ) r9 r� r; r� �_asciirer� �ranger� r r/ r� )r� r+ r, r� r� r� r� r! r! r" r � s
Fc C sN i }t | ||||||d�}|D ]*\} }
| |kr>|| �|
� q |
g|| < q |S )aX Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as
blank strings. The default false value indicates that
blank values are to be ignored and treated as if they were
not included.
strict_parsing: flag indicating what to do with parsing errors.
If false (the default), errors are silently ignored.
If true, errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError if there
are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a dictionary.
)r+ r, �max_num_fieldsrU )r
r� ) �qs�keep_blank_values�strict_parsingr+ r, r� rU Z
parsed_result�pairs�name�valuer! r! r" r � s � c @ s e Zd ZdZdS )� _QueryStringSeparatorWarningz>Warning for using default `separator` in parse_qs or parse_qslN)rB rC rD rE r! r! r! r" r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |�d�}|r2t|ttf�sB|dk rBtd��t� }|dk�rRt}d} |dkrrtj �
| �}d}
|dkr�z t t �} W n t
k
r� Y nJX | �: ddl} | jddd�}
|
�| � |
j
d | dd
�}|aW 5 Q R X t }
|dk�rd | k�rdd lm} |d
tdd� d}n:|dk�r(|}n*t|�dk�rRt| � d|
� d�d d ��|dk �r�||k�r�d| �d� | �d � }nd| �|� }||k �r�td��||k�r�dd� | �d�D �}ndd� | �|�D �}g }|D ]�}|�s�|�s�q�|�dd�}t|�dk�r4|�r td |f ��|�r�|�d � n�q�t|d ��sH|�r�|d �d d �}t|||d �}||�}|d �d d �}t|||d �}||�}|�||f� �q�|S )!aX Parse a query given as a string argument.
Arguments:
qs: percent-encoded query string to be parsed
keep_blank_values: flag indicating whether blank values in
percent-encoded queries should be treated as blank strings.
A true value indicates that blanks should be retained as blank
strings. The default false value indicates that blank values
are to be ignored and treated as if they were not included.
strict_parsing: flag indicating what to do with parsing errors. If
false (the default), errors are silently ignored. If true,
errors raise a ValueError exception.
encoding and errors: specify how to decode percent-encoded sequences
into Unicode characters, as accepted by the bytes.decode() method.
max_num_fields: int. If set, then throws a ValueError
if there are more than n fields read by parse_qsl().
separator: str. The symbol to use for separating the query arguments.
Defaults to &.
Returns a list, as G-d intended.
r$ Nz*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler )ro )Z
interpolationZcomment_prefixesr )Zfallbackry )�warna The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.r� ��
stacklevel�&Zlegacyr8 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|� d �D ]}|�qqS )ry �r� )r1 �s1�s2r! r! r" �
<listcomp>7 s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r! r! )r1 r� r! r! r" r� 9 s �=zbad query field: %rr �+� r3 )r= r9 r� r/ r: rX �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� r� �countr� r� r� r )r� r� r� r+ r, r� rU r~ Z_legacyZ envvar_nameZ
config_sourcer r� Zconfigr� �
num_fieldsr� �rZ
name_valueZnvr� r� r! r! r" r
� s�
�
�
���
c C s | � dd�} t| ||�S )z�Like unquote(), but also replace plus signs by spaces, as required for
unquoting HTML form values.
unquote_plus('%7e/abc+def') -> '~/abc def'
r� r� )r� r )r� r+ r, r! r! r" r Q s sB ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-~c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) �Quoterz�A mapping from bytes (in range(0,256)) to strings.
String values are percent-encoded byte values, unless the key < 128, and
in the "safe" set (either the specified safe set, or default set).
c C s t �|�| _dS )zsafe: bytes object.N)� _ALWAYS_SAFE�union�safe)rA r� r! r! r" �__init__i s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__rB �dictrL r! r! r" �__repr__m s zQuoter.__repr__c C s( || j krt|�nd�|�}|| |< |S )Nz%{:02X})r� �chr�format)rA r� r� r! r! r" � __missing__q s zQuoter.__missing__N)rB rC rD rE r� r� r� r! r! r! r" r� a s r� r� c C sb t | t�r8| s| S |dkr d}|dkr*d}| �||�} n |dk rHtd��|dk rXtd��t| |�S )a� quote('abc def') -> 'abc%20def'
Each part of a URL, e.g. the path info, the query, etc., has a
different set of reserved characters that must be quoted. The
quote function offers a cautious (not minimal) way to quote a
string for most of these parts.
RFC 3986 Uniform Resource Identifier (URI): Generic Syntax lists
the following (un)reserved characters.
unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
reserved = gen-delims / sub-delims
gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
/ "*" / "+" / "," / ";" / "="
Each of the reserved characters is reserved in some component of a URL,
but not necessarily in all of them.
The quote function %-escapes all characters that are neither in the
unreserved chars ("always safe") nor the additional chars set via the
safe arg.
The default for the safe arg is '/'. The character is reserved, but in
typical usage the quote function is being called on a path where the
existing slash characters are to be preserved.
Python 3.7 updates from using RFC 2396 to RFC 3986 to quote URL strings.
Now, "~" is included in the set of unreserved characters.
string and safe may be either str or bytes objects. encoding and errors
must not be specified if string is a bytes object.
The optional encoding and errors parameters specify how to deal with
non-ASCII characters, as accepted by the str.encode method.
By default, encoding='utf-8' (characters are encoded with UTF-8), and
errors='strict' (unsupported characters raise a UnicodeEncodeError).
Nr� r% z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r9 r: r* r; r
)r� r� r+ r, r! r! r" r w s '
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | �dd�S )z�Like quote(), but also replace ' ' with '+', as required for quoting
HTML form values. Plus signs in the original string are escaped unless
they are included in safe. It also does not have safe default to '/'.
r� � r� )r9 r: r� r r� )r� r� r+ r, Zspacer! r! r" r � s ��
c s� t | ttf�std��| s dS t |t�r6|�dd�}ntdd� |D ��}| �t| �s^| �� S z t | � W n& t
k
r� t |�j t |< � Y nX d�
� fdd�| D ��S )z�Like quote(), but accepts a bytes object rather than a str, and does
not perform string-to-bytes encoding. It always returns an ASCII string.
quote_from_bytes(b'abc def?') -> 'abc%20def%3f'
z!quote_from_bytes() expected bytesr r$ �ignorec S s g | ]}|d k r|�qS )� r! r� r! r! r" r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r! r! )r1 �char�Zquoterr! r" r� � s )r9 r� � bytearrayr; r: r* �rstrip�_ALWAYS_SAFE_BYTESr/ r r� r� � __getitem__r� )Zbsr� r! r� r" r
� s
c C s t | d�r| �� } nPz t| �r0t| d t�s0t�W n0 tk
rb t�� \}}}td��|��Y nX g } |s�| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | � |
d | � qp�n"| D �]\}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rB|| |�} | � |
d | � q�t| t
��rp|| |||�} | � |
d | � q�z t| �} W n: tk
�r� |t
| �|||�} | � |
d | � Y q�X | D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| � |
d |
� �q�q�d� | �S )a^ Encode a dict or sequence of two-element tuples into a URL query string.
If any values in the query arg are sequences and doseq is true, each
sequence element is converted to a separate parameter.
If the query arg is a sequence of two-element tuples, the order of the
parameters in the output will match the order of parameters in the
input.
The components of a query arg may each be either a string or a bytes type.
The safe, encoding, and errors parameters are passed down to the function
specified by quote_via (encoding and errors only if a component is a str).
�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� r� r9 r5 r; �sys�exc_info�with_tracebackr� r: r� r� )r Zdoseqr� r+ r, Z quote_viaZtyZva�tb�l�kr� r2 Zeltr! r! r" r � sR
�
c C s t jdtdd� t| �S )Nz/urllib.parse.to_bytes() is deprecated as of 3.8r� r� )r� r� �DeprecationWarning� _to_bytes�rr r! r! r" �to_bytes% s
�r c C sJ t | t�rFz| �d��� } W n( tk
rD tdt| � d ��Y nX | S )zto_bytes(u"URL") --> 'URL'.�ASCIIzURL z contains non-ASCII characters)r9 r: r* r/ � UnicodeError�reprr r! r! r" r + s
� r c C s` t | ��� } | dd� dkr<| dd� dkr<| dd� �� } | dd� dkr\| dd� �� } | S )z�Transform a string like '<URL:scheme://host/path>' into 'scheme://host/path'.
The string is returned unchanged if it's not a wrapped URL.
Nr8 �<r� �>� zURL:)r: r� r r! r! r" �unwrap9 s r
c C s t jdtdd� t| �S )NzUurllib.parse.splittype() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splittyper r! r! r" � splittypeF s
�r c C sD t dkrt�dtj�a t �| �}|r<|�� \}}|�� |fS d| fS )z:splittype('type:opaquestring') --> 'type', 'opaquestring'.Nz
([^/:]+):(.*))� _typeprog�re�compile�DOTALL�match�groupsrS )rr r r| �datar! r! r" r N s
r c C s t jdtdd� t| �S )NzUurllib.parse.splithost() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splithostr r! r! r" � splithost[ s
�r c C sX t dkrt�dtj�a t �| �}|rP|�� \}}|rH|d dkrHd| }||fS d| fS )z;splithost('//host[:port]/path') --> 'host[:port]', '/path'.Nz//([^/#?]*)(.*)r r� )� _hostprogr r r r r )rr r Z host_portr� r! r! r" r c s
r c C s t jdtdd� t| �S )NzUurllib.parse.splituser() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splituser��hostr! r! r" � splituserr s
�r c C s | � d�\}}} |r|nd| fS )zJsplituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.r] N�ra )r �userr� r! r! r" r y s r c C s t jdtdd� t| �S )NzWurllib.parse.splitpasswd() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitpasswd)r r! r! r" � splitpasswd s
�r! c C s | � d�\} }}| |r|ndfS )z/splitpasswd('user:passwd') -> 'user', 'passwd'.r^ N�rR )r r� Zpasswdr! r! r" r � s r c C s t jdtdd� t| �S )NzUurllib.parse.splitport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitportr r! r! r" � splitport� s
�r$ c C sD t dkrt�dtj�a t �| �}|r<|�� \} }|r<| |fS | dfS )z*splitport('host:port') --> 'host', 'port'.Nz
(.*):([0-9]*))� _portprogr r r � fullmatchr )r r rY r! r! r" r# � s
r# r� c C s t jdtdd� t| |�S )NzVurllib.parse.splitnport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitnport)r �defportr! r! r" �
splitnport� s
�r) c C sT | � d�\} }}|s|} n2|rLz t|�}W n tk
rB d}Y nX | |fS | |fS )z�Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number.r^ N)ra rW rX )r r( r� rY Znportr! r! r" r' � s
r' c C s t jdtdd� t| �S )NzVurllib.parse.splitquery() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitqueryr r! r! r" �
splitquery� s
�r+ c C s$ | � d�\}}}|r ||fS | dfS )z/splitquery('/path?query') --> '/path', 'query'.r� Nr )rr r� r� r r! r! r" r* � s r* c C s t jdtdd� t| �S )NzTurllib.parse.splittag() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splittagr r! r! r" �splittag� s
�r- c C s$ | � d�\}}}|r ||fS | dfS )z)splittag('/path#tag') --> '/path', 'tag'.ro Nr )rr r� r� �tagr! r! r" r, � s r, c C s t jdtdd� t| �S )NzUurllib.parse.splitattr() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitattrr r! r! r" � splitattr� s
�r0 c C s | � d�}|d |dd� fS )zksplitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...].ry r r8 Nr� )rr Zwordsr! r! r" r/ � s
r/ c C s t jdtdd� t| �S )NzWurllib.parse.splitvalue() is deprecated as of 3.8, use urllib.parse.parse_qsl() insteadr� r� )r� r� r � _splitvalue)�attrr! r! r" �
splitvalue� s
�r3 c C s | � d�\} }}| |r|ndfS )z-splitvalue('attr=value') --> 'attr', 'value'.r� Nr" )r2 r� r� r! r! r" r1 � s r1 )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )r� NN)r NN)r� )r� )r� )nrE r r� r� � collectionsr� �__all__r� r� rz Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r# Z_implicit_encodingZ_implicit_errorsr( r- r7 r= r� r> rG rI r\ ri rn Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBaserr rq r| r` r� r r� Z
ResultBaser r r r r r rx r r{ r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r � defaultdictr� r r r
r r r r
r r r r r r r r r! r r$ r% r# r) r' r+ r* r- r, r0 r/ r3 r1 r! r! r! r" �<module> s� ! � � � � � � �
�
�
%
� �
?
E
�
) �
}
6
�
Q
PK *(�Zi�) ) ( __pycache__/request.cpython-38.opt-1.pycnu �[��� U
e5d�� � ! @ s� d Z ddlZddlZddlZddlZddlZddlZddlZddl Z ddl
Z
ddl Z ddl Z ddl
Z
ddlZddlZddlZddlZddlmZmZmZ ddlmZmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z( ddl)m*Z*m+Z+ z ddl,Z,W n e-k
�r dZ.Y nX dZ.dd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'd(g!Z/d)e
j0dd*� Z1da2de j3fddddd+�d,d �Z4d-d � Z5g Z6d~d.d%�Z7d/d&� Z8e
�9d0e
j:�Z;d1d2� Z<G d3d� d�Z=G d4d � d �Z>d5d!� Z?G d6d
� d
�Z@G d7d � d e@�ZAG d8d � d e@�ZBG d9d � d e@�ZCd:d;� ZDG d<d� de@�ZEG d=d� d�ZFG d>d� deF�ZGG d?d� deG�ZHG d@d� d�ZIG dAd� deIe@�ZJG dBd� deIe@�ZKejLZMG dCd� d�ZNG dDd� de@eN�ZOG dEd� de@eN�ZPG dFdG� dGe@�ZQG dHd� deQ�ZReSejTdI��r*G dJdK� dKeQ�ZUe/�VdK� G dLd
� d
e@�ZWG dMd � d e@�ZXdNdO� ZYdPdQ� ZZG dRd� de@�Z[dSdT� Z\G dUd� de@�Z]G dVd� de]�Z^G dWd � d e@�Z_dXZ`ejadYk�r�ddZlbmcZcmdZd nd[d#� Zcd\d"� Zdi ZeG d]d'� d'�ZfG d^d(� d(ef�Zgdahd_d`� Zidajdadb� Zkdaldcdd� Zmdandedf� ZoG dgdh� dh�Zpdidj� Zqddkdl�Zrdmdn� Zse
jtdok�r�ddplumvZvmwZw dqdr� Zxdsdt� Zydudv� Zzdwd$� Z{n6ejadYk�r�dxdy� Z|dzd$� Z{d{d|� Z}d}dv� ZzneqZ{erZzdS )�a�
An extensible library for opening URLs using a variety of protocols
The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below). It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.
The OpenerDirector manages a collection of Handler objects that do
all the actual work. Each Handler implements a particular protocol or
option. The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL. For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns. The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.
urlopen(url, data=None) -- Basic usage is the same as original
urllib. pass the url and optionally data to post to an HTTP URL, and
get a file-like object back. One difference is that you can also pass
a Request instance instead of URL. Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.
build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers. Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate. If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.
install_opener -- Installs a new opener as the default opener.
objects of interest:
OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.
Request -- An object that encapsulates the state of a request. The
state can be as simple as the URL. It can also include extra HTTP
headers, e.g. a User-Agent.
BaseHandler --
internals:
BaseHandler and parent
_call_chain conventions
Example usage:
import urllib.request
# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
uri='https://mahler:8092/site-updates.py',
user='klem',
passwd='geheim$parole')
proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})
# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
urllib.request.CacheFTPHandler)
# install it
urllib.request.install_opener(opener)
f = urllib.request.urlopen('http://www.python.org/')
� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote�
_splittype�
_splithost�
_splitport�
_splituser� _splitpasswd�
_splitattr� _splitquery� _splitvalue� _splittag� _to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfddl }|�dtd� |dk r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt dkr�t
� a } nt } | � | ||�S ) a$
Open the URL url, which can be either a string or a Request object.
*data* must be an object specifying additional data to be sent to
the server, or None if no such data is needed. See Request for
details.
urllib.request module uses HTTP/1.1 and includes a "Connection:close"
header in its HTTP requests.
The optional *timeout* parameter specifies a timeout in seconds for
blocking operations like the connection attempt (if not specified, the
global default timeout setting will be used). This only works for HTTP,
HTTPS and FTP connections.
If *context* is specified, it must be a ssl.SSLContext instance describing
the various SSL options. See HTTPSConnection for more details.
The optional *cafile* and *capath* parameters specify a set of trusted CA
certificates for HTTPS requests. cafile should point to a single file
containing a bundle of CA certificates, whereas capath should point to a
directory of hashed certificate files. More information can be found in
ssl.SSLContext.load_verify_locations().
The *cadefault* parameter is ignored.
This function always returns an object which can work as a context
manager and has methods such as
* geturl() - return the URL of the resource retrieved, commonly used to
determine if a redirect was followed
* info() - return the meta-information of the page, such as headers, in the
form of an email.message_from_string() instance (see Quick Reference to
HTTP Headers)
* getcode() - return the HTTP status code of the response. Raises URLError
on errors.
For HTTP and HTTPS URLs, this function returns a http.client.HTTPResponse
object slightly modified. In addition to the three new methods above, the
msg attribute contains the same information as the reason attribute ---
the reason phrase returned by the server --- instead of the response
headers as it is specified in the documentation for HTTPResponse.
For FTP, file, and data URLs and requests explicitly handled by legacy
URLopener and FancyURLopener classes, this function returns a
urllib.response.addinfourl object.
Note that None may be returned if no handler handles the request (though
the default installed global OpenerDirector uses UnknownHandler to ensure
this never happens).
In addition, if proxy settings are detected (for example, when a *_proxy
environment variable like http_proxy is set), ProxyHandler is default
installed and makes sure the requests are handled through the proxy.
r NzJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.8/urllib/request.pyr0 � s2 < ��
�
c C s | a d S �N)rF )rK rL rL rM r1 � s c
C s: t | �\}}t�t| |����}|�� }|dkrN|sNtj�|�|fW 5 Q R � S |r^t|d�}n t j
dd�}|j }t �
|� |�� ||f} d}
d} d} d}
d|kr�t|d �} |r�||
|
| � |�|
�}|s�q�| t|�7 } |�|� |
d
7 }
|r�||
|
| � q�W 5 Q R X W 5 Q R X | dk�r6| | k �r6td | | f | ��| S ) aW
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
�file�wbF)�delete� ���r �content-length�Content-Length� �1retrieval incomplete: got only %i out of %i bytes)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typer\ �fp�headers�tfp�result�bs�sizerc �blocknum�blockrL rL rM r6 � sH
"��c C sD t D ](} zt�| � W q tk
r* Y qX qt dd�= tr@dadS )z0Clean up temporary files from urlretrieve calls.N)r` r[ �unlink�OSErrorrF )Z temp_filerL rL rM r7 $ s
z:\d+$c C s< | j }t|�d }|dkr&| �dd�}t�d|d�}|�� S )z�Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
rV � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host3 s r{ c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sl || _ i | _i | _d | _|| _d | _|�� D ]\}}| �||� q,|d krRt| �}|| _ || _
|rh|| _ d S rN ) rt ri �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerr{ �origin_req_host� unverifiable�method) �selfrH rI ri r� r� r� �key�valuerL rL rM �__init__E s zRequest.__init__c C s | j rd�| j| j �S | jS )Nz{}#{})�fragment�format� _full_url�r� rL rL rM rt W s zRequest.full_urlc C s( t |�| _t| j�\| _| _| �� d S rN )r r� r r� �_parse�r� rH rL rL rM rt ] s
c C s d | _ d | _d| _d S )Nrr )r� r� �selectorr� rL rL rM rt d s c C s | j S rN )r} r� rL rL rM rI j s z Request.datac C s( || j kr$|| _ | �d�r$| �d� d S )N�Content-length)r} �
has_header�
remove_header)r� rI rL rL rM rI n s
c C s
d | _ d S rN )rI r� rL rL rM rI x s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rt r rz r� r
)r� �restrL rL rM r� | s
zRequest._parsec C s | j dk rdnd}t| d|�S )z3Return a string indicating the HTTP request method.N�POST�GETr� )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S rN )rt r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s2 | j dkr| js| j| _n|| _ | j| _|| _d S )N�https)r� r~ rz rt r� )r� rz r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS rN )r� rt r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |�� < d S rN )ri �
capitalize�r� r� �valrL rL rM r� � s zRequest.add_headerc C s || j |�� < d S rN )r| r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS rN )ri r| �r� � header_namerL rL rM r� � s
�zRequest.has_headerc C s | j �|| j�||��S rN )ri �getr| )r� r� �defaultrL rL rM ru � s �zRequest.get_headerc C s | j �|d � | j�|d � d S rN )ri �popr| r� rL rL rM r� � s zRequest.remove_headerc C s | j | j�}t|�� �S rN )r| ri �listr )r� �hdrsrL rL rM � header_items� s zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrt �setter�deleterrI r� r� r� r� r� r� r� r� ru r� r� rL rL rL rM r C s8 �
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )N�Python-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sT t |d�stdt|� ��d}t|�D �]}|dkr6q&|�d�}|d |� }||d d � }|�d�r�|�d�| d }||d d � }z t|�}W n tk
r� Y nX | j� |i �} | | j|< n>|dkr�|}| j
} n*|d kr�|}| j } n|d
kr&|}| j } nq&| �
|g �}
|
�r"t�|
|� n
|
�|� d }q&|�rPt�| j|� |�| � d S ) N�
add_parentz%expected BaseHandler instance, got %rF)�redirect_request�do_open�
proxy_open�_rV �errorrG �responsery T)�hasattr� TypeErrorr� �dir�find�
startswithrb rB r� r� r� r� r� �
setdefault�bisectZinsortra r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sL
�
zOpenerDirector.add_handlerc C s d S rN rL r� rL rL rM �close� s zOpenerDirector.closec G s< |� |d�}|D ]&}t||�}||� }|d k r| S qd S )NrL )r� r� ) r� �chainr� � meth_name�argsr� r� �funcrk rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }| j�|g �D ]}t||�}||�}qJt �
d|j |j|j |�
� � | �||�} |d }| j�|g �D ]}t||�}||| �} q�| S )NZ_requestzurllib.RequestZ _response)�
isinstance�strr rI rJ r� r� r� r� �sys�auditrt ri r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s$
zOpenerDirector.openc C sP | � | jdd|�}|r|S |j}| � | j||d |�}|r>|S | � | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rk r� rL rL rM r� s$
� ��
�zOpenerDirector._openc G s~ |dkr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S )
N��httpr� r� r: z
http_error_%srV Z_errorr r� �http_error_default)r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrk rL rL rM r� & s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|�
t� t� }|D ]B}| D ]8}t|t�rht||�r||�|� qDt||�rD|�|� qDq<|D ]}|�|� q�|D ]}|�|� � q�| D ] }t|t�r�|� }|�|� q�|S )a* Create an opener object from a list of handlers.
The opener will use several default handlers, including support
for HTTP, FTP and when applicable HTTPS.
If any of the handlers passed as arguments are subclasses of the
default handlers, the default handlers will not be used.
�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientra rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 ? s8 �
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r �� c C s
|| _ d S rN )�parent)r� r� rL rL rM r� f s zBaseHandler.add_parentc C s d S rN rL r� rL rL rM r� i s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__m s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r c s c @ s e Zd ZdZdZdd� ZeZdS )r/ z Process HTTP error responses.i� c C sH |j |j|�� }}}d| kr,dk sDn | j�d|||||�}|S )N�� �, r� )�code�msgrZ r� r� )r� ry r� r� r� r� rL rL rM �
http_responsez s �z HTTPErrorProcessor.http_responseN)r� r� r� �__doc__r� r� �https_responserL rL rL rM r/ v s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S rN )r rt )r� r� rh r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c st |� � }|dkr|dks:|dkr(|dks:t|j||||��|�dd�}d� � fdd �|j�� D �}t|||jd
d �S ) a� Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
)�- �. �/ i3 )r� ZHEAD)r� r� r� r� � z%20)rT z content-typec s" i | ]\}}|� � � kr||�qS rL )rx ��.0�k�v�ZCONTENT_HEADERSrL rM �
<dictcomp>� s � z8HTTPRedirectHandler.redirect_request.<locals>.<dictcomp>T)ri r� r� )r� r rt �replaceri r r r� ) r� r� rh r� r� ri �newurl�mZ
newheadersrL r rM r� � s
�� �z$HTTPRedirectHandler.redirect_requestc
C sL d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|jsn|jrnt|�}d|d< t|�}t|dtj d�}t
|j |�}| � ||||||�}|d kr�d S t
|d ��r|j } |_| �|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| �|d
�d | |< |�� |�� | jj||jd �S )
N�location�uri�r� r� �ftprr z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rV �rJ )r �schemer r\ Znetlocr� r r �stringZ punctuationr rt r� r� r
r� � max_repeatsrd �max_redirections�inf_msgrc r� r� rG rJ )
r� r� rh r� r� ri r �urlparts�newZvisitedrL rL rM �http_error_302� sT
� � � �z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r �http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c
C s� t | �\}}|�d�s d}| }nZ|�d�s6td| ��d|krV|�d�}|�d|�}n |�dd�}|dkrnd}|d|� }t|�\}}|dk r�t|�\}} nd }} ||| |fS )a Return (scheme, user, password, host/port) given a URL or an authority.
If a URL is supplied, it must have an authority (host:port) component.
According to RFC 3986, having an authority component means the URL must
have two slashes after the scheme.
r
N�//z proxy URL with no authority: %r�@r: rS )r r� rB r� r r )
�proxyr Zr_scheme� authorityZhost_separator�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s$
r" c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C sP |d krt � }|| _|�� D ].\}}|�� }t| d| ||| jfdd�� q d S )Nz%s_openc S s || ||�S rN rL )�rr r� r� rL rL rM �<lambda>) s z'ProxyHandler.__init__.<locals>.<lambda>)r5 �proxiesr rx �setattrr� )r� r& r� rH rL rL rM r� ! s
�zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } t�| �� ��d�}
|� dd|
� t|�}|�
||� ||ks�|dkr�d S | j j ||j
d�S d S )N�%s:%s�ascii�Proxy-authorization�Basic r� r )r� r" rz � proxy_bypassr
�base64� b64encode�encode�decoder� r� r� rG rJ ) r� r� r r� Z orig_typeZ
proxy_typer r! r Z user_passZcredsrL rL rM r� , s" � zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S rN )�passwdr� rL rL rM r� J s zHTTPPasswordMgr.__init__c s\ t |t�r|g}|�jkr$i �j|< dD ].� t� �fdd�|D ��}||f�j| |< q(d S )N�TFc 3 s | ]}�� |� �V qd S rN )�
reduce_uri)r� �u�� default_portr� rL rM � <genexpr>T s z/HTTPPasswordMgr.add_password.<locals>.<genexpr>)r� r� r1 �tuple)r� �realmr r r1 � reduced_urirL r5 rM � add_passwordM s
�z HTTPPasswordMgr.add_passwordc C s` | j �|i �}dD ]H}| �||�}|�� D ].\}}|D ] }| �||�r6| S q6q*qdS )Nr2 �NN)r1 r� r3 r � is_suburi) r� r9 �authuriZdomainsr6 �reduced_authuriZurisZauthinfor rL rL rM �find_user_passwordX s z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d}|}d}t|�\}}|r~|dkr~|dk r~ddd��|�} | dk r~d || f }||fS )
z@Accept authority or URI and extract only the authority and path.rV r r: r
N�P i� r� z%s:%d)r r
r� )
r� r r6 �partsr r r\ rz �portZdportrL rL rM r3 b s$ �� zHTTPPasswordMgr.reduce_uric C sN ||kr dS |d |d kr dS |d }|dd� dkr@|d7 }|d � |�S )zcCheck if test is below base in a URI tree
Both args must be URIs in reduced form.
Tr FrV rS Nr
)r� )r� �base�test�prefixrL rL rM r= y s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r; r@ r3 r= rL rL rL rM r H s
c @ s e Zd Zdd� ZdS )r! c C s0 t �| ||�\}}|d k r"||fS t �| d |�S rN )r r@ )r� r9 r> r r! rL rL rM r@ � s �z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� r@ rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S rN )�
authenticated�superr� �r� r� �kwargs�� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | � ||� |d k r&t� �d |||� t� �||||� d S rN )�update_authenticatedrH r; )r� r9 r r r1 �is_authenticatedrK rL rM r; � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C s> t |t�r|g}dD ]$}|D ]}| �||�}|| j|< q qd S �Nr2 )r� r� r3 rG )r� r rN r6 r4 r: rL rL rM rM � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD dD ]:}| � ||�}| jD ]"}| �||�r| j| S qqd S rO )r3 rG r= )r� r> r6 r? r rL rL rM rN � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r; rM rN �
__classcell__rL rL rK rM r" � s
c @ sT e Zd Ze�dej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S rN )r r1 r; )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c sp d}t j�|�D ]6}|�� \}}}|dkr8t�dtd� ||fV d}q|sl|r^|�� d }nd}|d fV d S )NF)�"�'z Basic Auth Realm was unquoted� Tr rr )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r9 rL rL rM � _parse_realm� s �
z%AbstractBasicAuthHandler._parse_realmc C s~ |� |�}|sd S d }|D ]H}| �|�D ]8\}}|�� dkrB|}q(|d k r(| �|||� S q(q|d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allrZ rx �retry_http_basic_authrB ) r� �authreqrz r� ri Z unsupportedrY r r9 rL rL rM �http_error_auth_reqed� s
�z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j �||�\}}|d k rtd||f }dt�|�� ��d� }|�| jd �|krTd S |�| j|� | j j
||j d�S d S d S )Nr( r+ r) r ) r1 r@ r- r. r/ r0 ru � auth_headerr� r� rG rJ )r� rz r� r9 r �pw�raw�authrL rL rM r\ � s z.AbstractBasicAuthHandler.retry_http_basic_authc C st t | jd�r| j�|j�s |S |�d�sp| j�d |j�\}}d�||��� }t� |��
� }|� dd�|� � �� |S )NrN �
Authorizationz{0}:{1}zBasic {})
r� r1 rN rt r� r@ r� r/ r- Zstandard_b64encoder0 r� �strip)r� r� r r1 Z credentialsZauth_strrL rL rM � http_request s �
�z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j kr"dk r8n n| j�|jd� n| j�|jd� |S )NrN r� r� TF)r� r1 r� rM rt )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�IrT r� rZ r^ r\ re r� �
https_requestr� rL rL rL rM r# � s �
c @ s e Zd ZdZdd� ZdS )r$ rc c C s |j }| �d|||�}|S )N�www-authenticate)rt r^ )r� r� rh r� r� ri rH r� rL rL rM �http_error_401$ s �z#HTTPBasicAuthHandler.http_error_401N)r� r� r� r_ rk rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% r* c C s |j }| �d|||�}|S �N�proxy-authenticate)rz r^ )r� r� rh r� r� ri r r� rL rL rM �http_error_407/ s �z$ProxyBasicAuthHandler.http_error_407N)r� r� r� r_ rn rL rL rL rM r% + s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S �Nr )r r1 r; �retried� nonce_count�
last_nonce)r� r1 rL rL rM r� I s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S ro )rp r� rL rL rM �reset_retry_countR s z+AbstractDigestAuthHandler.reset_retry_countc C s| |� |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|�� d }|�� dkr`| �||�S |�� dkrxtd| ��d S ) N� i� zdigest auth failedrV r Zdigestr[ zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rp r rt rX rx �retry_http_digest_authrB )r� r_ rz r� ri r] r rL rL rM r^ U s
� �z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |� dd�\}}ttd t|���}| �||�}|rvd| }|j�| jd �|krRd S |�| j|� | j j
||j d�}|S d S )Nr� rV z Digest %sr ) rX �parse_keqv_list�filter�parse_http_list�get_authorizationri r� r_ r� r� rG rJ )r� r� rb �tokenZ challenge�chalZauth_valZresprL rL rM ru i s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |t�� f }|�d�td� }t�|��� }|d d� S )Nz %s:%s:%s:r) � � )rq �time�ctimer/ � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceu s z$AbstractDigestAuthHandler.get_cnoncec C s� z6|d }|d }|� d�}|� dd�}|� dd �}W n tk
rL Y d S X | �|�\}} |d krhd S | j�||j�\}
} |
d kr�d S |jd k r�| �|j|�} nd } d|
|| f }
d|�� |j f }|d kr�| ||
�d|||�f �}n~d |�
d
�k�r\|| j k�r| j d 7 _ n d | _ || _ d | j }| �
|�}d
|||d ||�f }| ||
�|�}n td| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr9 r� �qop� algorithm�MD5�opaquez%s:%s:%sr( rb �,rV z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr1 r@ rt rI �get_entity_digestr� r� rX rr rq r� r )r� r� r{ r9 r� r� r� r� �H�KDr r` ZentdigZA1ZA2ZrespdigZncvalueZcnonceZnoncebitrD rL rL rM ry � s\
�
�� z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nr� c S s t �| �d���� S �Nr) )r� Zmd5r/ r� ��xrL rL rM r% � � z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t �| �d���� S r� )r� r� r/ r� r� rL rL rM r% � r� z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nr( rL )r� �d�r� rL rM r% � r� )rB )r� r� r� rL r� rM r� � s
� z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S rN rL )r� rI r{ rL rL rM r� � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� rs r^ ru r� ry r� r� rL rL rL rM r& > s
>
c @ s e Zd ZdZdZdZdd� ZdS )r' z�An authentication protocol defined by RFC 2069
Digest authentication improves on basic authentication because it
does not transmit passwords in the clear.
rc �� c C s* t |j�d }| �d|||�}| �� |S )NrV rj )r rt r^ rs �r� r� rh r� r� ri rz �retryrL rL rM rk � s �z$HTTPDigestAuthHandler.http_error_401N)r� r� r� r� r_ r� rk rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( �Proxy-Authorizationr� c C s" |j }| �d|||�}| �� |S rl )rz r^ rs r� rL rL rM rn � s �z%ProxyDigestAuthHandler.http_error_407N)r� r� r� r_ r� rn rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S rN �� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S rN r� )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jj�|j|�� �S rN )r� r� �HTTPConnection�_get_content_lengthrI r� �r� ry rL rL rM r� � s �z'AbstractHTTPHandler._get_content_lengthc C s |j }|std��|jd k r�|j}t|t�r8d}t|��|�d�sN|�dd� |�d�s�|�d�s�| �|�}|d k r�|�dt|�� n |�dd� |}|� � r�t
|j �\}}t |�\}} |�d�s�|�d|� | j
jD ]&\}
} |
�� }
|�|
�s�|�|
| � q�|S ) N�
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-type�!application/x-www-form-urlencodedr� �Transfer-encodingZchunkedrs )rz r rI r� r� r� r� r� r� r� r r� r r� r� r� ) r� ry rz rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr_ r� rL rL rM � do_request_� sJ
�
�
� �
z AbstractHTTPHandler.do_request_c
sT |j }|std��||fd|ji|��}|�| j� t|j�� � �� fdd�|j� � D �� d� d< dd� � � � D �� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � z`z&|j |�
� |j|j� |�d
�d � W n, tk
�r } z t|��W 5 d }~X Y nX |�� } W n |�� � Y nX |j�r>|j�� d |_|�� | _| j| _| S )
z�Return an HTTPResponse object for the request, using http_class.
http_class must implement the HTTPConnection API from http.client.
r� rJ c s i | ]\}}|� kr||�qS rL rL r� �ri rL rM r / s � z/AbstractHTTPHandler.do_open.<locals>.<dictcomp>r� �
Connectionc S s i | ]\}}|� � |�qS rL )�title)r� r_ r� rL rL rM r < s r� r� r� )Zencode_chunkedN)rz r rJ Zset_debuglevelr� r� r| �updateri r r~ Z
set_tunnelry r� r� rI r� rq � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrz r� Ztunnel_headersZproxy_auth_hdr�errr$ rL r� rM r� ! sB
�
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r� r� r� r� rL rL rL rM r� � s
&r� c @ s e Zd Zdd� ZejZdS )r) c C s | � tjj|�S rN )r� r� r� r� �r� r� rL rL rM � http_openf s zHTTPHandler.http_openN)r� r� r� r� r� r� re rL rL rL rM r) d s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t �| |� || _|| _d S rN )r� r� �_context�_check_hostname)r� r� r> �check_hostnamerL rL rM r� o s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� r� rL rL rM �
https_opent s �zHTTPSHandler.https_open)r NN)r� r� r� r� r� r� r� ri rL rL rL rM rE m s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|j�� }|| _d S ro )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� } s
z HTTPCookieProcessor.__init__c C s | j �|� |S rN )r� Zadd_cookie_headerr� rL rL rM re � s z HTTPCookieProcessor.http_requestc C s | j �||� |S rN )r� Zextract_cookies)r� ry r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� re r� ri r� rL rL rL rM r | s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sN i }| D ]@}|� dd�\}}|d dkr@|d dkr@|dd� }|||< q|S )z>Parse list of key=value strings where keys are not duplicated.�=rV r rQ rS )rX )�lZparsedZeltr� r rL rL rM rv � s
rv c C s� g }d}d }}| D ]l}|r*||7 }d}q|rT|dkr>d}qn |dkrJd}||7 }q|dkrl|� |� d}q|dkrxd}||7 }q|r�|� |� dd� |D �S ) ap Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Neither commas nor quotes count if they are escaped.
Only double-quotes count, not single-quotes.
rr F�\TrQ r� c S s g | ] }|� � �qS rL )rd )r� �partrL rL rM �
<listcomp>� s z#parse_http_list.<locals>.<listcomp>)ra )r� �resr� �escaper ZcurrL rL rM rx � s4
rx c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| �� krXtd��n
| �|�S d S )Nr: r rS r
� localhost�-file:// scheme is supported only on localhost)r� rz � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &�
zFileHandler.file_openNc C s` t jd krZz*tt�d�d t�t�� �d �t _W n$ tjk
rX t�d�ft _Y nX t jS )Nr� r: )r* �namesr8 r� �gethostbyname_ex� gethostname�gaierror�
gethostbynamer� rL rL rM r� � s
��
zFileHandler.get_namesc
C s� dd l }dd l}|j}|j}t|�}z�t�|�}|j}|jj |j
dd�} |� |�d }
|� d|
pbd|| f �} |r~t
|�\}} |r�| s�t|�| �� kr�|r�d| | }
nd| }
tt|d�| |
�W S W n* tk
r� } z t|��W 5 d }~X Y nX td��d S ) Nr T�Zusegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
�
text/plain�file://�rbzfile not on local host)� email.utils� mimetypesrz r� r4 r[ �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rq r )r� r� �emailr� rz rf Z localfile�statsrm �modified�mtyperi rC Zorigurl�exprL rL rM r� � s:
�� ��zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s* z t �| �W S t jk
r$ Y d S X d S rN )r� r� r� )rz rL rL rM r� � s r� c @ s e Zd Zdd� Zdd� ZdS )r+ c
C s* dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}zt
� |�}W n* t k
r� } z t|��W 5 d }~X Y nX t
|j�\} }
| �d�} ttt | ��} | d d� | d } } | �r| d �s| dd � } z�| �||||| |j�}
| �r6d�p8d}|
D ]2}t|�\}}|�� d k�r>|d
k�r>|�� }�q>|
�| |�\}}d}|�|j�d }|�r�|d | 7 }|d k �r�|dk�r�|d | 7 }t�|�}t |||j�W S |j k
�r$ } z"td
| �}|� t � � d ��W 5 d }~X Y nX d S )Nr �ftp error: no host givenrr r
rS rV rh �Dr� ��a�Ar� rh r� r� zContent-type: %s
zContent-length: %d
�
ftp error: %rr: )!�ftplibr� rz r r
�FTP_PORTrb r r r
r� r� rq r r� rX r� �map� connect_ftprJ r rx �upper�retrfiler� rt r� r� r �
all_errors�with_tracebackr� �exc_info)r� r� r� r� rz rC r r1 r� r\ �attrs�dirsrO �fwr� �attrr� rh �retrlenri r� r� �excrL rL rM �ftp_open s^
�
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r1 rz rC r� rJ rL rL rM r� 7 s �zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< r} )�cacherJ �soonest�delay� max_connsr� rL rL rM r� > s
zCacheFTPHandler.__init__c C s
|| _ d S rN )r� )r� �trL rL rM �
setTimeoutE s zCacheFTPHandler.setTimeoutc C s
|| _ d S rN )r� )r� r rL rL rM � setMaxConnsH s zCacheFTPHandler.setMaxConnsc C sr |||d� |�|f}|| jkr4t�� | j | j|< n,t||||||�| j|< t�� | j | j|< | �� | j| S )Nr
)�joinr� r~ r� rJ r� � check_cache)r� r r1 rz rC r� rJ r� rL rL rM r� K s
�
zCacheFTPHandler.connect_ftpc C s� t � � }| j|krPt| j�� �D ].\}}||k r | j| �� | j|= | j|= q tt| j�� ��| _t | j�| j
kr�t| j�� �D ]&\}}|| jkr�| j|= | j|= q�q�tt| j�� ��| _d S rN ) r~ r� r� rJ r r� r� �min�valuesrd r� )r� r� r� r rL rL rM r� V s
zCacheFTPHandler.check_cachec C s0 | j �� D ] }|�� q
| j �� | j�� d S rN )r� r� r� �clearrJ )r� �connrL rL rM � clear_cachej s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r� r rL rL rL rM r, ; s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|�dd�\}}|�dd�\}}t|�}|�d�rNt�|�}|d d� }|sVd}t�d|t|�f �}t t
� |�||�S )N�:rV r� z;base64i�����text/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
) rt rX r �endswithr- � decodebytesr� r� rd r �io�BytesIO)r� r� rH r rI Z mediatyperi rL rL rM � data_openq s
�zDataHandler.data_openN)r� r� r� r rL rL rL rM r- p s r� �nt)r4 r3 c C s t | �S )zOS-specific conversion from a relative URL of the 'file' scheme
to a file system path; not recommended for general use.)r
��pathnamerL rL rM r4 � s c C s t | �S )zOS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use.)r r rL rL rM r3 � s c @ s� e Zd ZdZdZde Zd*dd�Zdd� Zdd � Z d
d � Z
d d
� Z d+dd�Z d,dd�Z
d-dd�Zd.dd�Zdd� Zd/dd�Zd0dd�Zd d � Zer�d d � Zd1d d!�Zd"d#� Zd$d%� Zd&d'� Zd2d(d)�ZdS )3r8 a, Class to open URLs.
This is a class rather than just a subroutine because we may need
more than one set of global protocol-specific options.
Note -- this is a base class for those who don't want the
automatic handling of errors type 302 (relocated) and 401
(authorization needed).Nr� c K sz dd| j ji }tj|tdd� |d kr.t� }|| _|�d�| _|�d�| _ d| j
fdg| _ g | _ t
j| _d | _t| _d S ) NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classrS )�
stacklevel�key_file� cert_filez
User-Agent)ZAcceptz*/*)rL r� r? r@ rA r5 r& r� r r �versionr� �_URLopener__tempfilesr[ rp �_URLopener__unlink� tempcache�ftpcache)r� r& Zx509r� rL rL rM r� � s
� zURLopener.__init__c C s | � � d S rN )r� r� rL rL rM �__del__� s zURLopener.__del__c C s | � � d S rN )�cleanupr� rL rL rM r� � s zURLopener.closec C sV | j rB| j D ](}z| �|� W q tk
r2 Y q X q | j d d �= | jrR| j�� d S rN )r r rq r r )r� rO rL rL rM r � s
zURLopener.cleanupc G s | j �|� dS )zdAdd a header to be used by the HTTP interface only
e.g. u.addheader('Accept', 'sound/basic')N)r� ra )r� r� rL rL rM � addheader� s zURLopener.addheaderc
C sp t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd}d| } || _ | �
dd�} t | | �r�| d kr�|r�| � |||�S | �
||�S z0|dk�r t| | �|�W S t| | �||�W S W nV ttfk
�r0 � Y n< tk
�rj }
z td
|
��t�� d ��W 5 d}
~
X Y nX dS ) z6Use URLopener().open(file) instead of open(file, 'r').z%/:=&?~#+!$,;'@()*[]|�r r� rO NZopen_�-r� r� z socket errorr: )r r r r rG r r r& r r� r r� �open_unknown_proxy� open_unknownr� r r rq r� r� r� )r� r� rI rf ri rh �urltyperH r � proxyhostrz r� r_ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��dS )�/Overridable interface to open unknown URL type.� url errorzunknown url typeN�r rq )r� r� rI r� rH rL rL rM r
s zURLopener.open_unknownc C s t |�\}}tdd| |��dS )r r zinvalid proxy for %sNr! )r� r r� rI r� rH rL rL rM r s z URLopener.open_unknown_proxyc
C s t t|��}| jr&|| jkr&| j| S t|�\}}|dkr�|rF|dkr�z0| �|�}|�� }|�� tt|�d �|fW S t k
r� } zW 5 d} ~ X Y nX | �
||�}�z<|�� }
|r�t
|d�} nrt|�\} }
t|
p�d�\} }
t |
p�d�\}
} t |
p�d�\}
} t
j�|
�d }t�|�\}}| j�|� t
�|d�} z�||
f}| jdk �rT|| j|< d}d}d}d}d |
k�rzt|
d
�}|�r�||||� |�|�}|�s��q�|t|�7 }| �|� |d7 }|�r�||||� �q�W 5 | �� X W 5 |�� X |dk�r||k �rtd ||f |��|S ) ztretrieve(url) returns (filename, headers) for a local object
or (tempfilename, headers) for a remote object.NrO rV rP rr rR rS r rT rU rW )r r r r r� rZ r� r4 r rq rG r r r[ r\ �splitextr^ Zmkstempr ra �fdopenrb rc rd re r )r� rH rf rg rI r� Zurl1rh r� r� ri rj Zgarbager\ �suffix�fdrk rl rm rc rn ro rL rL rM �retrieve sn
��zURLopener.retrievec C s$ d}d}t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d}| �� dkrvd}n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t �
|� � �� d�} nd} |�rt|�}t �
|� � �� d�} nd} ||�}
i }| �r*d| |d< | �r<d| |d < |�rJ||d
< d |d < | j
D ]\}}|||< �qX|dk �r�d
|d< |
�d|||� n|
jd||d� z |
�� }W n" tjjk
�r� td��Y nX d|j k�r�dk �rn nt||jd| |j�S | �||j|j|j|j|�S dS )a� Make an HTTP connection using connection_class.
This is an internal method that should be called from
open_http() or open_https().
Arguments:
- connection_factory should take a host name and return an
HTTPConnection instance.
- url is the url to retrieval or a host, relative-path pair.
- data is payload for a POST request or None.
Nr� z %s://%s%sz
http errorr� r) zBasic %sr� rc rs r� r� r� z Content-Typer� r� r� z$http protocol error: bad status liner� r� �http:)r� r� r r r
r rx r, rq r- r. r/ r0 r� ry r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrh r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrz r� Zrealhostr r� Z
proxy_authrb Z http_connri rY r� r� rL rL rM �_open_generic_httpV s~
� �z URLopener._open_generic_httpc C s | � tjj||�S )zUse HTTP protocol.)r) r� r� r� �r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|dkr6||||||�} n|||||||�} | rP| S | �|||||�S )z�Handle http errors.
Derived class can override this, or provide specific handlers
named http_error_DDD where DDD is the 3-digit error code.z
http_error_%dN)r� r� r� )
r� rH rh �errcode�errmsgri rI r_ r� rk rL rL rM r( � s
zURLopener.http_errorc C s |� � t||||d��dS )z>Default error handler: close the connection and raise OSError.N)r� r �r� rH rh r, r- ri rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r r )r� r� r� r r )r� rz rL rL rM �_https_connection� s �zURLopener._https_connectionc C s | � | j||�S )zUse HTTPS protocol.)r) r/ r* rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|dd� dkrP|dd� dkrP|dd� �� dkrPtd ��n
| �|�S dS )
z/Use local file or FTP depending on form of URL.zEfile error: proxy support for file protocol currently not implementedNr: r rS r
� z
localhost/r� )r� r� r rx rB r� r� rL rL rM � open_file� s
4
zURLopener.open_filec
C s\ ddl }ddl}t|�\}}t|�}zt�|�}W n0 tk
rb } zt|j|j ��W 5 d}~X Y nX |j
} |j j |j
dd�}
|�|�d } |�d| p�d| |
f �} |s�|}
|dd� dkr�d | }
tt|d
�| |
�S t|�\}}|�sPt�|�t� ft� k�rP|}
|dd� dk�r d | }
n |dd � d k�r>td
| ��tt|d
�| |
�S td��dS )zUse local file.r NTr� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
r� rV r
r� r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 r[ r� rq r �strerrorrf r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rz rO Z localnamer� �erm r� r� ri ZurlfilerC rL rL rM r� � s@ �� �
zURLopener.open_local_filec
C s� t |t�std��ddl}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd}t|�}t|ppd�}t|p|d�}t �
|�}|s�ddl }|j }nt
|�}t|�\}} t|�}|�d�}
|
dd� |
d }
} |
r�|
d s�|
dd� }
|
�r
|
d �s
d|
d< |||d�|
�f} t| j�tk�rbt| j�D ]*}
|
| k�r6| j|
}| j|
= |�� �q6z�| | jk�r�t|||||
�| j| < | �s�d }nd
}| D ]2}t|�\}}|�� d k�r�|d k�r�|�� }�q�| j| �| |�\}}|�d
| �d }d}|�r |d| 7 }|dk �r,|dk�r,|d| 7 }t � |�}t ||d
| �W S t � k
�r� } z td| �� t!�"� d ��W 5 d}~X Y nX dS )zUse FTP protocol.zCftp error: proxy support for ftp protocol currently not implementedr Nr� rr r
rS rV r� rh r� r� zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: )#r� r� r r� r r
r r r
r� r� r� r� rb r rX r� rd r � MAXFTPCACHEr� r� r� r rx r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rz r\ rC r r1 r� r� r� rO r� r� r r� r� r� rh r� r� ri r� rL rL rM �open_ftp� st
� �
zURLopener.open_ftpc
C s< t |t�std��z|�dd�\}}W n tk
rD tdd��Y nX |sNd}|�d�}|dkr�d ||d
� kr�||d d
� }|d
|� }nd }g }|�d t� d
t�
t�� �� � |�d| � |dkr�t � |�
d���d�}nt|�}|�dt|� � |�d � |�|� d�|�}t�|�}t�|�}t|||�S )zUse "data" URL.zEdata error: proxy support for data protocol currently not implementedr� rV z
data errorz bad data URLr �;r r� Nrr zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr- r) zlatin-1zContent-Length: %d�
)r� r� r rX rB rq �rfindra r~ �strftime�gmtimer- r r/ r0 r
rd r� r� r� r �StringIOr ) r� rH rI r� Zsemir r� ri �frL rL rM � open_data8 s8
�
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r� r r� r r� r r� r r rG r r r& r) r+ r( r� rC r/ r0 r2 r� r8 r@ rL rL rL rM r8 � s.
$
A\
:c @ s� e Zd ZdZdd� Zdd� Zd#dd�Zd d
� Zd$d d �Zd%d
d�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd�Zd,d d �Zd-d d �Zd!d"� ZdS ).r9 z?Derived class with handlers for errors we can handle (perhaps).c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtriesrI rL rL rM r� e s zFancyURLopener.__init__c C s t ||d| |�S )z3Default error handling -- don't raise an exception.r' )r r. rL rL rM r� k s z!FancyURLopener.http_error_defaultNc C sv | j d7 _ zZ| jrN| j | jkrNt| d�r4| j}n| j}|||dd|�W � S | �||||||�}|W �S d| _ X dS )z%Error 302 -- relocated (temporarily).rV r �http_error_500r� z)Internal Server Error: Redirect RecursionN)rB rC r� rD r� �redirect_internal) r� rH rh r, r- ri rI r� rk rL rL rM r o s
� �z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |� � t| jd | |�}t|�}|jdkrnt|||d| ||��| �|�S )Nr r r r z( Redirection to url '%s' is not allowed.)r� r r� r r r rG ) r� rH rh r, r- ri rI r r rL rL rM rE � s"
� �z FancyURLopener.redirect_internalc C s | � ||||||�S )z*Error 301 -- also relocated (permanently).�r �r� rH rh r, r- ri rI rL rL rM r � s z FancyURLopener.http_error_301c C s | � ||||||�S )z;Error 303 -- also relocated (essentially identical to 302).rF rG rL rL rM r � s z FancyURLopener.http_error_303c C s2 |dkr | � ||||||�S | �|||||�S dS )z1Error 307 -- relocated, but turn POST into error.N)r r� rG rL rL rM r � s z FancyURLopener.http_error_307Fc
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )z_Error 401 -- authentication required.
This function supports Basic authentication only.rj �![ ]*([^ ]+)[ ]+realm="([^"]*)"r[ Zretry_� _basic_authN�r8 r� rf �matchrV rx r� r� �
r� rH rh r, r- ri rI r� ZstuffrK r r9 r_ rL rL rM rk � s:
�
�
��z FancyURLopener.http_error_401c
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |dkr�t| | �|| �S t| | �|| |�S dS )zeError 407 -- proxy authentication required.
This function supports Basic authentication only.rm rH r[ Z retry_proxy_rI NrJ rL rL rL rM rn � s:
�
�
��z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�http://r� r rV �%s:%s@%srr r �r r& r r� �get_user_passwdr rG �r� rH r9 rI rz r� r r r r Z
proxyselectorr� r r1 rL rL rM �retry_proxy_http_basic_auth� s$
�
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�https://r� r rV rN rr r rO rQ rL rL rM � retry_proxy_https_basic_auth� s$
�
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rN rr r rM �r r� rP r rG �
r� rH r9 rI rz r� r� r r1 r rL rL rM r\ s
�
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rN rr r rS rU rV rL rL rM �retry_https_basic_auth s
�
z%FancyURLopener.retry_https_basic_authr c C s` |d |� � }|| jkr2|r(| j|= n
| j| S | �||�\}}|sJ|rX||f| j|< ||fS )Nr )rx rA �prompt_user_passwd)r� rz r9 r r� r r1 rL rL rM rP s
z FancyURLopener.get_user_passwdc C sX ddl }z.td||f �}|� d|||f �}||fW S tk
rR t� Y dS X dS )z#Override this in a GUI environment!r Nz Enter username for %s at %s: z#Enter password for %s in %s at %s: r< )�getpass�input�KeyboardInterrupt�print)r� rz r9 rY r r1 rL rL rM rX ) s �
z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r� r rE r r r rk rn rR rT r\ rW rP rX rL rL rL rM r9 b s(
�
�
c C s t dkrt�d�a t S )z8Return the IP address of the magic hostname 'localhost'.Nr� )�
_localhostr� r� rL rL rL rM r� 9 s
r� c C sP t dkrLztt�t�� �d �a W n( tjk
rJ tt�d�d �a Y nX t S )z,Return the IP addresses of the current host.Nr: r� )� _thishostr8 r� r� r� r� rL rL rL rM r4 A s r4 c C s t dkrddl} | ja t S )z1Return the set of errors raised by the FTP class.Nr )�
_ftperrorsr� r� )r� rL rL rM r7 L s r7 c C s t dkrt�d�a t S )z%Return an empty email Message object.Nrr )�
_noheadersr� r� rL rL rL rM � noheadersU s
ra c @ sJ e Zd ZdZddd�Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r� z;Class used by open_ftp() for cache of open FTP connections.NTc C sX || _ || _|| _|| _|| _|| _d| _|| _z | �� W n | � � � Y nX d S ro )
r r1 rz rC r� rJ �refcount� keepalive�initr� )r� r r1 rz rC r� rJ r� rL rL rM r� b s zftpwrapper.__init__c C s\ dd l }d| _|�� | _| j�| j| j| j� | j�| j | j
� d� | j �}| j�
|� d S )Nr r
)r� �busyZFTPr Zconnectrz rC rJ Zloginr r1 r� r� �cwd)r� r� Z_targetrL rL rM rd r s
zftpwrapper.initc
C s� dd l }| �� |dkr"d}d}n d| }d}z| j�|� W n* |jk
rh | �� | j�|� Y nX d }|r�|s�z d| }| j�|�\}}W nR |jk
r� } z2t|�d d� dkr�t d | ��
t � � d
��W 5 d }~X Y nX |�s�| j�d� |�rl| j�
� } zJz| j�|� W n4 |jk
�rN } zt d | �|�W 5 d }~X Y nX W 5 | j�| � X d | }nd }| j�|�\}}d| _t|�d
�| j�}
| jd7 _|�� |
|fS )Nr )r� r� zTYPE ArV zTYPE zRETR rS Z550r� r: zLIST ZLISTr� )r� � endtransferr Zvoidcmdr� rd Z ntransfercmdZ
error_permr� r r� r� r� �pwdrf re r Zmakefile�
file_closerb r� ) r� rO r� r� �cmd�isdirr r� r� rh ZftpobjrL rL rM r� { sP
�
$
zftpwrapper.retrfilec C s
d| _ d S ro )re r� rL rL rM rg � s zftpwrapper.endtransferc C s d| _ | jdkr| �� d S )NFr )rc rb �
real_closer� rL rL rM r� � s
zftpwrapper.closec C s2 | � � | jd8 _| jdkr.| js.| �� d S )NrV r )rg rb rc rl r� rL rL rM ri � s zftpwrapper.file_closec C s2 | � � z| j�� W n t� k
r, Y nX d S rN )rg r r� r7 r� rL rL rM rl � s
zftpwrapper.real_close)NT) r� r� r� r� r� rd r� rg r� ri rl rL rL rL rM r� _ s �
-r� c C s� i } t j�� D ]4\}}|�� }|r|dd� dkr|| |dd� < qdt jkrZ| �dd� t j�� D ]J\}}|dd� dkrd|�� }|r�|| |dd� < qd| �|dd� d� qd| S )a Return a dictionary of scheme -> proxy server URL mappings.
Scan the environment for variables named <scheme>_proxy;
this seems to be the standard convention. If you need a
different way, you can pass a proxies dictionary to the
[Fancy]URLopener constructor.
i����N�_proxyZREQUEST_METHODr� )r[ �environr rx r� )r& r_ r� rL rL rM �getproxies_environment� s
ro c C s� |dkrt � }z |d }W n tk
r0 Y dS X |dkr>dS | �� } t| �\}}|�d�D ]Z}|�� }|r\|�d�}|�� }||ks�| |kr� dS d| }|�|�s�| �|�r\ dS q\dS )z�Test if proxies should not be used for a particular host.
Checks the proxy dict for the value of no_proxy, which should
be a list of comma separated DNS suffixes, or '*' for all hosts.
NZnoF�*Tr� �.)ro r� rx r
rX rd �lstripr )rz r& Zno_proxy�hostonlyrC r_ rL rL rM �proxy_bypass_environment� s*
rt c C s0 ddl m } t| �\}}dd� }d| kr4|d r4dS d}|�d d
�D ]�}|sNqDt�d |�}|dk �r|dkr�zt�|�}||�}W n tk
r� Y qDY nX ||�d ��} |�d
�}
|
dkr�d|�d �� d�d }
nt
|
d d� �}
|
dk sD|
dkr�qDd|
}
||
? | |
? k�r* dS qD|| |�rD dS qDdS )aj
Return True iff this host shouldn't be accessed using a proxy
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
{ 'exclude_simple': bool,
'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
}
r )�fnmatchc S sh | � d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nrq r� r � rV r} r: r| rS )rX r� r� rb rd )ZipAddrrB rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numrq Zexclude_simpleTN�
exceptionsrL z(\d+(?:\.\d+)*)(/\d+)?rV r: r| � F) ru r
r� rf rK r� r� rq �group�countrb ) rz �proxy_settingsru rs rC rw ZhostIPr� r rD �maskrL rL rM � _proxy_bypass_macosx_sysconf
s>
r~ �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S rN )r� r~ )rz r| rL rL rM �proxy_bypass_macosx_sysconfF
s r� c C s t � S )z�Return a dictionary of scheme -> proxy server URL mappings.
This function uses the MacOSX framework SystemConfiguration
to fetch the proxy information.
)r� rL rL rL rM �getproxies_macosx_sysconfJ
s r� c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or from the MacOSX framework SystemConfiguration.
N)ro rt r� �rz r& rL rL rM r, T
s
r, c C s t � p
t� S rN )ro r� rL rL rL rM r5 a
s c
C s i } z ddl }W n tk
r( | Y S X z�|�|jd�}|�|d�d }|r�t|�|d�d �}d|kr�|�d�D ]4}|�dd�\}}t�d |�s�d
||f }|| |< qtn>|dd � d kr�|| d
< n$d| | d
< d| | d< d| | d< |� � W n t
t t fk
�r Y nX | S )zxReturn a dictionary of scheme -> proxy server URL mappings.
Win32 uses the registry to store proxies.
r N�;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r9 rV z
(?:[^/:]+)://z%s://%srt r' r� z http://%sz
https://%sr� zftp://%sr )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� rX rf rK ZCloserq rB r� )r& r� �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryf
sF
�����
r� c C s t � p
t� S )z�Return a dictionary of scheme -> proxy server URL mappings.
Returns settings gathered from the environment, if specified,
or the registry.
)ro r� rL rL rL rM r5 �
s c C s| z dd l }W n tk
r" Y dS X z6|�|jd�}|�|d�d }t|�|d�d �}W n tk
rp Y dS X |rz|s~dS t| �\}}|g} z t� |�}||kr�| �
|� W n tk
r� Y nX z t� |�}||kr�| �
|� W n tk
� r� Y nX |� d�}|D ]j} | dk�r*d|k�r* dS | �
dd �} | �
d
d �} | �
d d�} | D ] }
t�| |
tj��rR dS �qR�q dS )
Nr r� r� Z
ProxyOverrider9 z<local>rq rV z\.rp z.*�?)r� r� r� r� r� r� rq r
r� r� ra ZgetfqdnrX r rf rK rh ) rz r� r� r� Z
proxyOverrideZrawHostrC ZaddrZfqdnrE r� rL rL rM �proxy_bypass_registry�
s` �����
r� c C s t � }|rt| |�S t| �S dS )z�Return True, if host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
N)ro rt r� r� rL rL rM r, �
s
)NNN)N)~r� r- r� r� r� Z http.clientr� r r[ � posixpathrf r� r r� r~ r^ rX r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD r� rC �__all__� version_infor� rF r� r0 r1 r` r6 r7 rg �ASCIIrv r{ r r r2 r r/ r r r" r r r! r" r# r$ r% �urandomr� r& r' r( r� r) r� r� rE ra r r. rv rx r* r� r+ r, r- r6 r_ Z
nturl2pathr4 r3 r r8 r9 r] r� r^ r4 r_ r7 r` ra r� ro rt r~ �platformZ_scproxyr� r� r� r� r, r5 r� r� rL rL rL rM �<module> s SP
� � U
?m $q!+@
o v
+3:5! @ W
_
%A
- 2
PK *(�ZO�E�X X & __pycache__/error.cpython-38.opt-2.pycnu �[��� U
e5dH
� @ sL d dl ZdddgZG dd� de�ZG dd� deejj�ZG dd� de�ZdS )� N�URLError� HTTPError�ContentTooShortErrorc @ s e Zd Zddd�Zdd� ZdS )r Nc C s |f| _ || _|d k r || _d S �N)�args�reason�filename)�selfr r � r
�$/usr/lib64/python3.8/urllib/error.py�__init__ s zURLError.__init__c C s
d| j S )Nz<urlopen error %s>)r �r r
r
r �__str__ s zURLError.__str__)N)�__name__�
__module__� __qualname__r r r
r
r
r r s
c @ sT e Zd ZejjjZdd� Zdd� Zdd� Z e
dd� �Z e
d d
� �Z e j
d d
� �Z d S )
r c C s: || _ || _|| _|| _|| _|d k r6| �||||� d S r )�code�msg�hdrs�fpr �_HTTPError__super_init)r Zurlr r r r r
r
r r ' s zHTTPError.__init__c C s d| j | jf S )NzHTTP Error %s: %s�r r r
r
r
r r 4 s zHTTPError.__str__c C s d| j | jf S )Nz<HTTPError %s: %r>r r
r
r
r �__repr__7 s zHTTPError.__repr__c C s | j S r )r r
r
r
r r < s zHTTPError.reasonc C s | j S r �r r
r
r
r �headers@ s zHTTPError.headersc C s
|| _ d S r r )r r r
r
r r D s N)r r r �urllib�response�
addinfourlr r r r �propertyr r �setterr
r
r
r r # s
c @ s e Zd Zdd� ZdS )r c C s t �| |� || _d S r )r r �content)r �messager r
r
r r K s z ContentTooShortError.__init__N)r r r r r
r
r
r r I s ) Zurllib.responser �__all__�OSErrorr r r r r r
r
r
r �<module> s
&PK *(�Z.�v�#� #� ( __pycache__/request.cpython-38.opt-2.pycnu �[��� U
e5d�� � ! @ s� d dl Z d dlZd dlZd dlZd dlZd dlZd dlZd dlZd dl Z d dl
Z
d dl Z d dl Z d dl
Z
d dlZd dlZd dlZd dlmZmZmZ d dlmZmZmZmZmZmZm Z m Z m Z m Z m Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z' d dl(m)Z)m*Z* z d dl+Z+W n e,k
�r dZ-Y nX dZ-ddd d
d d d
ddddddddddddddd d d d d d!d"d#d$d%d&d'g!Z.d(e j/dd)� Z0da1de
j2fddddd*�d+d �Z3d,d � Z4g Z5d}d-d$�Z6d.d%� Z7e �8d/e j9�Z:d0d1� Z;G d2d� d�Z<G d3d� d�Z=d4d � Z>G d5d � d �Z?G d6d � d e?�Z@G d7d
� d
e?�ZAG d8d � d e?�ZBd9d:� ZCG d;d
� d
e?�ZDG d<d� d�ZEG d=d� deE�ZFG d>d� deF�ZGG d?d� d�ZHG d@d� deHe?�ZIG dAd� deHe?�ZJejKZLG dBd� d�ZMG dCd� de?eM�ZNG dDd� de?eM�ZOG dEdF� dFe?�ZPG dGd� deP�ZQeRejSdH��r&G dIdJ� dJeP�ZTe.�UdJ� G dKd � d e?�ZVG dLd � d e?�ZWdMdN� ZXdOdP� ZYG dQd� de?�ZZdRdS� Z[G dTd� de?�Z\G dUd� de\�Z]G dVd� de?�Z^dWZ_ej`dXk�r�d dYlambZbmcZc ndZd"� Zbd[d!� Zci ZdG d\d&� d&�ZeG d]d'� d'ee�Zfdagd^d_� Zhdaid`da� Zjdakdbdc� Zldamddde� ZnG dfdg� dg�Zodhdi� Zpd~djdk�Zqdldm� Zre jsdnk�r�d doltmuZumvZv dpdq� Zwdrds� Zxdtdu� Zydvd#� Zzn6ej`dXk�r�dwdx� Z{dyd#� Zzdzd{� Z|d|du� ZynepZzeqZydS )� N)�URLError� HTTPError�ContentTooShortError)�urlparse�urlsplit�urljoin�unwrap�quote�unquote�
_splittype�
_splithost�
_splitport�
_splituser� _splitpasswd�
_splitattr� _splitquery� _splitvalue� _splittag� _to_bytes�unquote_to_bytes�
urlunparse)�
addinfourl� addclosehookFT�Request�OpenerDirector� BaseHandler�HTTPDefaultErrorHandler�HTTPRedirectHandler�HTTPCookieProcessor� ProxyHandler�HTTPPasswordMgr� HTTPPasswordMgrWithDefaultRealm� HTTPPasswordMgrWithPriorAuth�AbstractBasicAuthHandler�HTTPBasicAuthHandler�ProxyBasicAuthHandler�AbstractDigestAuthHandler�HTTPDigestAuthHandler�ProxyDigestAuthHandler� HTTPHandler� FileHandler�
FTPHandler�CacheFTPHandler� DataHandler�UnknownHandler�HTTPErrorProcessor�urlopen�install_opener� build_opener� pathname2url� url2pathname�
getproxies� urlretrieve�
urlcleanup� URLopener�FancyURLopenerz%d.%d� )�cafile�capath� cadefault�contextc
C s� |s |s |rfdd l }|�dtd� |d k r2td��ts>td��tjtjj||d�}t |d�}t
|�} n0|r~t |d�}t
|�} nt d kr�t
� a } nt } | � | ||�S )Nr zJcafile, capath and cadefault are deprecated, use a custom context instead.r: zDYou can't pass both context and any of cafile, capath, and cadefaultzSSL support not available)r; r< )r> )
�warnings�warn�DeprecationWarning�
ValueError� _have_ssl�sslZcreate_default_contextZPurposeZ SERVER_AUTH� HTTPSHandlerr2 �_opener�open)
�url�data�timeoutr; r< r= r> r? Z
https_handler�opener� rL �&/usr/lib64/python3.8/urllib/request.pyr0 � s2 < ��
�
c C s | a d S �N)rF )rK rL rL rM r1 � s c
C s: t | �\}}t�t| |����}|�� }|dkrN|sNtj�|�|fW 5 Q R � S |r^t|d�}n t j
dd�}|j }t �
|� |�� ||f} d}
d} d} d}
d|kr�t|d �} |r�||
|
| � |�|
�}|s�q�| t|�7 } |�|� |
d
7 }
|r�||
|
| � q�W 5 Q R X W 5 Q R X | dk�r6| | k �r6td | | f | ��| S ) N�file�wbF)�delete� ���r �content-length�Content-Length� �1retrieval incomplete: got only %i out of %i bytes)r �
contextlib�closingr0 �info�os�path�normpathrG �tempfileZNamedTemporaryFile�name�_url_tempfiles�append�int�read�len�writer )rH �filename�
reporthookrI Zurl_typer\ �fp�headers�tfp�result�bs�sizerc �blocknum�blockrL rL rM r6 � sH
"��c C sD t D ](} zt�| � W q tk
r* Y qX qt d d �= tr@d ad S rN )r` r[ �unlink�OSErrorrF )Z temp_filerL rL rM r7 $ s
z:\d+$c C s< | j }t|�d }|dkr&| �dd�}t�d|d�}|�� S )NrV � �Host)�full_urlr �
get_header� _cut_port_re�sub�lower)�requestrH �hostrL rL rM � request_host3 s r{ c @ s� e Zd Zdi dddfdd�Zedd� �Zejdd� �Zejdd� �Zed d
� �Zejd d
� �Zejd d
� �Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� Zdd � Zd#d d �Zd d � Zd!d"� ZdS )$r NFc C sl || _ i | _i | _d | _|| _d | _|�� D ]\}}| �||� q,|d krRt| �}|| _ || _
|rh|| _ d S rN ) rt ri �unredirected_hdrs�_datarI � _tunnel_host�items�
add_headerr{ �origin_req_host� unverifiable�method) �selfrH rI ri r� r� r� �key�valuerL rL rM �__init__E s zRequest.__init__c C s | j rd�| j| j �S | jS )Nz{}#{})�fragment�format� _full_url�r� rL rL rM rt W s zRequest.full_urlc C s( t |�| _t| j�\| _| _| �� d S rN )r r� r r� �_parse�r� rH rL rL rM rt ] s
c C s d | _ d | _d| _d S �Nrr )r� r� �selectorr� rL rL rM rt d s c C s | j S rN )r} r� rL rL rM rI j s z Request.datac C s( || j kr$|| _ | �d�r$| �d� d S )N�Content-length)r} �
has_header�
remove_header)r� rI rL rL rM rI n s
c C s
d | _ d S rN )rI r� rL rL rM rI x s c C sN t | j�\| _}| jd kr(td| j ��t|�\| _| _| jrJt| j�| _d S )Nzunknown url type: %r) r r� �typerB rt r rz r� r
)r� �restrL rL rM r� | s
zRequest._parsec C s | j d k rdnd}t| d|�S )N�POST�GETr� )rI �getattr)r� Zdefault_methodrL rL rM �
get_method� s zRequest.get_methodc C s | j S rN )rt r� rL rL rM � get_full_url� s zRequest.get_full_urlc C s2 | j dkr| js| j| _n|| _ | j| _|| _d S )N�https)r� r~ rz rt r� )r� rz r� rL rL rM � set_proxy� s
zRequest.set_proxyc C s | j | jkS rN )r� rt r� rL rL rM � has_proxy� s zRequest.has_proxyc C s || j |�� < d S rN )ri �
capitalize�r� r� �valrL rL rM r� � s zRequest.add_headerc C s || j |�� < d S rN )r| r� r� rL rL rM �add_unredirected_header� s z Request.add_unredirected_headerc C s || j kp|| jkS rN )ri r| �r� � header_namerL rL rM r� � s
�zRequest.has_headerc C s | j �|| j�||��S rN )ri �getr| )r� r� �defaultrL rL rM ru � s �zRequest.get_headerc C s | j �|d � | j�|d � d S rN )ri �popr| r� rL rL rM r� � s zRequest.remove_headerc C s | j | j�}t|�� �S rN )r| ri �listr )r� �hdrsrL rL rM � header_items� s zRequest.header_items)N)�__name__�
__module__� __qualname__r� �propertyrt �setter�deleterrI r� r� r� r� r� r� r� r� ru r� r� rL rL rL rM r C s8 �
c @ sN e Zd Zdd� Zdd� Zdd� Zdd� Zd ejfd
d �Z dd d
�Z
dd� Z d S )r c C s6 dt }d|fg| _g | _i | _i | _i | _i | _d S )N�Python-urllib/%sz
User-agent)� __version__�
addheaders�handlers� handle_open� handle_error�process_response�process_request)r� Zclient_versionrL rL rM r� � s zOpenerDirector.__init__c C sT t |d�stdt|� ��d}t|�D �]}|dkr6q&|�d�}|d |� }||d d � }|�d�r�|�d�| d }||d d � }z t|�}W n tk
r� Y nX | j� |i �} | | j|< n>|dkr�|}| j
} n*|d kr�|}| j } n|d
kr&|}| j } nq&| �
|g �}
|
�r"t�|
|� n
|
�|� d }q&|�rPt�| j|� |�| � d S ) N�
add_parentz%expected BaseHandler instance, got %rF)�redirect_request�do_open�
proxy_open�_rV �errorrG �responsery T)�hasattr� TypeErrorr� �dir�find�
startswithrb rB r� r� r� r� r� �
setdefault�bisectZinsortra r� r� ) r� �handlerZadded�meth�i�protocolZ condition�j�kind�lookupr� rL rL rM � add_handler� sL
�
zOpenerDirector.add_handlerc C s d S rN rL r� rL rL rM �close� s zOpenerDirector.closec G s< |� |d�}|D ]&}t||�}||� }|d k r| S qd S )NrL )r� r� ) r� �chainr� � meth_name�argsr� r� �funcrk rL rL rM � _call_chain� s
zOpenerDirector._call_chainNc
C s� t |t�rt||�}n|}|d k r(||_||_|j}|d }| j�|g �D ]}t||�}||�}qJt �
d|j |j|j |�
� � | �||�} |d }| j�|g �D ]}t||�}||| �} q�| S )NZ_requestzurllib.RequestZ _response)�
isinstance�strr rI rJ r� r� r� r� �sys�auditrt ri r� �_openr� )
r� �fullurlrI rJ �reqr� r� Z processorr� r� rL rL rM rG � s$
zOpenerDirector.openc C sP | � | jdd|�}|r|S |j}| � | j||d |�}|r>|S | � | jdd|�S )Nr� Z default_openr� �unknown� unknown_open)r� r� r� )r� r� rI rk r� rL rL rM r� s$
� ��
�zOpenerDirector._openc G s~ |dkr,| j d }|d }d| }d}|}n| j }|d }d}|||f| }| j|� }|r^|S |rz|dd f| }| j|� S d S )
N��httpr� r� r: z
http_error_%srV Z_errorr r� �http_error_default)r� r� )r� �protor� �dictr� Zhttp_errZ orig_argsrk rL rL rM r� & s
zOpenerDirector.error)N) r� r� r� r� r� r� r� �socket�_GLOBAL_DEFAULT_TIMEOUTrG r� r� rL rL rL rM r � s /
c G s� t � }ttttttttt g }t
t j d�r2|�
t� t� }|D ]B}| D ]8}t|t�rht||�r||�|� qDt||�rD|�|� qDq<|D ]}|�|� q�|D ]}|�|� � q�| D ] }t|t�r�|� }|�|� q�|S )N�HTTPSConnection)r r r. r) r r r+ r* r/ r- r� r� �clientra rE �setr� r� �
issubclass�add�remover� )r� rK Zdefault_classes�skip�klassZcheck�hrL rL rM r2 ? s8 �
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r �� c C s
|| _ d S rN )�parent)r� r� rL rL rM r� f s zBaseHandler.add_parentc C s d S rN rL r� rL rL rM r� i s zBaseHandler.closec C s t |d�sdS | j|jk S )N�
handler_orderT)r� r� )r� �otherrL rL rM �__lt__m s
zBaseHandler.__lt__N)r� r� r� r� r� r� r� rL rL rL rM r c s c @ s e Zd ZdZdd� ZeZdS )r/ i� c C sH |j |j|�� }}}d| kr,dk sDn | j�d|||||�}|S )N�� �, r� )�code�msgrZ r� r� )r� ry r� r� r� r� rL rL rM �
http_responsez s �z HTTPErrorProcessor.http_responseN)r� r� r� r� r� �https_responserL rL rL rM r/ v s c @ s e Zd Zdd� ZdS )r c C s t |j||||��d S rN )r rt )r� r� rh r� r� r� rL rL rM r� � s z*HTTPDefaultErrorHandler.http_error_defaultN)r� r� r� r� rL rL rL rM r � s c @ s4 e Zd ZdZdZdd� Zdd� Ze Z ZZ dZ
dS ) r � �
c st |� � }|dkr|dks:|dkr(|dks:t|j||||��|�dd�}d� � fdd �|j�� D �}t|||jd
d �S ) N)�- �. �/ i3 )r� ZHEAD)r� r� r� r� � z%20)rT z content-typec s" i | ]\}}|� � � kr||�qS rL )rx ��.0�k�v�ZCONTENT_HEADERSrL rM �
<dictcomp>� s � z8HTTPRedirectHandler.redirect_request.<locals>.<dictcomp>T)ri r� r� )r� r rt �replaceri r r r� ) r� r� rh r� r� ri �newurl�mZ
newheadersrL r rM r� � s
�� �z$HTTPRedirectHandler.redirect_requestc
C sL d|kr|d }nd|kr$|d }nd S t |�}|jdkrRt||d||f ||��|jsn|jrnt|�}d|d< t|�}t|dtj d�}t
|j |�}| � ||||||�}|d kr�d S t
|d ��r|j } |_| �|d
�| jks�t| �| jk�rt|j || j| ||��ni } |_|_| �|d
�d | |< |�� |�� | jj||jd �S )
N�location�uri�r� r� �ftprr z+%s - Redirection to url '%s' is not allowed�/r: z
iso-8859-1)�encoding�safe�
redirect_dictr rV �rJ )r �schemer r\ Znetlocr� r r �stringZ punctuationr rt r� r� r
r� � max_repeatsrd �max_redirections�inf_msgrc r� r� rG rJ )
r� r� rh r� r� ri r �urlparts�newZvisitedrL rL rM �http_error_302� sT
� � � �z"HTTPRedirectHandler.http_error_302zoThe HTTP server returned a redirect error that would lead to an infinite loop.
The last 30x error message was:
N) r� r� r� r r r� r �http_error_301�http_error_303�http_error_307r rL rL rL rM r � s &< c
C s� t | �\}}|�d�s d }| }nZ|�d�s6td| ��d|krV|�d�}|�d|�}n |�dd�}|dkrnd }|d|� }t|�\}}|d k r�t|�\}} nd }} ||| |fS )Nr
�//z proxy URL with no authority: %r�@r: rS )r r� rB r� r r )
�proxyr Zr_scheme� authorityZhost_separator�endZuserinfo�hostport�user�passwordrL rL rM � _parse_proxy� s$
r" c @ s" e Zd ZdZddd�Zdd� ZdS )r �d Nc C sP |d krt � }|| _|�� D ].\}}|�� }t| d| ||| jfdd�� q d S )Nz%s_openc S s || ||�S rN rL )�rr r� r� rL rL rM �<lambda>) s z'ProxyHandler.__init__.<locals>.<lambda>)r5 �proxiesr rx �setattrr� )r� r& r� rH rL rL rM r� ! s
�zProxyHandler.__init__c C s� |j }t|�\}}}}|d kr"|}|jr6t|j�r6d S |rv|rvdt|�t|�f } t�| �� ��d�}
|� dd|
� t|�}|�
||� ||ks�|dkr�d S | j j ||j
d�S d S )N�%s:%s�ascii�Proxy-authorization�Basic r� r )r� r" rz � proxy_bypassr
�base64� b64encode�encode�decoder� r� r� rG rJ ) r� r� r r� Z orig_typeZ
proxy_typer r! r Z user_passZcredsrL rL rM r� , s" � zProxyHandler.proxy_open)N)r� r� r� r� r� r� rL rL rL rM r s
c @ s6 e Zd Zdd� Zdd� Zdd� Zd
dd �Zd
d � Zd S )r c C s
i | _ d S rN )�passwdr� rL rL rM r� J s zHTTPPasswordMgr.__init__c s\ t |t�r|g}|�jkr$i �j|< dD ].� t� �fdd�|D ��}||f�j| |< q(d S )N�TFc 3 s | ]}�� |� �V qd S rN )�
reduce_uri)r� �u�� default_portr� rL rM � <genexpr>T s z/HTTPPasswordMgr.add_password.<locals>.<genexpr>)r� r� r1 �tuple)r� �realmr r r1 � reduced_urirL r5 rM � add_passwordM s
�z HTTPPasswordMgr.add_passwordc C s` | j �|i �}dD ]H}| �||�}|�� D ].\}}|D ] }| �||�r6| S q6q*qdS )Nr2 �NN)r1 r� r3 r � is_suburi) r� r9 �authuriZdomainsr6 �reduced_authuriZurisZauthinfor rL rL rM �find_user_passwordX s z"HTTPPasswordMgr.find_user_passwordTc
C s� t |�}|d r.|d }|d }|d p*d}n d }|}d}t|�\}}|r~|d kr~|d k r~ddd��|�} | d k r~d|| f }||fS ) NrV r r: r
�P i� r� z%s:%d)r r
r� )
r� r r6 �partsr r r\ rz �portZdportrL rL rM r3 b s$ �� zHTTPPasswordMgr.reduce_uric C sN ||kr dS |d |d kr dS |d }|dd � dkr@|d7 }|d � |�S )NTr FrV rS r
)r� )r� �base�test�prefixrL rL rM r= y s zHTTPPasswordMgr.is_suburiN)T)r� r� r� r� r; r@ r3 r= rL rL rL rM r H s
c @ s e Zd Zdd� ZdS )r! c C s0 t �| ||�\}}|d k r"||fS t �| d |�S rN )r r@ )r� r9 r> r r! rL rL rM r@ � s �z2HTTPPasswordMgrWithDefaultRealm.find_user_passwordN)r� r� r� r@ rL rL rL rM r! � s c s< e Zd Z� fdd�Zd
� fdd� Zd dd�Zdd � Z� ZS ) r" c s i | _ t� j||� d S rN )�
authenticated�superr� �r� r� �kwargs�� __class__rL rM r� � s z%HTTPPasswordMgrWithPriorAuth.__init__Fc s< | � ||� |d k r&t� �d |||� t� �||||� d S rN )�update_authenticatedrH r; )r� r9 r r r1 �is_authenticatedrK rL rM r; � s z)HTTPPasswordMgrWithPriorAuth.add_passwordc C s> t |t�r|g}dD ]$}|D ]}| �||�}|| j|< q qd S �Nr2 )r� r� r3 rG )r� r rN r6 r4 r: rL rL rM rM � s
z1HTTPPasswordMgrWithPriorAuth.update_authenticatedc C sD dD ]:}| � ||�}| jD ]"}| �||�r| j| S qqd S rO )r3 rG r= )r� r> r6 r? r rL rL rM rN � s
z-HTTPPasswordMgrWithPriorAuth.is_authenticated)F)F)r� r� r� r� r; rM rN �
__classcell__rL rL rK rM r" � s
c @ sT e Zd Ze�dej�Zddd�Zdd� Zdd� Z d d
� Z
d d � Z d
d� Z e Z
e ZdS )r# z1(?:^|,)[ ]*([^ ,]+)[ ]+realm=(["']?)([^"']*)\2Nc C s" |d krt � }|| _| jj| _d S rN )r r1 r; )r� Z password_mgrrL rL rM r� � s z!AbstractBasicAuthHandler.__init__c c sp d}t j�|�D ]6}|�� \}}}|dkr8t�dtd� ||fV d}q|sl|r^|�� d }nd}|d fV d S )NF)�"�'z Basic Auth Realm was unquoted� Tr rr )r# �rx�finditer�groupsr? r@ � UserWarning�split)r� �headerZfound_challengeZmor r r9 rL rL rM � _parse_realm� s �
z%AbstractBasicAuthHandler._parse_realmc C s~ |� |�}|sd S d }|D ]H}| �|�D ]8\}}|�� dkrB|}q(|d k r(| �|||� S q(q|d k rztd|f ��d S )N�basiczBAbstractBasicAuthHandler does not support the following scheme: %r)Zget_allrZ rx �retry_http_basic_authrB ) r� �authreqrz r� ri Z unsupportedrY r r9 rL rL rM �http_error_auth_reqed� s
�z.AbstractBasicAuthHandler.http_error_auth_reqedc C s| | j �||�\}}|d k rtd||f }dt�|�� ��d� }|�| jd �|krTd S |�| j|� | j j
||j d�S d S d S )Nr( r+ r) r ) r1 r@ r- r. r/ r0 ru � auth_headerr� r� rG rJ )r� rz r� r9 r �pw�raw�authrL rL rM r\ � s z.AbstractBasicAuthHandler.retry_http_basic_authc C st t | jd�r| j�|j�s |S |�d�sp| j�d |j�\}}d�||��� }t� |��
� }|� dd�|� � �� |S )NrN �
Authorizationz{0}:{1}zBasic {})
r� r1 rN rt r� r@ r� r/ r- Zstandard_b64encoder0 r� �strip)r� r� r r1 Z credentialsZauth_strrL rL rM � http_request s �
�z%AbstractBasicAuthHandler.http_requestc C sL t | jd�rHd|j kr"dk r8n n| j�|jd� n| j�|jd� |S )NrN r� r� TF)r� r1 r� rM rt )r� r� r� rL rL rM r� s
z&AbstractBasicAuthHandler.http_response)N)r� r� r� �re�compile�IrT r� rZ r^ r\ re r� �
https_requestr� rL rL rL rM r# � s �
c @ s e Zd ZdZdd� ZdS )r$ rc c C s |j }| �d|||�}|S )N�www-authenticate)rt r^ )r� r� rh r� r� ri rH r� rL rL rM �http_error_401$ s �z#HTTPBasicAuthHandler.http_error_401N)r� r� r� r_ rk rL rL rL rM r$ s c @ s e Zd ZdZdd� ZdS )r% r* c C s |j }| �d|||�}|S �N�proxy-authenticate)rz r^ )r� r� rh r� r� ri r r� rL rL rM �http_error_407/ s �z$ProxyBasicAuthHandler.http_error_407N)r� r� r� r_ rn rL rL rL rM r% + s c @ sN e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dS )r& Nc C s4 |d krt � }|| _| jj| _d| _d| _d | _d S �Nr )r r1 r; �retried� nonce_count�
last_nonce)r� r1 rL rL rM r� I s
z"AbstractDigestAuthHandler.__init__c C s
d| _ d S ro )rp r� rL rL rM �reset_retry_countR s z+AbstractDigestAuthHandler.reset_retry_countc C s| |� |d �}| jdkr*t|jdd|d ��n| jd7 _|rx|�� d }|�� dkr`| �||�S |�� dkrxtd| ��d S ) N� i� zdigest auth failedrV r Zdigestr[ zEAbstractDigestAuthHandler does not support the following scheme: '%s')r� rp r rt rX rx �retry_http_digest_authrB )r� r_ rz r� ri r] r rL rL rM r^ U s
� �z/AbstractDigestAuthHandler.http_error_auth_reqedc C sz |� dd�\}}ttd t|���}| �||�}|rvd| }|j�| jd �|krRd S |�| j|� | j j
||j d�}|S d S )Nr� rV z Digest %sr ) rX �parse_keqv_list�filter�parse_http_list�get_authorizationri r� r_ r� r� rG rJ )r� r� rb �tokenZ challenge�chalZauth_valZresprL rL rM ru i s z0AbstractDigestAuthHandler.retry_http_digest_authc C s@ d| j |t�� f }|�d�td� }t�|��� }|d d� S )Nz %s:%s:%s:r) � � )rq �time�ctimer/ � _randombytes�hashlib�sha1� hexdigest)r� �nonce�s�b�digrL rL rM �
get_cnonceu s z$AbstractDigestAuthHandler.get_cnoncec C s� z6|d }|d }|� d�}|� dd�}|� dd �}W n tk
rL Y d S X | �|�\}} |d krhd S | j�||j�\}
} |
d kr�d S |jd k r�| �|j|�} nd } d|
|| f }
d|�� |j f }|d kr�| ||
�d|||�f �}n~d |�
d
�k�r\|| j k�r| j d 7 _ n d | _ || _ d | j }| �
|�}d
|||d ||�f }| ||
�|�}n td| ��d|
|||j |f }|�r�|d| 7 }| �r�|d| 7 }|d| 7 }|�r�|d||f 7 }|S )Nr9 r� �qop� algorithm�MD5�opaquez%s:%s:%sr( rb �,rV z%08xz%s:%s:%s:%s:%szqop '%s' is not supported.z>username="%s", realm="%s", nonce="%s", uri="%s", response="%s"z
, opaque="%s"z
, digest="%s"z, algorithm="%s"z , qop=auth, nc=%s, cnonce="%s")r� �KeyError�get_algorithm_implsr1 r@ rt rI �get_entity_digestr� r� rX rr rq r� r )r� r� r{ r9 r� r� r� r� �H�KDr r` ZentdigZA1ZA2ZrespdigZncvalueZcnonceZnoncebitrD rL rL rM ry � s\
�
�� z+AbstractDigestAuthHandler.get_authorizationc sD |dkrdd� � n |dkr$dd� � n t d| ��� fdd�}� |fS )Nr� c S s t �| �d���� S �Nr) )r� Zmd5r/ r� ��xrL rL rM r% � � z?AbstractDigestAuthHandler.get_algorithm_impls.<locals>.<lambda>ZSHAc S s t �| �d���� S r� )r� r� r/ r� r� rL rL rM r% � r� z.Unsupported digest authentication algorithm %rc s � d| |f �S )Nr( rL )r� �d�r� rL rM r% � r� )rB )r� r� r� rL r� rM r� � s
� z-AbstractDigestAuthHandler.get_algorithm_implsc C s d S rN rL )r� rI r{ rL rL rM r� � s z+AbstractDigestAuthHandler.get_entity_digest)N) r� r� r� r� rs r^ ru r� ry r� r� rL rL rL rM r& > s
>
c @ s e Zd ZdZdZdd� ZdS )r' rc �� c C s* t |j�d }| �d|||�}| �� |S )NrV rj )r rt r^ rs �r� r� rh r� r� ri rz �retryrL rL rM rk � s �z$HTTPDigestAuthHandler.http_error_401N)r� r� r� r_ r� rk rL rL rL rM r' � s c @ s e Zd ZdZdZdd� ZdS )r( �Proxy-Authorizationr� c C s" |j }| �d|||�}| �� |S rl )rz r^ rs r� rL rL rM rn � s �z%ProxyDigestAuthHandler.http_error_407N)r� r� r� r_ r� rn rL rL rL rM r( � s c @ s6 e Zd Zd
dd�Zdd� Zdd� Zdd � Zd
d � Zd S )�AbstractHTTPHandlerr c C s
|| _ d S rN �� _debuglevel)r� �
debuglevelrL rL rM r� � s z AbstractHTTPHandler.__init__c C s
|| _ d S rN r� )r� �levelrL rL rM �set_http_debuglevel� s z'AbstractHTTPHandler.set_http_debuglevelc C s t jj�|j|�� �S rN )r� r� �HTTPConnection�_get_content_lengthrI r� �r� ry rL rL rM r� � s �z'AbstractHTTPHandler._get_content_lengthc C s |j }|std��|jd k r�|j}t|t�r8d}t|��|�d�sN|�dd� |�d�s�|�d�s�| �|�}|d k r�|�dt|�� n |�dd� |}|� � r�t
|j �\}}t |�\}} |�d�s�|�d|� | j
jD ]&\}
} |
�� }
|�|
�s�|�|
| � q�|S ) N�
no host givenz\POST data should be bytes, an iterable of bytes, or a file object. It cannot be of type str.z Content-type�!application/x-www-form-urlencodedr� �Transfer-encodingZchunkedrs )rz r rI r� r� r� r� r� r� r� r r� r r� r� r� ) r� ry rz rI r� Zcontent_lengthZsel_hostr ZselZsel_pathr_ r� rL rL rM � do_request_� sJ
�
�
� �
z AbstractHTTPHandler.do_request_c
sT |j }|std��||fd|ji|��}|�| j� t|j�� � �� fdd�|j� � D �� d� d< dd� � � � D �� |j
r�i }d}|� kr�� | ||< � |= |j |j
|d � z`z&|j |�
� |j|j� |�d
�d � W n, tk
�r } z t|��W 5 d }~X Y nX |�� } W n |�� � Y nX |j�r>|j�� d |_|�� | _| j| _| S ) Nr� rJ c s i | ]\}}|� kr||�qS rL rL r� �ri rL rM r / s � z/AbstractHTTPHandler.do_open.<locals>.<dictcomp>r� �
Connectionc S s i | ]\}}|� � |�qS rL )�title)r� r_ r� rL rL rM r < s r� r� r� )Zencode_chunked)rz r rJ Zset_debuglevelr� r� r| �updateri r r~ Z
set_tunnelry r� r� rI r� rq � getresponser� Zsockr� rH �reasonr� )
r� Z
http_classr� Zhttp_conn_argsrz r� Ztunnel_headersZproxy_auth_hdr�errr$ rL r� rM r� ! sB
�
zAbstractHTTPHandler.do_openN)r )r� r� r� r� r� r� r� r� rL rL rL rM r� � s
&r� c @ s e Zd Zdd� ZejZdS )r) c C s | � tjj|�S rN )r� r� r� r� �r� r� rL rL rM � http_openf s zHTTPHandler.http_openN)r� r� r� r� r� r� re rL rL rL rM r) d s r� c @ s$ e Zd Zddd�Zdd� ZejZdS )rE r Nc C s t �| |� || _|| _d S rN )r� r� �_context�_check_hostname)r� r� r> �check_hostnamerL rL rM r� o s zHTTPSHandler.__init__c C s | j tjj|| j| jd�S )N)r> r� )r� r� r� r� r� r� r� rL rL rM �
https_opent s �zHTTPSHandler.https_open)r NN)r� r� r� r� r� r� r� ri rL rL rL rM rE m s
rE c @ s. e Zd Zddd�Zdd� Zdd� ZeZeZdS ) r Nc C s$ dd l }|d kr|j�� }|| _d S ro )Zhttp.cookiejar� cookiejarZ CookieJar)r� r� r� rL rL rM r� } s
z HTTPCookieProcessor.__init__c C s | j �|� |S rN )r� Zadd_cookie_headerr� rL rL rM re � s z HTTPCookieProcessor.http_requestc C s | j �||� |S rN )r� Zextract_cookies)r� ry r� rL rL rM r� � s z!HTTPCookieProcessor.http_response)N)r� r� r� r� re r� ri r� rL rL rL rM r | s
c @ s e Zd Zdd� ZdS )r. c C s |j }td| ��d S )Nzunknown url type: %s)r� r )r� r� r� rL rL rM r� � s zUnknownHandler.unknown_openN)r� r� r� r� rL rL rL rM r. � s c C sN i }| D ]@}|� dd�\}}|d dkr@|d dkr@|dd� }|||< q|S )N�=rV r rQ rS )rX )�lZparsedZeltr� r rL rL rM rv � s
rv c C s� g }d}d }}| D ]l}|r*||7 }d}q|rT|dkr>d}qn |dkrJd}||7 }q|dkrl|� |� d}q|dkrxd}||7 }q|r�|� |� dd� |D �S ) Nrr F�\TrQ r� c S s g | ] }|� � �qS rL )rd )r� �partrL rL rM �
<listcomp>� s z#parse_http_list.<locals>.<listcomp>)ra )r� �resr� �escaper ZcurrL rL rM rx � s4
rx c @ s( e Zd Zdd� ZdZdd� Zdd� ZdS )r* c C s\ |j }|d d� dkrN|dd� dkrN|jrN|jdkrN|j| �� krXtd��n
| �|�S d S )Nr: r rS r
� localhost�-file:// scheme is supported only on localhost)r� rz � get_namesr �open_local_file)r� r� rH rL rL rM � file_open� s &�
zFileHandler.file_openNc C s` t jd krZz*tt�d�d t�t�� �d �t _W n$ tjk
rX t�d�ft _Y nX t jS )Nr� r: )r* �namesr8 r� �gethostbyname_ex� gethostname�gaierror�
gethostbynamer� rL rL rM r� � s
��
zFileHandler.get_namesc
C s� dd l }dd l}|j}|j}t|�}z�t�|�}|j}|jj |j
dd�} |� |�d }
|� d|
pbd|| f �} |r~t
|�\}} |r�| s�t|�| �� kr�|r�d| | }
nd| }
tt|d�| |
�W S W n* tk
r� } z t|��W 5 d }~X Y nX td��d S ) Nr T�Zusegmtz6Content-type: %s
Content-length: %d
Last-modified: %s
�
text/plain�file://�rbzfile not on local host)� email.utils� mimetypesrz r� r4 r[ �stat�st_size�utils�
formatdate�st_mtime�
guess_type�message_from_stringr
�_safe_gethostbynamer� r rG rq r )r� r� �emailr� rz rf Z localfile�statsrm �modified�mtyperi rC Zorigurl�exprL rL rM r� � s:
�� ��zFileHandler.open_local_file)r� r� r� r� r� r� r� rL rL rL rM r* � s
c C s* z t �| �W S t jk
r$ Y d S X d S rN )r� r� r� )rz rL rL rM r� � s r� c @ s e Zd Zdd� Zdd� ZdS )r+ c
C s* dd l }dd l}|j}|s"td��t|�\}}|d kr>|j}nt|�}t|�\}}|rdt|�\}}nd }t |�}|pvd}|p~d}zt
� |�}W n* t k
r� } z t|��W 5 d }~X Y nX t
|j�\} }
| �d�} ttt | ��} | d d� | d } } | �r| d �s| dd � } z�| �||||| |j�}
| �r6d�p8d}|
D ]2}t|�\}}|�� d k�r>|d
k�r>|�� }�q>|
�| |�\}}d}|�|j�d }|�r�|d | 7 }|d k �r�|dk�r�|d | 7 }t�|�}t |||j�W S |j k
�r$ } z"td
| �}|� t � � d ��W 5 d }~X Y nX d S )Nr �ftp error: no host givenrr r
rS rV rh �Dr� ��a�Ar� rh r� r� zContent-type: %s
zContent-length: %d
�
ftp error: %rr: )!�ftplibr� rz r r
�FTP_PORTrb r r r
r� r� rq r r� rX r� �map� connect_ftprJ r rx �upper�retrfiler� rt r� r� r �
all_errors�with_tracebackr� �exc_info)r� r� r� r� rz rC r r1 r� r\ �attrs�dirsrO �fwr� �attrr� rh �retrlenri r� r� �excrL rL rM �ftp_open s^
�
zFTPHandler.ftp_openc C s t ||||||dd�S )NF)�
persistent)�
ftpwrapper)r� r r1 rz rC r� rJ rL rL rM r� 7 s �zFTPHandler.connect_ftpN)r� r� r� r� r� rL rL rL rM r+ s 5c @ s< e Zd Zdd� Zdd� Zdd� Zdd� Zd d
� Zd d � Zd
S )r, c C s" i | _ i | _d| _d| _d| _d S )Nr �< r} )�cacherJ �soonest�delay� max_connsr� rL rL rM r� > s
zCacheFTPHandler.__init__c C s
|| _ d S rN )r� )r� �trL rL rM �
setTimeoutE s zCacheFTPHandler.setTimeoutc C s
|| _ d S rN )r� )r� r rL rL rM � setMaxConnsH s zCacheFTPHandler.setMaxConnsc C sr |||d� |�|f}|| jkr4t�� | j | j|< n,t||||||�| j|< t�� | j | j|< | �� | j| S )Nr
)�joinr� r~ r� rJ r� � check_cache)r� r r1 rz rC r� rJ r� rL rL rM r� K s
�
zCacheFTPHandler.connect_ftpc C s� t � � }| j|krPt| j�� �D ].\}}||k r | j| �� | j|= | j|= q tt| j�� ��| _t | j�| j
kr�t| j�� �D ]&\}}|| jkr�| j|= | j|= q�q�tt| j�� ��| _d S rN ) r~ r� r� rJ r r� r� �min�valuesrd r� )r� r� r� r rL rL rM r� V s
zCacheFTPHandler.check_cachec C s0 | j �� D ] }|�� q
| j �� | j�� d S rN )r� r� r� �clearrJ )r� �connrL rL rM � clear_cachej s
zCacheFTPHandler.clear_cacheN) r� r� r� r� r� r� r� r� r rL rL rL rM r, ; s c @ s e Zd Zdd� ZdS )r- c C s~ |j }|�dd�\}}|�dd�\}}t|�}|�d�rNt�|�}|d d� }|sVd}t�d|t|�f �}t t
� |�||�S )N�:rV r� z;base64i�����text/plain;charset=US-ASCIIz$Content-type: %s
Content-length: %d
) rt rX r �endswithr- � decodebytesr� r� rd r �io�BytesIO)r� r� rH r rI Z mediatyperi rL rL rM � data_openq s
�zDataHandler.data_openN)r� r� r� r rL rL rL rM r- p s r� �nt)r4 r3 c C s t | �S rN )r
��pathnamerL rL rM r4 � s c C s t | �S rN )r r rL rL rM r3 � s c @ s� e Zd ZdZde Zd)dd�Zdd� Zdd� Zd d
� Z d d � Z
d*d
d�Z d+dd�Z d,dd�Z
d-dd�Zdd� Zd.dd�Zd/dd�Zdd � Zer�d d � Zd0d d �Zd!d"� Zd#d$� Zd%d&� Zd1d'd(�ZdS )2r8 Nr� c K sz dd| j ji }tj|tdd� |d kr.t� }|| _|�d�| _|�d�| _ d| j
fdg| _ g | _ t
j| _d | _t| _d S ) NzW%(class)s style of invoking requests is deprecated. Use newer urlopen functions/methods�classrS )�
stacklevel�key_file� cert_filez
User-Agent)ZAcceptz*/*)rL r� r? r@ rA r5 r& r� r r �versionr� �_URLopener__tempfilesr[ rp �_URLopener__unlink� tempcache�ftpcache)r� r& Zx509r� rL rL rM r� � s
� zURLopener.__init__c C s | � � d S rN )r� r� rL rL rM �__del__� s zURLopener.__del__c C s | � � d S rN )�cleanupr� rL rL rM r� � s zURLopener.closec C sV | j rB| j D ](}z| �|� W q tk
r2 Y q X q | j d d �= | jrR| j�� d S rN )r r rq r r )r� rO rL rL rM r � s
zURLopener.cleanupc G s | j �|� d S rN )r� ra )r� r� rL rL rM � addheader� s zURLopener.addheaderc
C sp t t|��}t|dd�}| jrL|| jkrL| j| \}}t|d�}t|||�S t|�\}}|s`d}|| jkr�| j| }t|�\}} t| �\}
} |
|f}nd }d| } || _ | �
dd�} t | | �r�| dkr�|r�| � |||�S | �
||�S z0|d k�r t| | �|�W S t| | �||�W S W nV ttfk
�r0 � Y n< tk
�rj }
z td |
��t�� d
��W 5 d }
~
X Y nX d S ) Nz%/:=&?~#+!$,;'@()*[]|�r r� rO Zopen_�-r� r� z socket errorr: )r r r r rG r r r& r r� r r� �open_unknown_proxy� open_unknownr� r r rq r� r� r� )r� r� rI rf ri rh �urltyperH r � proxyhostrz r� r_ r� rL rL rM rG � s<
zURLopener.openc C s t |�\}}tdd|��d S )N� url errorzunknown url type�r rq )r� r� rI r� rH rL rL rM r
s zURLopener.open_unknownc C s t |�\}}tdd| |��d S )Nr zinvalid proxy for %sr )r� r r� rI r� rH rL rL rM r s z URLopener.open_unknown_proxyc
C s t t|��}| jr&|| jkr&| j| S t|�\}}|d kr�|rF|dkr�z0| �|�}|�� }|�� tt|�d �|fW S t k
r� } zW 5 d } ~ X Y nX | �
||�}�z<|�� }
|r�t
|d�} nrt|�\} }
t|
p�d�\} }
t |
p�d�\}
} t |
p�d�\}
} t
j�|
�d }t�|�\}}| j�|� t
�|d�} z�||
f}| jd k �rT|| j|< d}d}d}d}d|
k�rzt|
d �}|�r�||||� |�|�}|�s��q�|t|�7 }| �|� |d7 }|�r�||||� �q�W 5 | �� X W 5 |�� X |dk�r||k �rtd
||f |��|S ) NrO rV rP rr rR rS r rT rU rW )r r r r r� rZ r� r4 r rq rG r r r[ r\ �splitextr^ Zmkstempr ra �fdopenrb rc rd re r )r� rH rf rg rI r� Zurl1rh r� r� ri rj Zgarbager\ �suffix�fdrk rl rm rc rn ro rL rL rM �retrieve sn
��zURLopener.retrievec C s$ d }d }t |t�r<t|�\}}|r6t|�\}}t|�}|}nt|\}}t|�\}}t|�\} }
|
}d }| �� dkrvd }n:t|
�\}}
|r�t|�\}}|r�d| ||
f }t|�r�|}|s�tdd��|r�t|�}t �
|� � �� d�} nd } |�rt|�}t �
|� � �� d�} nd } ||�}
i }| �r*d| |d< | �r<d| |d< |�rJ||d < d
|d < | j
D ]\}}|||< �qX|d k �r�d |d
< |
�d|||� n|
jd||d� z |
�� }W n" tjjk
�r� td��Y nX d|j k�r�dk �rn nt||jd| |j�S | �||j|j|j|j|�S d S )Nr� z %s://%s%sz
http errorr� r) zBasic %sr� rc rs r� r� r� z Content-Typer� r� r� z$http protocol error: bad status liner� r� �http:)r� r� r r r
r rx r, rq r- r. r/ r0 r� ry r� r� r� Z
BadStatusLiner Zstatusr r� �
http_errorrh r� )r� Zconnection_factoryrH rI Z user_passwdZ proxy_passwdrz r� Zrealhostr r� Z
proxy_authrb Z http_connri rY r� r� rL rL rM �_open_generic_httpV s~
� �z URLopener._open_generic_httpc C s | � tjj||�S rN )r( r� r� r� �r� rH rI rL rL rM � open_http� s zURLopener.open_httpc
C sb d| }t | |�rPt| |�}|d kr6||||||�} n|||||||�} | rP| S | �|||||�S )Nz
http_error_%d)r� r� r� )
r� rH rh �errcode�errmsgri rI r_ r� rk rL rL rM r' � s
zURLopener.http_errorc C s |� � t||||d ��d S rN )r� r �r� rH rh r+ r, ri rL rL rM r� � s z URLopener.http_error_defaultc C s t jj|| j| jd�S )N)r r )r� r� r� r r )r� rz rL rL rM �_https_connection� s �zURLopener._https_connectionc C s | � | j||�S rN )r( r. r) rL rL rM �
open_https� s zURLopener.open_httpsc C s^ t |t�std��|d d� dkrP|dd� dkrP|dd� �� dkrPtd��n
| �|�S d S ) NzEfile error: proxy support for file protocol currently not implementedr: r rS r
� z
localhost/r� )r� r� r rx rB r� r� rL rL rM � open_file� s
4
zURLopener.open_filec
C s\ dd l }dd l}t|�\}}t|�}zt�|�}W n0 tk
rb } zt|j|j ��W 5 d }~X Y nX |j
} |j j |j
dd�}
|�|�d } |�d| p�d| |
f �} |s�|}
|d d� dkr�d| }
tt|d �| |
�S t|�\}}|�sPt�|�t� ft� k�rP|}
|d d� dk�r d| }
n |d d
� d k�r>td | ��tt|d �| |
�S td
��d S )Nr Tr� z6Content-Type: %s
Content-Length: %d
Last-modified: %s
r� rV r
r� r� r: z./zAlocal file url may start with / or file:. Unknown url of type: %sz#local file error: not on local host)r� r� r r4 r[ r� rq r �strerrorrf r� r� r� r� r� r� r rG r
r� r� r� �thishostrB )r� rH r� r� rz rO Z localnamer� �erm r� r� ri ZurlfilerC rL rL rM r� � s@ �� �
zURLopener.open_local_filec
C s� t |t�std��dd l}t|�\}}|s2td��t|�\}}t|�\}}|r\t|�\}}nd }t|�}t|ppd�}t|p|d�}t �
|�}|s�dd l }|j }nt
|�}t|�\}} t|�}|�d�}
|
d d� |
d }
} |
r�|
d s�|
dd � }
|
�r
|
d �s
d|
d< |||d�|
�f} t| j�tk�rbt| j�D ]*}
|
| k�r6| j|
}| j|
= |�� �q6z�| | jk�r�t|||||
�| j| < | �s�d}nd }| D ]2}t|�\}}|�� d
k�r�|d k�r�|�� }�q�| j| �| |�\}}|�d | �d }d}|�r |d
| 7 }|d k �r,|dk�r,|d| 7 }t � |�}t ||d | �W S t � k
�r� } z td| �� t!�"� d ��W 5 d }~X Y nX d S )NzCftp error: proxy support for ftp protocol currently not implementedr r� rr r
rS rV r� rh r� r� zftp:zContent-Type: %s
zContent-Length: %d
z ftp error %rr: )#r� r� r r� r r
r r r
r� r� r� r� rb r rX r� rd r � MAXFTPCACHEr� r� r� r rx r� r� r� r� r� r � ftperrorsr� r� r� )r� rH r� rz r\ rC r r1 r� r� r� rO r� r� r r� r� r� rh r� r� ri r� rL rL rM �open_ftp� st
� �
zURLopener.open_ftpc
C s< t |t�std��z|�dd�\}}W n tk
rD tdd��Y nX |sNd}|�d�}|dkr�d ||d � kr�||d d � }|d |� }nd
}g }|�d t� d t�
t�� �� � |�d
| � |dkr�t � |�
d���d�}nt|�}|�dt|� � |�d
� |�|� d�|�}t�|�}t�|�}t|||�S )NzEdata error: proxy support for data protocol currently not implementedr� rV z
data errorz bad data URLr �;r r� rr zDate: %sz%a, %d %b %Y %H:%M:%S GMTzContent-type: %sr- r) zlatin-1zContent-Length: %d�
)r� r� r rX rB rq �rfindra r~ �strftime�gmtimer- r r/ r0 r
rd r� r� r� r �StringIOr ) r� rH rI r� Zsemir r� ri �frL rL rM � open_data8 s8
�
zURLopener.open_data)N)N)N)N)NNN)N)N)N)N)r� r� r� r r� r r� r r� r r rG r r r% r( r* r' r� rC r. r/ r1 r� r7 r? rL rL rL rM r8 � s,
$
A\
:c @ s� e Zd Zdd� Zdd� Zd"dd�Zdd � Zd#d
d �Zd$d d
�Zd%dd�Z d&dd�Z
d'dd�Z d(dd�Z d)dd�Z
d*dd�Zd+dd �Zd,d d �Zd d!� ZdS )-r9 c O s( t j| f|�|� i | _d| _d| _d S )Nr r� )r8 r� �
auth_cache�tries�maxtriesrI rL rL rM r� e s zFancyURLopener.__init__c C s t ||d| |�S )Nr& )r r- rL rL rM r� k s z!FancyURLopener.http_error_defaultNc C sv | j d7 _ zZ| jrN| j | jkrNt| d�r4| j}n| j}|||dd|�W � S | �||||||�}|W �S d| _ X d S )NrV r �http_error_500r� z)Internal Server Error: Redirect Recursion)rA rB r� rC r� �redirect_internal) r� rH rh r+ r, ri rI r� rk rL rL rM r o s
� �z FancyURLopener.http_error_302c C sx d|kr|d }nd|kr$|d }nd S |� � t| jd | |�}t|�}|jdkrnt|||d| ||��| �|�S )Nr r r r z( Redirection to url '%s' is not allowed.)r� r r� r r r rG ) r� rH rh r+ r, ri rI r r rL rL rM rD � s"
� �z FancyURLopener.redirect_internalc C s | � ||||||�S rN �r �r� rH rh r+ r, ri rI rL rL rM r � s z FancyURLopener.http_error_301c C s | � ||||||�S rN rE rF rL rL rM r � s z FancyURLopener.http_error_303c C s2 |d kr | � ||||||�S | �|||||�S d S rN )r r� rF rL rL rM r � s z FancyURLopener.http_error_307Fc
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |d kr�t| | �|| �S t| | �|| |�S d S )Nrj �![ ]*([^ ]+)[ ]+realm="([^"]*)"r[ Zretry_� _basic_auth�r8 r� rf �matchrV rx r� r� �
r� rH rh r+ r, ri rI r� ZstuffrJ r r9 r_ rL rL rM rk � s:
�
�
��z FancyURLopener.http_error_401c
C s� d|kr t �| |||||� |d }t�d|�} | sHt �| |||||� | �� \}
} |
�� dkrtt �| |||||� |s�t �| |||||� d| j d } |d kr�t| | �|| �S t| | �|| |�S d S )Nrm rG r[ Z retry_proxy_rH rI rK rL rL rM rn � s:
�
�
��z FancyURLopener.http_error_407c C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�http://r� r rV �%s:%s@%srr r �r r& r r� �get_user_passwdr rG �r� rH r9 rI rz r� r r r r Z
proxyselectorr� r r1 rL rL rM �retry_proxy_http_basic_auth� s$
�
z*FancyURLopener.retry_proxy_http_basic_authc C s� t |�\}}d| | }| jd }t|�\}} t | �\} }
| �d�d } | | d � } | �| || �\} }
| sr|
srd S dt| dd�t|
dd�| f } d| |
| jd< |d kr�| �|�S | �||�S d S )N�https://r� r rV rM rr r rN rP rL rL rM � retry_proxy_https_basic_auth� s$
�
z+FancyURLopener.retry_proxy_https_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rM rr r rL �r r� rO r rG �
r� rH r9 rI rz r� r� r r1 r rL rL rM r\ s
�
z$FancyURLopener.retry_http_basic_authc
C s� t |�\}}|�d�d }||d � }| �|||�\}}|sD|sDd S dt|dd�t|dd�|f }d| | } |d kr�| �| �S | �| |�S d S )Nr rV rM rr r rR rT rU rL rL rM �retry_https_basic_auth s
�
z%FancyURLopener.retry_https_basic_authr c C s` |d |� � }|| jkr2|r(| j|= n
| j| S | �||�\}}|sJ|rX||f| j|< ||fS )Nr )rx r@ �prompt_user_passwd)r� rz r9 r r� r r1 rL rL rM rO s
z FancyURLopener.get_user_passwdc C sX dd l }z.td||f �}|� d|||f �}||fW S tk
rR t� Y dS X d S )Nr z Enter username for %s at %s: z#Enter password for %s in %s at %s: r< )�getpass�input�KeyboardInterrupt�print)r� rz r9 rX r r1 rL rL rM rW ) s �
z!FancyURLopener.prompt_user_passwd)N)N)N)N)NF)NF)N)N)N)N)r )r� r� r� r� r� r rD r r r rk rn rQ rS r\ rV rO rW rL rL rL rM r9 b s&
�
�
c C s t d krt�d�a t S )Nr� )�
_localhostr� r� rL rL rL rM r� 9 s
r� c C sP t d krLztt�t�� �d �a W n( tjk
rJ tt�d�d �a Y nX t S )Nr: r� )� _thishostr8 r� r� r� r� rL rL rL rM r3 A s r3 c C s t d krdd l} | ja t S ro )�
_ftperrorsr� r� )r� rL rL rM r6 L s r6 c C s t d krt�d�a t S r� )�
_noheadersr� r� rL rL rL rM � noheadersU s
r` c @ sF e Zd Zddd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Zdd� Z dS )r� NTc C sX || _ || _|| _|| _|| _|| _d| _|| _z | �� W n | � � � Y nX d S ro )
r r1 rz rC r� rJ �refcount� keepalive�initr� )r� r r1 rz rC r� rJ r� rL rL rM r� b s zftpwrapper.__init__c C s\ dd l }d| _|�� | _| j�| j| j| j� | j�| j | j
� d� | j �}| j�
|� d S )Nr r
)r� �busyZFTPr Zconnectrz rC rJ Zloginr r1 r� r� �cwd)r� r� Z_targetrL rL rM rc r s
zftpwrapper.initc
C s� dd l }| �� |dkr"d}d}n d| }d}z| j�|� W n* |jk
rh | �� | j�|� Y nX d }|r�|s�z d| }| j�|�\}}W nR |jk
r� } z2t|�d d� dkr�t d | ��
t � � d
��W 5 d }~X Y nX |�s�| j�d� |�rl| j�
� } zJz| j�|� W n4 |jk
�rN } zt d | �|�W 5 d }~X Y nX W 5 | j�| � X d | }nd }| j�|�\}}d| _t|�d
�| j�}
| jd7 _|�� |
|fS )Nr )r� r� zTYPE ArV zTYPE zRETR rS Z550r� r: zLIST ZLISTr� )r� � endtransferr Zvoidcmdr� rc Z ntransfercmdZ
error_permr� r r� r� r� �pwdre rd r Zmakefile�
file_closera r� ) r� rO r� r� �cmd�isdirr r� r� rg ZftpobjrL rL rM r� { sP
�
$
zftpwrapper.retrfilec C s
d| _ d S ro )rd r� rL rL rM rf � s zftpwrapper.endtransferc C s d| _ | jdkr| �� d S )NFr )rb ra �
real_closer� rL rL rM r� � s
zftpwrapper.closec C s2 | � � | jd8 _| jdkr.| js.| �� d S )NrV r )rf ra rb rk r� rL rL rM rh � s zftpwrapper.file_closec C s2 | � � z| j�� W n t� k
r, Y nX d S rN )rf r r� r6 r� rL rL rM rk � s
zftpwrapper.real_close)NT)
r� r� r� r� rc r� rf r� rh rk rL rL rL rM r� _ s �
-r� c C s� i } t j�� D ]4\}}|�� }|r|dd � dkr|| |d d� < qdt jkrZ| �dd � t j�� D ]J\}}|dd � dkrd|�� }|r�|| |d d� < qd| �|d d� d � qd| S )Ni�����_proxyZREQUEST_METHODr� )r[ �environr rx r� )r& r_ r� rL rL rM �getproxies_environment� s
rn c C s� |d krt � }z |d }W n tk
r0 Y dS X |dkr>dS | �� } t| �\}}|�d�D ]Z}|�� }|r\|�d�}|�� }||ks�| |kr� dS d| }|�|�s�| �|�r\ dS q\dS )NZnoF�*Tr� �.)rn r� rx r
rX rd �lstripr )rz r& Zno_proxy�hostonlyrC r_ rL rL rM �proxy_bypass_environment� s*
rs c C s0 ddl m } t| �\}}dd� }d| kr4|d r4dS d }|�dd �D ]�}|sNqDt�d
|�}|d k �r|d kr�zt�|�}||�}W n tk
r� Y qDY nX ||�d ��} |�d �}
|
d kr�d
|�d �� d�d }
nt
|
d d � �}
|
dk sD|
dkr�qDd|
}
||
? | |
? k�r* dS qD|| |�rD dS qDdS )Nr )�fnmatchc S sh | � d�}ttt|��}t|�dkr<|ddddg d d� }|d d> |d d> B |d d> B |d B S )
Nrp r� r � rV r} r: r| rS )rX r� r� rb rd )ZipAddrrB rL rL rM �ip2num
s
z,_proxy_bypass_macosx_sysconf.<locals>.ip2numrp Zexclude_simpleT�
exceptionsrL z(\d+(?:\.\d+)*)(/\d+)?rV r: r| � F) rt r
r� rf rJ r� r� rq �group�countrb ) rz �proxy_settingsrt rr rC rv ZhostIPr� r rD �maskrL rL rM � _proxy_bypass_macosx_sysconf
s>
r} �darwin)�_get_proxy_settings� _get_proxiesc C s t � }t| |�S rN )r r} )rz r{ rL rL rM �proxy_bypass_macosx_sysconfF
s r� c C s t � S rN )r� rL rL rL rM �getproxies_macosx_sysconfJ
s r� c C s t � }|rt| |�S t| �S d S rN )rn rs r� �rz r& rL rL rM r, T
s
r, c C s t � p
t� S rN )rn r� rL rL rL rM r5 a
s c
C s i } z dd l }W n tk
r( | Y S X z�|�|jd�}|�|d�d }|r�t|�|d�d �}d|kr�|�d�D ]4}|�dd�\}}t�d|�s�d ||f }|| |< qtn>|d d
� d kr�|| d < n$d
| | d < d| | d< d| | d< |� � W n t
t t fk
�r Y nX | S )Nr �;Software\Microsoft\Windows\CurrentVersion\Internet Settings� ProxyEnableZ ProxyServerr� r8 rV z
(?:[^/:]+)://z%s://%srt r& r� z http://%sz
https://%sr� zftp://%sr )
�winreg� ImportError�OpenKey�HKEY_CURRENT_USER� QueryValueExr� rX rf rJ ZCloserq rB r� )r& r� �internetSettings� proxyEnableZ proxyServer�pr� ZaddressrL rL rM �getproxies_registryf
sF
�����
r� c C s t � p
t� S rN )rn r� rL rL rL rM r5 �
s c C s| z dd l }W n tk
r" Y dS X z6|�|jd�}|�|d�d }t|�|d�d �}W n tk
rp Y dS X |rz|s~dS t| �\}}|g} z t� |�}||kr�| �
|� W n tk
r� Y nX z t� |�}||kr�| �
|� W n tk
� r� Y nX |� d�}|D ]j} | dk�r*d|k�r* dS | �
dd �} | �
d
d �} | �
d d�} | D ] }
t�| |
tj��rR dS �qR�q dS )
Nr r� r� Z
ProxyOverrider8 z<local>rp rV z\.ro z.*�?)r� r� r� r� r� r� rq r
r� r� ra ZgetfqdnrX r rf rJ rh ) rz r� r� r� Z
proxyOverrideZrawHostrC ZaddrZfqdnrE r� rL rL rM �proxy_bypass_registry�
s` �����
r� c C s t � }|rt| |�S t| �S d S rN )rn rs r� r� rL rL rM r, �
s
)NNN)N)}r- r� r� r� Z http.clientr� r r[ � posixpathrf r� r r� r~ r^ rX r? Z urllib.errorr r r Z urllib.parser r r r r r
r r r
r r r r r r r r r Zurllib.responser r rD r� rC �__all__� version_infor� rF r� r0 r1 r` r6 r7 rg �ASCIIrv r{ r r r2 r r/ r r r" r r r! r" r# r$ r% �urandomr� r& r' r( r� r) r� r� rE ra r r. rv rx r* r� r+ r, r- r5 r_ Z
nturl2pathr4 r3 r r8 r9 r\ r� r] r3 r^ r6 r_ r` r� rn rs r} �platformZ_scproxyr r� r� r� r, r5 r� r� rL rL rL rM �<module>T s P
� � U
?m $q!+@
o v
+3:5! @ W
_
%A
- 2
PK *(�Z�|�I I , __pycache__/robotparser.cpython-38.opt-2.pycnu �[��� U
e5d�$ � @ sX d dl Z d dlZd dlZdgZe �dd�ZG dd� d�ZG dd� d�ZG dd � d �Z dS )
� N�RobotFileParser� RequestRatezrequests secondsc @ sn e Zd Zddd�Zdd� Zdd� Zdd � Zd
d � Zd d
� Zdd� Z dd� Z
dd� Z dd� Z dd� Z
dd� ZdS ) r � c C s2 g | _ g | _d | _d| _d| _| �|� d| _d S )NFr )�entries�sitemaps�
default_entry� disallow_all� allow_all�set_url� last_checked��self�url� r �*/usr/lib64/python3.8/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S �N)r �r
r r r �mtime% s zRobotFileParser.mtimec C s dd l }|� � | _d S )Nr )�timer )r
r r r r �modified. s zRobotFileParser.modifiedc C s& || _ tj�|�dd� \| _| _d S )N� � )r �urllib�parse�urlparseZhost�pathr r r r r
6 s zRobotFileParser.set_urlc
C s� zt j�| j�}W nR t jjk
rd } z0|jdkr:d| _n|jdkrT|jdk rTd| _W 5 d }~X Y n X |� � }| �
|� d�� � � d S )N)i� i� Ti� i� zutf-8)
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r
�f�err�rawr r r r ; s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | j�|� d S �N�*)�
useragentsr r �append)r
�entryr r r �
_add_entryH s
zRobotFileParser._add_entryc C sP d}t � }| �� |D �] }|sP|dkr4t � }d}n |dkrP| �|� t � }d}|�d�}|dkrn|d |� }|�� }|s|q|�dd�}t|�dkr|d �� �� |d< tj �
|d �� �|d< |d dkr�|dkr�| �|� t � }|j � |d � d}q|d dk�r.|dk�r6|j
� t|d d�� d}q|d d k�rb|dk�r6|j
� t|d d
�� d}q|d d k�r�|dk�r6|d �� �� �r�t|d �|_d}q|d d k�r|dk�r6|d �d
�}t|�dk�r|d �� �� �r|d �� �� �rtt|d �t|d ��|_d}q|d dkr| j� |d � q|dk�rL| �|� d S )Nr r � �#�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/Zsitemap)�Entryr r* �find�strip�split�len�lowerr r �unquoter' r( � rulelines�RuleLine�isdigit�int�delayr �req_rater )r
�lines�stater) �line�iZnumbersr r r r Q sj
�
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tj�tj�|��}tj�dd|j|j |j
|j f�}tj� |�}|sfd}| j
D ] }|�|�rl|�|� S ql| jr�| j�|�S dS )NFTr r. )r r r r r r r5 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r
� useragentr Z
parsed_urlr) r r r � can_fetch� s* �
zRobotFileParser.can_fetchc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S r )r r rB r: r �r
rD r) r r r � crawl_delay� s
zRobotFileParser.crawl_delayc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S r )r r rB r; r rF r r r � request_rate� s
z RobotFileParser.request_ratec C s | j s
d S | j S r )r r r r r � site_maps� s zRobotFileParser.site_mapsc C s, | j }| jd k r || jg }d�tt|��S )Nz
)r r �join�map�str)r
r r r r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__r r r r
r r* r rE rG rH rI rM r r r r r s
I
c @ s$ e Zd Zdd� Zdd� Zdd� ZdS )r7 c C s< |dkr|sd}t j�t j�|��}t j�|�| _|| _d S )Nr T)r r r@ r rA r rC )r
r rC r r r r � s
zRuleLine.__init__c C s | j dkp|�| j �S r% )r �
startswith)r
�filenamer r r rB � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rC r r r r r rM � s zRuleLine.__str__N)rN rO rP r rB rM r r r r r7 � s r7 c @ s, e Zd Zdd� Zdd� Zdd� Zdd� Zd S )
r/ c C s g | _ g | _d | _d | _d S r )r' r6 r: r; r r r r r � s zEntry.__init__c C s� g }| j D ]}|�d|� �� q
| jd k r<|�d| j� �� | jd k rf| j}|�d|j� d|j� �� |�tt| j �� d�
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r. �
) r' r( r: r; ZrequestsZseconds�extendrK rL r6 rJ )r
Zret�agentZrater r r rM � s
z
Entry.__str__c C sF |� d�d �� }| jD ](}|dkr* dS |�� }||kr dS qdS )Nr. r r& TF)r2 r4 r' )r
rD rU r r r rB � s
zEntry.applies_toc C s$ | j D ]}|�|�r|j S qdS )NT)r6 rB rC )r
rR r> r r r rC
s
zEntry.allowanceN)rN rO rP r rM rB rC r r r r r/ � s
r/ )
� collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r7 r/ r r r r �<module>
s BPK *(�Z�f<.�g �g & __pycache__/parse.cpython-38.opt-2.pycnu �[��� U
&�.e�� � @ s� d dl Z d dlZd dlZd dlZd dlZdddddddd d
d d d
dddddddddgZdddddd d d d d d!d"d#d$d%d&d'd(d)gZdddddd*d d d d!d d d+d"d#d$d,d&d'd%d-d.d/d(d)gZddd0d"dd d d d#d$d1d2d!d%d3gZdd0d4d5d*d d d+d1d2g
Z ddd d d d d!dd#d$d1d2g Z
ddd0ddd5dd d d d+d d"g
Z d6Z d7Z
d8d9d:gZd;Zi Zd<d=� Zd>Zd?Zd@dA� ZeefdBdC�ZeefdDdE�ZdFdG� ZG dHdI� dIe�ZG dJdK� dKe�ZG dLdM� dMe�ZG dNdO� dOee�Z G dPdQ� dQee�Z d dRlm Z e ddS�Z e ddT�Z e ddU�Z!dVe _"dWe j#_"dXe j$_"dYe _"dZe j%_"d[e j&_"d\e j'_"d]e j(_"d^e j$_"d_e!_"e j%j"e!j%_"e j&j"e!j&_"e j'j"e!j'_"d`e!j)_"e j(j"e!j(_"e j$j"e!j$_"e Z*G dad� de e�Z+G dbd� de e �Z,G dcd� de!e �Z-G ddd� de e�Z.G ded� de e �Z/G dfd� de!e �Z0dgdh� Z1e1� [1d�djd�Z2dkdl� Z3d�dmdn�Z4dodp� Z5dqdr� Z6d�dsd�Z7dtd� Z8dud� Z9d�dvd�Z:dwd� Z;dxZ<da=dyd� Z>e �?dz�Z@d�d}d�ZAd�dd �ZBG d�d�� d�eC�ZDd�ZEdaFd�d�d
�ZGd�d�d�ZHeId��ZJeKeJ�ZLi ZMG d�d�� d�ejN�ZOd�d�d �ZPd�d�d �ZQd�d�d
�ZRd~dddeQfd�d�ZSd�d�� ZTd�d�� ZUd�d�� ZVd�d�� ZWdaXd�d�� ZYd�d�� ZZda[d�d�� Z\d�d�� Z]d�d�� Z^d�d�� Z_d�d�� Z`d�d�� Zadabd�d�� Zcd�d�d��Zdd�d�d��Zed�d�� Zfd�d�� Zgd�d�� Zhd�d�� Zid�d�� Zjd�d�� Zkd�d�� Zld�d�� ZmdS )�� N�urlparse�
urlunparse�urljoin� urldefrag�urlsplit�
urlunsplit� urlencode�parse_qs� parse_qsl�quote�
quote_plus�quote_from_bytes�unquote� unquote_plus�unquote_to_bytes� DefragResult� ParseResult� SplitResult�DefragResultBytes�ParseResultBytes�SplitResultBytes� Zftp�httpZgopherZnntpZimapZwais�fileZhttpsZshttpZmmsZprosperoZrtspZrtspuZsftpZsvnzsvn+sshZwsZwssZtelnetZsnewsZrsyncZnfsZgitzgit+sshZhdlZsipZsipsZtelZmailtoZnewszAabcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789+-.z!
� �
�
� c C s t �� t�� d S �N)� _parse_cache�clear�
_safe_quoters� r" r" �$/usr/lib64/python3.8/urllib/parse.py� clear_cache` s r$ �ascii�strictc C s | S r r" )�objr" r" r# �_noopo s r( c C s | � ||�S r ��encode)r' �encoding�errorsr" r" r# �_encode_resultr s r- c s t � �fdd�| D ��S )Nc 3 s" | ]}|r|� � ��nd V qdS )r N��decode��.0�x�r+ r, r" r# � <genexpr>x s z _decode_args.<locals>.<genexpr>)�tuple)�argsr+ r, r" r3 r# � _decode_argsv s r7 c G sV t | d t�}| dd � D ] }|rt |t�|krtd��q|rH| tf S t| �tf S )Nr � z$Cannot mix str and non-str arguments)�
isinstance�str� TypeErrorr( r7 r- )r6 Z str_input�argr" r" r# � _coerce_argsz s
r= c @ s e Zd ZdZddd�ZdS )�_ResultMixinStrr" r% r& c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r r) r0 r3 r" r# r4 � s z)_ResultMixinStr.encode.<locals>.<genexpr>)�_encoded_counterpart��selfr+ r, r" r3 r# r* � s z_ResultMixinStr.encodeN)r% r& )�__name__�
__module__� __qualname__� __slots__r* r" r" r" r# r> � s r> c @ s e Zd ZdZddd�ZdS )�_ResultMixinBytesr" r% r& c s | j � �fdd�| D �� S )Nc 3 s | ]}|� � ��V qd S r r. r0 r3 r" r# r4 � s z+_ResultMixinBytes.decode.<locals>.<genexpr>)�_decoded_counterpartr@ r" r3 r# r/ � s z_ResultMixinBytes.decodeN)r% r& )rB rC rD rE r/ r" r" r" r# rF � s rF c @ s@ e Zd ZdZedd� �Zedd� �Zedd� �Zedd � �Zd
S ) �_NetlocResultMixinBaser" c C s
| j d S )Nr �� _userinfo�rA r" r" r# �username� s z _NetlocResultMixinBase.usernamec C s
| j d S )Nr8 rI rK r" r" r# �password� s z _NetlocResultMixinBase.passwordc C sD | j d }|sd S t|t�r dnd}|�|�\}}}|�� | | S )Nr �%� %)� _hostinfor9 r: � partition�lower)rA �hostname� separatorZpercentZzoner" r" r# rS � s
z _NetlocResultMixinBase.hostnamec C sl | j d }|d k rhzt|d�}W n( tk
rH d|��}t|�d �Y nX d| kr^dkshn td��|S )Nr8 �
z+Port could not be cast to integer value as r i�� zPort out of range 0-65535)rP �int�
ValueError)rA �port�messager" r" r# rX � s
z_NetlocResultMixinBase.portN) rB rC rD rE �propertyrL rM rS rX r" r" r" r# rH � s
rH c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinStrr" c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N�@�:��netloc�
rpartitionrQ �rA r_ ZuserinfoZ have_info�hostinforL Z
have_passwordrM r" r" r# rJ � s z _NetlocResultMixinStr._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nr\ �[�]r] r^ �rA r_ �_rb Z have_open_brZ bracketedrS rX r" r" r# rP � s z _NetlocResultMixinStr._hostinfoN�rB rC rD rE rZ rJ rP r" r" r" r# r[ � s
r[ c @ s( e Zd ZdZedd� �Zedd� �ZdS )�_NetlocResultMixinBytesr" c C sD | j }|�d�\}}}|r4|�d�\}}}|s<d }nd }}||fS )N� @� :r^ ra r" r" r# rJ � s z!_NetlocResultMixinBytes._userinfoc C sl | j }|�d�\}}}|�d�\}}}|rL|�d�\}}}|�d�\}}}n|�d�\}}}|sdd }||fS )Nri � [� ]rj r^ re r" r" r# rP � s z!_NetlocResultMixinBytes._hostinfoNrg r" r" r" r# rh � s
rh )�
namedtuplez url fragmentz!scheme netloc path query fragmentz(scheme netloc path params query fragmentz�
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
z$The URL with no fragment identifier.z�
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
information.
z�
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
z%Specifies URL scheme for the request.z0
Network location where the request is made to.
z@
The hierarchical path, such as the path to a file to download.
z�
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
network location.
z�
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
zq
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
z�
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
c @ s e Zd ZdZdd� ZdS )r r" c C s | j r| jd | j S | jS d S �N�#��fragment�urlrK r" r" r# �geturlI s zDefragResult.geturlN�rB rC rD rE rs r" r" r" r# r G s c @ s e Zd ZdZdd� ZdS )r r" c C s t | �S r �r rK r" r" r# rs Q s zSplitResult.geturlNrt r" r" r" r# r O s c @ s e Zd ZdZdd� ZdS )r r" c C s t | �S r �r rK r" r" r# rs V s zParseResult.geturlNrt r" r" r" r# r T s c @ s e Zd ZdZdd� ZdS )r r" c C s | j r| jd | j S | jS d S )N� #rp rK r" r" r# rs \ s zDefragResultBytes.geturlNrt r" r" r" r# r Z s c @ s e Zd ZdZdd� ZdS )r r" c C s t | �S r ru rK r" r" r# rs d s zSplitResultBytes.geturlNrt r" r" r" r# r b s c @ s e Zd ZdZdd� ZdS )r r" c C s t | �S r rv rK r" r" r# rs i s zParseResultBytes.geturlNrt r" r" r" r# r g s c C s4 t tfttfttff} | D ]\}}||_||_qd S r )r r r r r r r? rG )Z
_result_pairsZ_decodedZ_encodedr" r" r# �_fix_result_transcodingm s � rx Tc
C sf t | |�\} }}t| ||�}|\}}} }}|tkrHd| krHt| �\} }nd}t||| |||�} || �S )N�;r )r= r � uses_params� _splitparamsr )
rr �scheme�allow_fragments�_coerce_resultZ splitresultr_ �queryrq �params�resultr" r" r# r z s c C sR d| kr,| � d| �d��}|dk r6| dfS n
| � d�}| d |� | |d d � fS )N�/ry r r r8 )�find�rfind)rr �ir" r" r# r{ � s
r{ c C sH t | �}dD ]"}| �||�}|dkr t||�}q | ||� | |d � fS )Nz/?#r )�lenr� �min)rr �start�delim�cZwdelimr" r" r# � _splitnetloc� s r� c C s� | r | � � rd S dd l}| �dd�}|�dd�}|�dd�}|�dd�}|�d|�}||kr`d S dD ] }||krdtd | d
d ��qdd S ) Nr r\ r r] ro �?�NFKCz/?#@:znetloc 'z' contains invalid z#characters under NFKC normalization)�isascii� unicodedata�replace� normalizerW )r_ r� �nZnetloc2r� r" r" r# � _checknetloc� s �r� c C s t D ]}| �|d�} q| S )Nr )�_UNSAFE_URL_BYTES_TO_REMOVEr� )rr �br" r" r# � _remove_unsafe_bytes_from_url� s r� c
C s� t | |�\} }}t| �} t|�}| �t�} |�t�}t|�}| ||t| �t|�f}t�|d �}|rj||�S t t�t
kr|t � d } }}| � d�} | dk�r�| d | � dk�rn| | d d � } | d d� dk�r t
| d�\}} d|kr�d |k�sd |k�r d|k�r td
��|�r,d | k�r,| �d d�\} }d | k�rF| �d d�\} }t|� td|| ||�}
|
t|< ||
�S | d | � D ]} | tk�rz �qҐqz| | d d � } | �r�td
d� | D ���r�| d | � �� | }} | d d� dk�r"t
| d�\}} d|k�rd |k�sd |k�r"d|k�r"td
��|�rBd | k�rB| �d d�\} }d | k�r\| �d d�\} }t|� t||| ||�}
|
t|< ||
�S )Nr r] r r r8 � �//rc rd zInvalid IPv6 URLro r� c s s | ]}|d kV qdS )�
0123456789Nr" �r1 r� r" r" r# r4 � s zurlsplit.<locals>.<genexpr>)r= r� �lstrip�_WHATWG_C0_CONTROL_OR_SPACE�strip�bool�typer �getr� �MAX_CACHE_SIZEr$ r� r� rW �splitr� r � scheme_chars�anyrR )
rr r| r} r~ �key�cachedr_ r rq r� �vr� �restr" r" r# r � sn
��
��
c C s< t | � \}}}}}}}|r&d||f }|t|||||f��S )Nz%s;%s)r= r )�
componentsr| r_ rr r� r rq r~ r" r" r# r � s
� c C s� t | � \}}}}}}|s4|r`|tkr`|d d� dkr`|rP|d d� dkrPd| }d|pXd | }|rp|d | }|r�|d | }|r�|d | }||�S ) Nr� r� r8 r� r r] r� ro )r= � uses_netloc)r� r| r_ rr r rq r~ r" r" r# r � s � c C s� | s|S |s| S t | |�\} }}t| d|�\}}}}}} t|||�\}
} } }
}}|
|ks`|
tkrh||�S |
tkr�| r�|t|
| | |
||f��S |} | s�|
s�|} |}
|s�|}|t|
| | |
||f��S |�d�}|d dkr�|d= | d d� dkr�| �d�}n(|| �d� }td |dd� �|dd�< g }|D ]P}|dk�r\z |�� W n tk
�rX Y nX n|dk�rl�q(n
|� |� �q(|d dk�r�|� d� |t|
| d�
|��p�d|
||f��S )Nr r� ���r8 �..�.)r� r� ) r= r �
uses_relativer� r r� �filter�pop�
IndexError�append�join)�baserr r} r~ ZbschemeZbnetlocZbpathZbparamsZbqueryZ bfragmentr| r_ �pathr� r rq Z
base_partsZsegmentsZ
resolved_pathZsegr" r" r# r sp
�
�
�
�
� �c C sT t | �\} }d| kr>t| �\}}}}}}t|||||df�}nd}| }|t||��S )Nro r )r= r r r ) rr r~ �sr� �p�a�qZfragZdefragr" r" r# r T s Z0123456789ABCDEFabcdefc C s� | s| j dS t| t�r"| �d�} | � d�}t|�dkr<| S |d g}|j}td krbdd� tD �a|dd � D ]R}z(|t|d d� � ||dd � � W qn tk
r� |d� ||� Y qnX qnd� |�S ) N� �utf-8rO r8 r c S s. i | ]&}t D ] }|| �� t�|| ��q qS r" )�_hexdigr* �bytes�fromhex)r1 r� r� r" r" r# �
<dictcomp>z s
�
z$unquote_to_bytes.<locals>.<dictcomp>r� )
r� r9 r: r* r� r� �
_hextobyter� �KeyErrorr� )�string�bits�resr� �itemr" r" r# r g s,
�z([ -]+)r� r� c C s� t | t�rtd��d| kr$| j | S |d kr0d}|d kr<d}t�| �}|d g}|j}tdt|�d�D ],}|t|| �� ||�� |||d � qfd�
|�S ) NzExpected str, got bytesrN r� r� r r8 r� r ) r9 r� r; r� �_asciirer� �ranger� r r/ r� )r� r+ r, r� r� r� r� r" r" r# r � s
Fc C sN i }t | ||||||d�}|D ]*\} }
| |kr>|| �|
� q |
g|| < q |S )N)r+ r, �max_num_fieldsrT )r
r� ) �qs�keep_blank_values�strict_parsingr+ r, r� rT Z
parsed_result�pairs�name�valuer" r" r# r � s � c @ s e Zd ZdS )� _QueryStringSeparatorWarningN)rB rC rD r" r" r" r# r� � s r� z/etc/python/urllib.cfgc C s� t | �\} }t|t�r |�d�}|r2t|ttf�sB|d k rBtd��t� }|d k�rRt}d} |d krrtj �
| �}d}
|d kr�z t t �} W n t
k
r� Y nJX | �: dd l} | jd dd�}
|
�| � |
j
d| d d �}|aW 5 Q R X t }
|d k�rd
| k�rdd lm} |d td
d� d}n:|dk�r(|}n*t|�dk�rRt| � d|
� d�d d ��|d k �r�||k�r�d| �d� | �d
� }nd| �|� }||k �r�td��||k�r�dd� | �d�D �}ndd� | �|�D �}g }|D ]�}|�s�|�s�q�|�dd�}t|�d
k�r4|�r td|f ��|�r�|�d � n�q�t|d ��sH|�r�|d �d d �}t|||d �}||�}|d �d d �}t|||d �}||�}|�||f� �q�|S ) Nr% z*Separator must be of type string or bytes.ZPYTHON_URLLIB_QS_SEPARATORzenvironment variabler )ro )Z
interpolationZcomment_prefixesr )Zfallbackry )�warna The default separator of urllib.parse.parse_qsl and parse_qs was changed to '&' to avoid a web cache poisoning issue (CVE-2021-23336). By default, semicolons no longer act as query field separators. See https://access.redhat.com/articles/5860431 for more details.r� ��
stacklevel�&Zlegacyr8 z (from z) must contain z 1 character, or "legacy". See z<https://access.redhat.com/articles/5860431 for more details.z Max number of fields exceededc S s g | ]}|� d �D ]}|�qqS )ry �r� )r1 �s1�s2r" r" r# �
<listcomp>7 s z parse_qsl.<locals>.<listcomp>c S s g | ]}|�qS r" r" )r1 r� r" r" r# r� 9 s �=zbad query field: %rr �+� r3 )r= r9 r� r/ r: rW �object�_default_qs_separator�os�environr� �open� _QS_SEPARATOR_CONFIG_FILENAME�FileNotFoundError� configparserZ ConfigParserZ read_file�warningsr� r� r� �countr� r� r� r )r� r� r� r+ r, r� rT r~ Z_legacyZ envvar_nameZ
config_sourcer r� Zconfigr� �
num_fieldsr� �rZ
name_valueZnvr� r� r" r" r# r
� s�
�
�
���
c C s | � dd�} t| ||�S )Nr� r� )r� r )r� r+ r, r" r" r# r Q s sB ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-~c @ s$ e Zd Zdd� Zdd� Zdd� ZdS )�Quoterc C s t �|�| _d S r )� _ALWAYS_SAFE�union�safe)rA r� r" r" r# �__init__i s zQuoter.__init__c C s d| j jt| �f S )Nz<%s %r>)� __class__rB �dictrK r" r" r# �__repr__m s zQuoter.__repr__c C s( || j krt|�nd�|�}|| |< |S )Nz%{:02X})r� �chr�format)rA r� r� r" r" r# � __missing__q s zQuoter.__missing__N)rB rC rD r� r� r� r" r" r" r# r� a s r� r� c C sb t | t�r8| s| S |d kr d}|d kr*d}| �||�} n |d k rHtd��|d k rXtd��t| |�S )Nr� r& z,quote() doesn't support 'encoding' for bytesz*quote() doesn't support 'errors' for bytes)r9 r: r* r; r
)r� r� r+ r, r" r" r# r w s '
c C sd t | t�rd| ks$t | t�r2d| kr2t| |||�S t |t�rBd}nd}t| || ||�} | �dd�S )Nr� � r� )r9 r: r� r r� )r� r� r+ r, Zspacer" r" r# r � s ��
c s� t | ttf�std��| s dS t |t�r6|�dd�}ntdd� |D ��}| �t| �s^| �� S z t | � W n& t
k
r� t |�j t |< � Y nX d�
� fdd�| D ��S )Nz!quote_from_bytes() expected bytesr r% �ignorec S s g | ]}|d k r|�qS )� r" r� r" r" r# r� � s z$quote_from_bytes.<locals>.<listcomp>c s g | ] }� |��qS r" r" )r1 �char�Zquoterr" r# r� � s )r9 r� � bytearrayr; r: r* �rstrip�_ALWAYS_SAFE_BYTESr/ r! r� r� � __getitem__r� )Zbsr� r" r� r# r
� s
c C s t | d�r| �� } nPz t| �r0t| d t�s0t�W n0 tk
rb t�� \}}}td��|��Y nX g } |s�| D ]j\}
} t|
t �r�||
|�}
n|t
|
�|||�}
t| t �r�|| |�} n|t
| �|||�} | � |
d | � qp�n"| D �]\}
} t|
t ��r||
|�}
n|t
|
�|||�}
t| t ��rB|| |�} | � |
d | � q�t| t
��rp|| |||�} | � |
d | � q�z t| �} W n: tk
�r� |t
| �|||�} | � |
d | � Y q�X | D ]B}
t|
t ��r�||
|�}
n|t
|
�|||�}
| � |
d |
� �q�q�d� | �S )N�itemsr z1not a valid non-string sequence or mapping objectr� r� )
�hasattrr� r� r9 r5 r; �sys�exc_info�with_tracebackr� r: r� r� )r Zdoseqr� r+ r, Z quote_viaZtyZva�tb�l�kr� r2 Zeltr" r" r# r � sR
�
c C s t jdtdd� t| �S )Nz/urllib.parse.to_bytes() is deprecated as of 3.8r� r� )r� r� �DeprecationWarning� _to_bytes�rr r" r" r# �to_bytes% s
�r c C sJ t | t�rFz| �d��� } W n( tk
rD tdt| � d ��Y nX | S )N�ASCIIzURL z contains non-ASCII characters)r9 r: r* r/ � UnicodeError�reprr r" r" r# r + s
� r c C s` t | ��� } | d d� dkr<| dd � dkr<| dd� �� } | d d� dkr\| dd � �� } | S )Nr8 �<r� �>� zURL:)r: r� r r" r" r# �unwrap9 s r
c C s t jdtdd� t| �S )NzUurllib.parse.splittype() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splittyper r" r" r# � splittypeF s
�r c C sD t d krt�dtj�a t �| �}|r<|�� \}}|�� |fS d | fS )Nz
([^/:]+):(.*))� _typeprog�re�compile�DOTALL�match�groupsrR )rr r r| �datar" r" r# r N s
r c C s t jdtdd� t| �S )NzUurllib.parse.splithost() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splithostr r" r" r# � splithost[ s
�r c C sX t d krt�dtj�a t �| �}|rP|�� \}}|rH|d dkrHd| }||fS d | fS )Nz//([^/#?]*)(.*)r r� )� _hostprogr r r r r )rr r Z host_portr� r" r" r# r c s
r c C s t jdtdd� t| �S )NzUurllib.parse.splituser() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splituser��hostr" r" r# � splituserr s
�r c C s | � d�\}}} |r|nd | fS )Nr\ �r` )r �userr� r" r" r# r y s r c C s t jdtdd� t| �S )NzWurllib.parse.splitpasswd() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitpasswd)r r" r" r# � splitpasswd s
�r! c C s | � d�\} }}| |r|nd fS �Nr] �rQ )r r� Zpasswdr" r" r# r � s r c C s t jdtdd� t| �S )NzUurllib.parse.splitport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitportr r" r" r# � splitport� s
�r% c C sD t d krt�dtj�a t �| �}|r<|�� \} }|r<| |fS | d fS )Nz
(.*):([0-9]*))� _portprogr r r � fullmatchr )r r rX r" r" r# r$ � s
r$ r� c C s t jdtdd� t| |�S )NzVurllib.parse.splitnport() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitnport)r �defportr" r" r# �
splitnport� s
�r* c C sT | � d�\} }}|s|} n2|rLz t|�}W n tk
rB d }Y nX | |fS | |fS r" )r` rV rW )r r) r� rX Znportr" r" r# r( � s
r( c C s t jdtdd� t| �S )NzVurllib.parse.splitquery() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splitqueryr r" r" r# �
splitquery� s
�r, c C s$ | � d�\}}}|r ||fS | d fS )Nr� r )rr r� r� r r" r" r# r+ � s r+ c C s t jdtdd� t| �S )NzTurllib.parse.splittag() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r � _splittagr r" r" r# �splittag� s
�r. c C s$ | � d�\}}}|r ||fS | d fS rn r )rr r� r� �tagr" r" r# r- � s r- c C s t jdtdd� t| �S )NzUurllib.parse.splitattr() is deprecated as of 3.8, use urllib.parse.urlparse() insteadr� r� )r� r� r �
_splitattrr r" r" r# � splitattr� s
�r1 c C s | � d�}|d |dd � fS )Nry r r8 r� )rr Zwordsr" r" r# r0 � s
r0 c C s t jdtdd� t| �S )NzWurllib.parse.splitvalue() is deprecated as of 3.8, use urllib.parse.parse_qsl() insteadr� r� )r� r� r � _splitvalue)�attrr" r" r# �
splitvalue� s
�r4 c C s | � d�\} }}| |r|nd fS )Nr� r# )r3 r� r� r" r" r# r2 � s r2 )r T)r )r T)T)r� r� )FFr� r� NN)FFr� r� NN)r� r� )r� NN)r NN)r� )r� )r� )nr r� r� � collectionsr� �__all__r� r� rz Znon_hierarchicalZ
uses_queryZ
uses_fragmentr� r� r� r� r r$ Z_implicit_encodingZ_implicit_errorsr( r- r7 r= r� r> rF rH r[ rh rm Z_DefragResultBaseZ_SplitResultBaseZ_ParseResultBase�__doc__rr rq r| r_ r� r r� Z
ResultBaser r r r r r rx r r{ r� r� r� r r r r r r� r� r r r� r r �RuntimeWarningr� r� r� r
r � frozensetr� r� r� r! � defaultdictr� r r r
r r r r
r r r r r r r r r! r r% r& r$ r* r( r, r+ r. r- r1 r0 r4 r2 r" r" r" r# �<module>" s� � � � � � � �
�
�
%
� �
?
E
�
) �
}
6
�
Q
PK *(�Z�,� � , __pycache__/robotparser.cpython-38.opt-1.pycnu �[��� U
e5d�$ � @ s\ d Z ddlZddlZddlZdgZe�dd�ZG dd� d�ZG dd� d�Z G d d
� d
�Z
dS ) a% robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://www.robotstxt.org/norobots-rfc.txt
� N�RobotFileParser� RequestRatezrequests secondsc @ sr e Zd ZdZd dd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� ZdS ) r zs This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
� c C s2 g | _ g | _d | _d| _d| _| �|� d| _d S )NFr )�entries�sitemaps�
default_entry� disallow_all� allow_all�set_url� last_checked��self�url� r �*/usr/lib64/python3.8/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S )z�Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
)r �r
r r r �mtime% s zRobotFileParser.mtimec C s ddl }|� � | _dS )zYSets the time the robots.txt file was last fetched to the
current time.
r N)�timer )r
r r r r �modified. s zRobotFileParser.modifiedc C s& || _ tj�|�dd� \| _| _dS )z,Sets the URL referring to a robots.txt file.� � N)r �urllib�parse�urlparseZhost�pathr r r r r
6 s zRobotFileParser.set_urlc
C s� zt j�| j�}W nR t jjk
rd } z0|jdkr:d| _n|jdkrT|jdk rTd| _W 5 d}~X Y n X |� � }| �
|� d�� � � dS )z4Reads the robots.txt URL and feeds it to the parser.)i� i� Ti� i� Nzutf-8)
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r
�f�err�rawr r r r ; s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | j�|� d S �N�*)�
useragentsr r �append)r
�entryr r r �
_add_entryH s
zRobotFileParser._add_entryc C sP d}t � }| �� |D �] }|sP|dkr4t � }d}n |dkrP| �|� t � }d}|�d�}|dkrn|d|� }|�� }|s|q|�dd�}t|�dkr|d �� �� |d< tj �
|d �� �|d< |d dkr�|dkr�| �|� t � }|j � |d � d}q|d dk�r.|dk�r6|j
� t|d d �� d}q|d d
k�rb|dk�r6|j
� t|d d �� d}q|d d k�r�|dk�r6|d �� �� �r�t|d �|_d}q|d d
k�r|dk�r6|d �d�}t|�dk�r|d �� �� �r|d �� �� �rtt|d �t|d ��|_d}q|d dkr| j� |d � q|dk�rL| �|� dS )z�Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
r r � �#N�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/Zsitemap)�Entryr r) �find�strip�split�len�lowerr r �unquoter& r' � rulelines�RuleLine�isdigit�int�delayr �req_rater )r
�lines�stater( �line�iZnumbersr r r r Q sj
�
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tj�tj�|��}tj�dd|j|j |j
|j f�}tj� |�}|sfd}| j
D ] }|�|�rl|�|� S ql| jr�| j�|�S dS )z=using the parsed robots.txt decide if useragent can fetch urlFTr r- )r r r r r r r4 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r
� useragentr Z
parsed_urlr( r r r � can_fetch� s* �
zRobotFileParser.can_fetchc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S �N)r r rA r9 r �r
rC r( r r r � crawl_delay� s
zRobotFileParser.crawl_delayc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S rE )r r rA r: r rF r r r � request_rate� s
z RobotFileParser.request_ratec C s | j s
d S | j S rE )r r r r r � site_maps� s zRobotFileParser.site_mapsc C s, | j }| jd k r || jg }d�tt|��S )Nz
)r r �join�map�str)r
r r r r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__�__doc__r r r r
r r) r rD rG rH rI rM r r r r r s
I
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r6 zoA rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path.c C s< |dkr|sd}t j�t j�|��}t j�|�| _|| _d S )Nr T)r r r? r r@ r rB )r
r rB r r r r � s
zRuleLine.__init__c C s | j dkp|�| j �S r$ )r �
startswith)r
�filenamer r r rA � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rB r r r r r rM � s zRuleLine.__str__N)rN rO rP rQ r rA rM r r r r r6 � s r6 c @ s0 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd
S ) r. z?An entry has one or more user-agents and zero or more rulelinesc C s g | _ g | _d | _d | _d S rE )r& r5 r9 r: r r r r r � s zEntry.__init__c C s� g }| j D ]}|�d|� �� q
| jd k r<|�d| j� �� | jd k rf| j}|�d|j� d|j� �� |�tt| j �� d�
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r- �
) r& r' r9 r: ZrequestsZseconds�extendrK rL r5 rJ )r
Zret�agentZrater r r rM � s
z
Entry.__str__c C sF |� d�d �� }| jD ](}|dkr* dS |�� }||kr dS qdS )z2check if this entry applies to the specified agentr- r r% TF)r1 r3 r& )r
rC rV r r r rA � s
zEntry.applies_toc C s$ | j D ]}|�|�r|j S qdS )zZPreconditions:
- our agent applies to this entry
- filename is URL decodedT)r5 rA rB )r
rS r= r r r rB
s
zEntry.allowanceN)rN rO rP rQ r rM rA rB r r r r r. � s
r. ) rQ � collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r6 r. r r r r �<module> s BPK *(�ZQ�t�
�
) __pycache__/response.cpython-38.opt-2.pycnu �[��� U
e5d� � @ sZ d dl Z ddddgZG dd� de j�ZG dd� de�ZG dd� de�ZG d d� de�ZdS )
� N�addbase� addclosehook�addinfo�
addinfourlc s4 e Zd Z� fdd�Zdd� Zdd� Zdd� Z� ZS ) r c s t t| �j|ddd� || _d S )Nz<urllib response>F)�delete)�superr �__init__�fp)�selfr �� __class__� �'/usr/lib64/python3.8/urllib/response.pyr s zaddbase.__init__c C s d| j jt| �| jf S )Nz<%s at %r whose fp = %r>)r �__name__�id�file�r
r
r
r �__repr__ s �zaddbase.__repr__c C s | j jrtd��| S )Nz I/O operation on closed file)r �closed�
ValueErrorr r
r
r � __enter__ s zaddbase.__enter__c C s | � � d S �N)�close)r
�type�value� tracebackr
r
r �__exit__! s zaddbase.__exit__)r �
__module__� __qualname__r r r r �
__classcell__r
r
r r r s c s( e Zd Z� fdd�Z� fdd�Z� ZS )r c s t t| ��|� || _|| _d S r )r r r � closehook�hookargs)r
r r r! r r
r r ( s zaddclosehook.__init__c s> z(| j}| j}|r&d | _d | _||� W 5 t t| ��� X d S r )r r r r r! )r
r r! r r
r r - s zaddclosehook.close)r r r r r r r
r
r r r % s c s$ e Zd Z� fdd�Zdd� Z� ZS )r c s t t| ��|� || _d S r )r r r �headers)r
r r" r r
r r < s zaddinfo.__init__c C s | j S r )r" r r
r
r �info@ s z addinfo.info)r r r r r# r r
r
r r r 9 s c s. e Zd Zd� fdd� Zdd� Zdd� Z� ZS ) r Nc s" t t| ��||� || _|| _d S r )r r r �url�code)r
r r" r$ r% r r
r r G s zaddinfourl.__init__c C s | j S r )r% r r
r
r �getcodeL s zaddinfourl.getcodec C s | j S r )r$ r r
r
r �geturlO s zaddinfourl.geturl)N)r r r r r& r' r r
r
r r r D s )Ztempfile�__all__Z_TemporaryFileWrapperr r r r r
r
r
r �<module> s
PK *(�Z�,� � & __pycache__/robotparser.cpython-38.pycnu �[��� U
e5d�$ � @ s\ d Z ddlZddlZddlZdgZe�dd�ZG dd� d�ZG dd� d�Z G d d
� d
�Z
dS ) a% robotparser.py
Copyright (C) 2000 Bastian Kleineidam
You can choose between two licenses when using this package:
1) GNU GPLv2
2) PSF license for Python 2.2
The robots.txt Exclusion Protocol is implemented as specified in
http://www.robotstxt.org/norobots-rfc.txt
� N�RobotFileParser� RequestRatezrequests secondsc @ sr e Zd ZdZd dd�Zdd� Zdd� Zd d
� Zd d � Zd
d� Z dd� Z
dd� Z dd� Z dd� Z
dd� Zdd� ZdS ) r zs This class provides a set of methods to read, parse and answer
questions about a single robots.txt file.
� c C s2 g | _ g | _d | _d| _d| _| �|� d| _d S )NFr )�entries�sitemaps�
default_entry� disallow_all� allow_all�set_url� last_checked��self�url� r �*/usr/lib64/python3.8/urllib/robotparser.py�__init__ s
zRobotFileParser.__init__c C s | j S )z�Returns the time the robots.txt file was last fetched.
This is useful for long-running web spiders that need to
check for new robots.txt files periodically.
)r �r
r r r �mtime% s zRobotFileParser.mtimec C s ddl }|� � | _dS )zYSets the time the robots.txt file was last fetched to the
current time.
r N)�timer )r
r r r r �modified. s zRobotFileParser.modifiedc C s& || _ tj�|�dd� \| _| _dS )z,Sets the URL referring to a robots.txt file.� � N)r �urllib�parse�urlparseZhost�pathr r r r r
6 s zRobotFileParser.set_urlc
C s� zt j�| j�}W nR t jjk
rd } z0|jdkr:d| _n|jdkrT|jdk rTd| _W 5 d}~X Y n X |� � }| �
|� d�� � � dS )z4Reads the robots.txt URL and feeds it to the parser.)i� i� Ti� i� Nzutf-8)
r ZrequestZurlopenr �errorZ HTTPError�coder r �readr �decode�
splitlines)r
�f�err�rawr r r r ; s
zRobotFileParser.readc C s, d|j kr | jd kr(|| _n | j�|� d S �N�*)�
useragentsr r �append)r
�entryr r r �
_add_entryH s
zRobotFileParser._add_entryc C sP d}t � }| �� |D �] }|sP|dkr4t � }d}n |dkrP| �|� t � }d}|�d�}|dkrn|d|� }|�� }|s|q|�dd�}t|�dkr|d �� �� |d< tj �
|d �� �|d< |d dkr�|dkr�| �|� t � }|j � |d � d}q|d dk�r.|dk�r6|j
� t|d d �� d}q|d d
k�rb|dk�r6|j
� t|d d �� d}q|d d k�r�|dk�r6|d �� �� �r�t|d �|_d}q|d d
k�r|dk�r6|d �d�}t|�dk�r|d �� �� �r|d �� �� �rtt|d �t|d ��|_d}q|d dkr| j� |d � q|dk�rL| �|� dS )z�Parse the input lines from a robots.txt file.
We allow that a user-agent: line is not preceded by
one or more blank lines.
r r � �#N�:z
user-agentZdisallowFZallowTz crawl-delayz request-rate�/Zsitemap)�Entryr r) �find�strip�split�len�lowerr r �unquoter& r' � rulelines�RuleLine�isdigit�int�delayr �req_rater )r
�lines�stater( �line�iZnumbersr r r r Q sj
�
zRobotFileParser.parsec C s� | j r
dS | jrdS | js dS tj�tj�|��}tj�dd|j|j |j
|j f�}tj� |�}|sfd}| j
D ] }|�|�rl|�|� S ql| jr�| j�|�S dS )z=using the parsed robots.txt decide if useragent can fetch urlFTr r- )r r r r r r r4 �
urlunparser ZparamsZqueryZfragment�quoter �
applies_to� allowancer )r
� useragentr Z
parsed_urlr( r r r � can_fetch� s* �
zRobotFileParser.can_fetchc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S �N)r r rA r9 r �r
rC r( r r r � crawl_delay� s
zRobotFileParser.crawl_delayc C s> | � � s d S | jD ]}|�|�r|j S q| jr:| jjS d S rE )r r rA r: r rF r r r � request_rate� s
z RobotFileParser.request_ratec C s | j s
d S | j S rE )r r r r r � site_maps� s zRobotFileParser.site_mapsc C s, | j }| jd k r || jg }d�tt|��S )Nz
)r r �join�map�str)r
r r r r �__str__� s
zRobotFileParser.__str__N)r )�__name__�
__module__� __qualname__�__doc__r r r r
r r) r rD rG rH rI rM r r r r r s
I
c @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) r6 zoA rule line is a single "Allow:" (allowance==True) or "Disallow:"
(allowance==False) followed by a path.c C s< |dkr|sd}t j�t j�|��}t j�|�| _|| _d S )Nr T)r r r? r r@ r rB )r
r rB r r r r � s
zRuleLine.__init__c C s | j dkp|�| j �S r$ )r �
startswith)r
�filenamer r r rA � s zRuleLine.applies_toc C s | j r
dndd | j S )NZAllowZDisallowz: )rB r r r r r rM � s zRuleLine.__str__N)rN rO rP rQ r rA rM r r r r r6 � s r6 c @ s0 e Zd ZdZdd� Zdd� Zdd� Zdd � Zd
S ) r. z?An entry has one or more user-agents and zero or more rulelinesc C s g | _ g | _d | _d | _d S rE )r& r5 r9 r: r r r r r � s zEntry.__init__c C s� g }| j D ]}|�d|� �� q
| jd k r<|�d| j� �� | jd k rf| j}|�d|j� d|j� �� |�tt| j �� d�
|�S )Nz User-agent: z
Crawl-delay: zRequest-rate: r- �
) r& r' r9 r: ZrequestsZseconds�extendrK rL r5 rJ )r
Zret�agentZrater r r rM � s
z
Entry.__str__c C sF |� d�d �� }| jD ](}|dkr* dS |�� }||kr dS qdS )z2check if this entry applies to the specified agentr- r r% TF)r1 r3 r& )r
rC rV r r r rA � s
zEntry.applies_toc C s$ | j D ]}|�|�r|j S qdS )zZPreconditions:
- our agent applies to this entry
- filename is URL decodedT)r5 rA rB )r
rS r= r r r rB
s
zEntry.allowanceN)rN rO rP rQ r rM rA rB r r r r r. � s
r. ) rQ � collectionsZ urllib.parser Zurllib.request�__all__�
namedtupler r r6 r. r r r r �<module> s BPK *(�Z�ͭ� � # __pycache__/__init__.cpython-38.pycnu �[��� U
��.e � @ s d S )N� r r r �'/usr/lib64/python3.8/urllib/__init__.py�<module> � PK (�Z __init__.pynu �[��� PK (�Z�%��$ �$ ; robotparser.pynu �[��� PK (�Z����� �� I% parse.pynu �[��� PK (�Z� ��� ��
>� request.pynu �[��� PK (�Z��P2� � ) 5f __pycache__/response.cpython-36.opt-1.pycnu �[��� PK (�Z�
�� � & +s __pycache__/robotparser.cpython-36.pycnu �[��� PK (�Z��
z z ) � __pycache__/__init__.cpython-36.opt-2.pycnu �[��� PK (�Z��d��
�
& � __pycache__/error.cpython-36.opt-1.pycnu �[��� PK (�ZZ� " �� __pycache__/request.cpython-36.pycnu �[��� PK (�Z��P2� � # O� __pycache__/response.cpython-36.pycnu �[��� PK (�Z�
�� � , ?� __pycache__/robotparser.cpython-36.opt-1.pycnu �[��� PK (�Z��d��
�
(� __pycache__/error.cpython-36.pycnu �[��� PK (�ZN�z z ( <� __pycache__/request.cpython-36.opt-1.pycnu �[��� PK (�Z�s/�l� l� & __pycache__/parse.cpython-36.opt-1.pycnu �[��� PK (�Z�犽�b �b & Џ __pycache__/parse.cpython-36.opt-2.pycnu �[��� PK (�Z�甖2� 2� ( �� __pycache__/request.cpython-36.opt-2.pycnu �[��� PK (�Z3<�Z
Z
) m� __pycache__/response.cpython-36.opt-2.pycnu �[��� PK (�Z�s/�l� l� � __pycache__/parse.cpython-36.pycnu �[��� PK (�Z��
z z # �p __pycache__/__init__.cpython-36.pycnu �[��� PK (�Z���;! ! & �q __pycache__/error.cpython-36.opt-2.pycnu �[��� PK (�Z��
z z ) z __pycache__/__init__.cpython-36.opt-1.pycnu �[��� PK (�Zw��3 3 , �z __pycache__/robotparser.cpython-36.opt-2.pycnu �[��� PK (�Z���QH
H
�� error.pynu �[��� PK (�Z��@� � � response.pynu �[��� PK *(�ZyR� � " 8� __pycache__/request.cpython-38.pycnu �[��� PK *(�ZSC^��
�
%� __pycache__/error.cpython-38.pycnu �[��� PK *(�Z ��� � ) p� __pycache__/response.cpython-38.opt-1.pycnu �[��� PK *(�Z ��� � # �� __pycache__/response.cpython-38.pycnu �[��� PK *(�ZSC^��
�
& �� __pycache__/error.cpython-38.opt-1.pycnu �[��� PK *(�ZH� �� �� #� __pycache__/parse.cpython-38.pycnu �[��� PK *(�Z�ͭ� � ) � __pycache__/__init__.cpython-38.opt-1.pycnu �[��� PK *(�Z�ͭ� � ) �� __pycache__/__init__.cpython-38.opt-2.pycnu �[��� PK *(�ZH� �� �� & ӂ __pycache__/parse.cpython-38.opt-1.pycnu �[��� PK *(�Zi�) ) ( �
__pycache__/request.cpython-38.opt-1.pycnu �[��� PK *(�ZO�E�X X & T- __pycache__/error.cpython-38.opt-2.pycnu �[��� PK *(�Z.�v�#� #� ( 6 __pycache__/request.cpython-38.opt-2.pycnu �[��� PK *(�Z�|�I I , }! __pycache__/robotparser.cpython-38.opt-2.pycnu �[��� PK *(�Z�f<.�g �g & "9 __pycache__/parse.cpython-38.opt-2.pycnu �[��� PK *(�Z�,� � , Y� __pycache__/robotparser.cpython-38.opt-1.pycnu �[��� PK *(�ZQ�t�
�
) V� __pycache__/response.cpython-38.opt-2.pycnu �[��� PK *(�Z�,� � & G� __pycache__/robotparser.cpython-38.pycnu �[��� PK *(�Z�ͭ� � # >� __pycache__/__init__.cpython-38.pycnu �[��� PK * * " �