| Current File : /home/mmdealscpanel/yummmdeals.com/http.tar |
__init__.py 0000644 00000014352 15032716522 0006665 0 ustar 00 from enum import IntEnum
__all__ = ['HTTPStatus']
class HTTPStatus(IntEnum):
"""HTTP status codes and reason phrases
Status codes from the following RFCs are all observed:
* RFC 7231: Hypertext Transfer Protocol (HTTP/1.1), obsoletes 2616
* RFC 6585: Additional HTTP Status Codes
* RFC 3229: Delta encoding in HTTP
* RFC 4918: HTTP Extensions for WebDAV, obsoletes 2518
* RFC 5842: Binding Extensions to WebDAV
* RFC 7238: Permanent Redirect
* RFC 2295: Transparent Content Negotiation in HTTP
* RFC 2774: An HTTP Extension Framework
* RFC 7725: An HTTP Status Code to Report Legal Obstacles
* RFC 7540: Hypertext Transfer Protocol Version 2 (HTTP/2)
"""
def __new__(cls, value, phrase, description=''):
obj = int.__new__(cls, value)
obj._value_ = value
obj.phrase = phrase
obj.description = description
return obj
# informational
CONTINUE = 100, 'Continue', 'Request received, please continue'
SWITCHING_PROTOCOLS = (101, 'Switching Protocols',
'Switching to new protocol; obey Upgrade header')
PROCESSING = 102, 'Processing'
# success
OK = 200, 'OK', 'Request fulfilled, document follows'
CREATED = 201, 'Created', 'Document created, URL follows'
ACCEPTED = (202, 'Accepted',
'Request accepted, processing continues off-line')
NON_AUTHORITATIVE_INFORMATION = (203,
'Non-Authoritative Information', 'Request fulfilled from cache')
NO_CONTENT = 204, 'No Content', 'Request fulfilled, nothing follows'
RESET_CONTENT = 205, 'Reset Content', 'Clear input form for further input'
PARTIAL_CONTENT = 206, 'Partial Content', 'Partial content follows'
MULTI_STATUS = 207, 'Multi-Status'
ALREADY_REPORTED = 208, 'Already Reported'
IM_USED = 226, 'IM Used'
# redirection
MULTIPLE_CHOICES = (300, 'Multiple Choices',
'Object has several resources -- see URI list')
MOVED_PERMANENTLY = (301, 'Moved Permanently',
'Object moved permanently -- see URI list')
FOUND = 302, 'Found', 'Object moved temporarily -- see URI list'
SEE_OTHER = 303, 'See Other', 'Object moved -- see Method and URL list'
NOT_MODIFIED = (304, 'Not Modified',
'Document has not changed since given time')
USE_PROXY = (305, 'Use Proxy',
'You must use proxy specified in Location to access this resource')
TEMPORARY_REDIRECT = (307, 'Temporary Redirect',
'Object moved temporarily -- see URI list')
PERMANENT_REDIRECT = (308, 'Permanent Redirect',
'Object moved permanently -- see URI list')
# client error
BAD_REQUEST = (400, 'Bad Request',
'Bad request syntax or unsupported method')
UNAUTHORIZED = (401, 'Unauthorized',
'No permission -- see authorization schemes')
PAYMENT_REQUIRED = (402, 'Payment Required',
'No payment -- see charging schemes')
FORBIDDEN = (403, 'Forbidden',
'Request forbidden -- authorization will not help')
NOT_FOUND = (404, 'Not Found',
'Nothing matches the given URI')
METHOD_NOT_ALLOWED = (405, 'Method Not Allowed',
'Specified method is invalid for this resource')
NOT_ACCEPTABLE = (406, 'Not Acceptable',
'URI not available in preferred format')
PROXY_AUTHENTICATION_REQUIRED = (407,
'Proxy Authentication Required',
'You must authenticate with this proxy before proceeding')
REQUEST_TIMEOUT = (408, 'Request Timeout',
'Request timed out; try again later')
CONFLICT = 409, 'Conflict', 'Request conflict'
GONE = (410, 'Gone',
'URI no longer exists and has been permanently removed')
LENGTH_REQUIRED = (411, 'Length Required',
'Client must specify Content-Length')
PRECONDITION_FAILED = (412, 'Precondition Failed',
'Precondition in headers is false')
REQUEST_ENTITY_TOO_LARGE = (413, 'Request Entity Too Large',
'Entity is too large')
REQUEST_URI_TOO_LONG = (414, 'Request-URI Too Long',
'URI is too long')
UNSUPPORTED_MEDIA_TYPE = (415, 'Unsupported Media Type',
'Entity body in unsupported format')
REQUESTED_RANGE_NOT_SATISFIABLE = (416,
'Requested Range Not Satisfiable',
'Cannot satisfy request range')
EXPECTATION_FAILED = (417, 'Expectation Failed',
'Expect condition could not be satisfied')
MISDIRECTED_REQUEST = (421, 'Misdirected Request',
'Server is not able to produce a response')
UNPROCESSABLE_ENTITY = 422, 'Unprocessable Entity'
LOCKED = 423, 'Locked'
FAILED_DEPENDENCY = 424, 'Failed Dependency'
UPGRADE_REQUIRED = 426, 'Upgrade Required'
PRECONDITION_REQUIRED = (428, 'Precondition Required',
'The origin server requires the request to be conditional')
TOO_MANY_REQUESTS = (429, 'Too Many Requests',
'The user has sent too many requests in '
'a given amount of time ("rate limiting")')
REQUEST_HEADER_FIELDS_TOO_LARGE = (431,
'Request Header Fields Too Large',
'The server is unwilling to process the request because its header '
'fields are too large')
UNAVAILABLE_FOR_LEGAL_REASONS = (451,
'Unavailable For Legal Reasons',
'The server is denying access to the '
'resource as a consequence of a legal demand')
# server errors
INTERNAL_SERVER_ERROR = (500, 'Internal Server Error',
'Server got itself in trouble')
NOT_IMPLEMENTED = (501, 'Not Implemented',
'Server does not support this operation')
BAD_GATEWAY = (502, 'Bad Gateway',
'Invalid responses from another server/proxy')
SERVICE_UNAVAILABLE = (503, 'Service Unavailable',
'The server cannot process the request due to a high load')
GATEWAY_TIMEOUT = (504, 'Gateway Timeout',
'The gateway server did not receive a timely response')
HTTP_VERSION_NOT_SUPPORTED = (505, 'HTTP Version Not Supported',
'Cannot fulfill request')
VARIANT_ALSO_NEGOTIATES = 506, 'Variant Also Negotiates'
INSUFFICIENT_STORAGE = 507, 'Insufficient Storage'
LOOP_DETECTED = 508, 'Loop Detected'
NOT_EXTENDED = 510, 'Not Extended'
NETWORK_AUTHENTICATION_REQUIRED = (511,
'Network Authentication Required',
'The client needs to authenticate to gain network access')
client.py 0000644 00000154231 15032716522 0006405 0 ustar 00 r"""HTTP/1.1 client library
<intro stuff goes here>
<other stuff, too>
HTTPConnection goes through a number of "states", which define when a client
may legally make another request or fetch the response for a particular
request. This diagram details these state transitions:
(null)
|
| HTTPConnection()
v
Idle
|
| putrequest()
v
Request-started
|
| ( putheader() )* endheaders()
v
Request-sent
|\_____________________________
| | getresponse() raises
| response = getresponse() | ConnectionError
v v
Unread-response Idle
[Response-headers-read]
|\____________________
| |
| response.read() | putrequest()
v v
Idle Req-started-unread-response
______/|
/ |
response.read() | | ( putheader() )* endheaders()
v v
Request-started Req-sent-unread-response
|
| response.read()
v
Request-sent
This diagram presents the following rules:
-- a second request may not be started until {response-headers-read}
-- a response [object] cannot be retrieved until {request-sent}
-- there is no differentiation between an unread response body and a
partially read response body
Note: this enforcement is applied by the HTTPConnection class. The
HTTPResponse class does not enforce this state machine, which
implies sophisticated clients may accelerate the request/response
pipeline. Caution should be taken, though: accelerating the states
beyond the above pattern may imply knowledge of the server's
connection-close behavior for certain requests. For example, it
is impossible to tell whether the server will close the connection
UNTIL the response headers have been read; this means that further
requests cannot be placed into the pipeline until it is known that
the server will NOT be closing the connection.
Logical State __state __response
------------- ------- ----------
Idle _CS_IDLE None
Request-started _CS_REQ_STARTED None
Request-sent _CS_REQ_SENT None
Unread-response _CS_IDLE <response_class>
Req-started-unread-response _CS_REQ_STARTED <response_class>
Req-sent-unread-response _CS_REQ_SENT <response_class>
"""
import email.parser
import email.message
import http
import io
import re
import socket
import collections.abc
from urllib.parse import urlsplit
# HTTPMessage, parse_headers(), and the HTTP status code constants are
# intentionally omitted for simplicity
__all__ = ["HTTPResponse", "HTTPConnection",
"HTTPException", "NotConnected", "UnknownProtocol",
"UnknownTransferEncoding", "UnimplementedFileMode",
"IncompleteRead", "InvalidURL", "ImproperConnectionState",
"CannotSendRequest", "CannotSendHeader", "ResponseNotReady",
"BadStatusLine", "LineTooLong", "RemoteDisconnected", "error",
"responses"]
HTTP_PORT = 80
HTTPS_PORT = 443
_UNKNOWN = 'UNKNOWN'
# connection states
_CS_IDLE = 'Idle'
_CS_REQ_STARTED = 'Request-started'
_CS_REQ_SENT = 'Request-sent'
# hack to maintain backwards compatibility
globals().update(http.HTTPStatus.__members__)
# another hack to maintain backwards compatibility
# Mapping status codes to official W3C names
responses = {v: v.phrase for v in http.HTTPStatus.__members__.values()}
# maximal line length when calling readline().
_MAXLINE = 65536
_MAXHEADERS = 100
# Header name/value ABNF (http://tools.ietf.org/html/rfc7230#section-3.2)
#
# VCHAR = %x21-7E
# obs-text = %x80-FF
# header-field = field-name ":" OWS field-value OWS
# field-name = token
# field-value = *( field-content / obs-fold )
# field-content = field-vchar [ 1*( SP / HTAB ) field-vchar ]
# field-vchar = VCHAR / obs-text
#
# obs-fold = CRLF 1*( SP / HTAB )
# ; obsolete line folding
# ; see Section 3.2.4
# token = 1*tchar
#
# tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*"
# / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
# / DIGIT / ALPHA
# ; any VCHAR, except delimiters
#
# VCHAR defined in http://tools.ietf.org/html/rfc5234#appendix-B.1
# the patterns for both name and value are more lenient than RFC
# definitions to allow for backwards compatibility
_is_legal_header_name = re.compile(rb'[^:\s][^:\r\n]*').fullmatch
_is_illegal_header_value = re.compile(rb'\n(?![ \t])|\r(?![ \t\n])').search
# These characters are not allowed within HTTP URL paths.
# See https://tools.ietf.org/html/rfc3986#section-3.3 and the
# https://tools.ietf.org/html/rfc3986#appendix-A pchar definition.
# Prevents CVE-2019-9740. Includes control characters such as \r\n.
# We don't restrict chars above \x7f as putrequest() limits us to ASCII.
_contains_disallowed_url_pchar_re = re.compile('[\x00-\x20\x7f]')
# Arguably only these _should_ allowed:
# _is_allowed_url_pchars_re = re.compile(r"^[/!$&'()*+,;=:@%a-zA-Z0-9._~-]+$")
# We are more lenient for assumed real world compatibility purposes.
# These characters are not allowed within HTTP method names
# to prevent http header injection.
_contains_disallowed_method_pchar_re = re.compile('[\x00-\x1f]')
# We always set the Content-Length header for these methods because some
# servers will otherwise respond with a 411
_METHODS_EXPECTING_BODY = {'PATCH', 'POST', 'PUT'}
def _encode(data, name='data'):
"""Call data.encode("latin-1") but show a better error message."""
try:
return data.encode("latin-1")
except UnicodeEncodeError as err:
raise UnicodeEncodeError(
err.encoding,
err.object,
err.start,
err.end,
"%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') "
"if you want to send it encoded in UTF-8." %
(name.title(), data[err.start:err.end], name)) from None
class HTTPMessage(email.message.Message):
# XXX The only usage of this method is in
# http.server.CGIHTTPRequestHandler. Maybe move the code there so
# that it doesn't need to be part of the public API. The API has
# never been defined so this could cause backwards compatibility
# issues.
def getallmatchingheaders(self, name):
"""Find all header lines matching a given header name.
Look through the list of headers and find all lines matching a given
header name (and their continuation lines). A list of the lines is
returned, without interpretation. If the header does not occur, an
empty list is returned. If the header occurs multiple times, all
occurrences are returned. Case is not important in the header name.
"""
name = name.lower() + ':'
n = len(name)
lst = []
hit = 0
for line in self.keys():
if line[:n].lower() == name:
hit = 1
elif not line[:1].isspace():
hit = 0
if hit:
lst.append(line)
return lst
def _read_headers(fp):
"""Reads potential header lines into a list from a file pointer.
Length of line is limited by _MAXLINE, and number of
headers is limited by _MAXHEADERS.
"""
headers = []
while True:
line = fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
headers.append(line)
if len(headers) > _MAXHEADERS:
raise HTTPException("got more than %d headers" % _MAXHEADERS)
if line in (b'\r\n', b'\n', b''):
break
return headers
def parse_headers(fp, _class=HTTPMessage):
"""Parses only RFC2822 headers from a file pointer.
email Parser wants to see strings rather than bytes.
But a TextIOWrapper around self.rfile would buffer too many bytes
from the stream, bytes which we later need to read as bytes.
So we read the correct bytes here, as bytes, for email Parser
to parse.
"""
headers = _read_headers(fp)
hstring = b''.join(headers).decode('iso-8859-1')
return email.parser.Parser(_class=_class).parsestr(hstring)
class HTTPResponse(io.BufferedIOBase):
# See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details.
# The bytes from the socket object are iso-8859-1 strings.
# See RFC 2616 sec 2.2 which notes an exception for MIME-encoded
# text following RFC 2047. The basic status line parsing only
# accepts iso-8859-1.
def __init__(self, sock, debuglevel=0, method=None, url=None):
# If the response includes a content-length header, we need to
# make sure that the client doesn't read more than the
# specified number of bytes. If it does, it will block until
# the server times out and closes the connection. This will
# happen if a self.fp.read() is done (without a size) whether
# self.fp is buffered or not. So, no self.fp.read() by
# clients unless they know what they are doing.
self.fp = sock.makefile("rb")
self.debuglevel = debuglevel
self._method = method
# The HTTPResponse object is returned via urllib. The clients
# of http and urllib expect different attributes for the
# headers. headers is used here and supports urllib. msg is
# provided as a backwards compatibility layer for http
# clients.
self.headers = self.msg = None
# from the Status-Line of the response
self.version = _UNKNOWN # HTTP-Version
self.status = _UNKNOWN # Status-Code
self.reason = _UNKNOWN # Reason-Phrase
self.chunked = _UNKNOWN # is "chunked" being used?
self.chunk_left = _UNKNOWN # bytes left to read in current chunk
self.length = _UNKNOWN # number of bytes left in response
self.will_close = _UNKNOWN # conn will close at end of response
def _read_status(self):
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
if len(line) > _MAXLINE:
raise LineTooLong("status line")
if self.debuglevel > 0:
print("reply:", repr(line))
if not line:
# Presumably, the server closed the connection before
# sending a valid response.
raise RemoteDisconnected("Remote end closed connection without"
" response")
try:
version, status, reason = line.split(None, 2)
except ValueError:
try:
version, status = line.split(None, 1)
reason = ""
except ValueError:
# empty version will cause next test to fail.
version = ""
if not version.startswith("HTTP/"):
self._close_conn()
raise BadStatusLine(line)
# The status code is a three-digit number
try:
status = int(status)
if status < 100 or status > 999:
raise BadStatusLine(line)
except ValueError:
raise BadStatusLine(line)
return version, status, reason
def begin(self):
if self.headers is not None:
# we've already started reading the response
return
# read until we get a non-100 response
while True:
version, status, reason = self._read_status()
if status != CONTINUE:
break
# skip the header from the 100 response
skipped_headers = _read_headers(self.fp)
if self.debuglevel > 0:
print("headers:", skipped_headers)
del skipped_headers
self.code = self.status = status
self.reason = reason.strip()
if version in ("HTTP/1.0", "HTTP/0.9"):
# Some servers might still return "0.9", treat it as 1.0 anyway
self.version = 10
elif version.startswith("HTTP/1."):
self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1
else:
raise UnknownProtocol(version)
self.headers = self.msg = parse_headers(self.fp)
if self.debuglevel > 0:
for hdr, val in self.headers.items():
print("header:", hdr + ":", val)
# are we using the chunked-style of transfer encoding?
tr_enc = self.headers.get("transfer-encoding")
if tr_enc and tr_enc.lower() == "chunked":
self.chunked = True
self.chunk_left = None
else:
self.chunked = False
# will the connection close at the end of the response?
self.will_close = self._check_close()
# do we have a Content-Length?
# NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked"
self.length = None
length = self.headers.get("content-length")
if length and not self.chunked:
try:
self.length = int(length)
except ValueError:
self.length = None
else:
if self.length < 0: # ignore nonsensical negative lengths
self.length = None
else:
self.length = None
# does the body have a fixed length? (of zero)
if (status == NO_CONTENT or status == NOT_MODIFIED or
100 <= status < 200 or # 1xx codes
self._method == "HEAD"):
self.length = 0
# if the connection remains open, and we aren't using chunked, and
# a content-length was not provided, then assume that the connection
# WILL close.
if (not self.will_close and
not self.chunked and
self.length is None):
self.will_close = True
def _check_close(self):
conn = self.headers.get("connection")
if self.version == 11:
# An HTTP/1.1 proxy is assumed to stay open unless
# explicitly closed.
if conn and "close" in conn.lower():
return True
return False
# Some HTTP/1.0 implementations have support for persistent
# connections, using rules different than HTTP/1.1.
# For older HTTP, Keep-Alive indicates persistent connection.
if self.headers.get("keep-alive"):
return False
# At least Akamai returns a "Connection: Keep-Alive" header,
# which was supposed to be sent by the client.
if conn and "keep-alive" in conn.lower():
return False
# Proxy-Connection is a netscape hack.
pconn = self.headers.get("proxy-connection")
if pconn and "keep-alive" in pconn.lower():
return False
# otherwise, assume it will close
return True
def _close_conn(self):
fp = self.fp
self.fp = None
fp.close()
def close(self):
try:
super().close() # set "closed" flag
finally:
if self.fp:
self._close_conn()
# These implementations are for the benefit of io.BufferedReader.
# XXX This class should probably be revised to act more like
# the "raw stream" that BufferedReader expects.
def flush(self):
super().flush()
if self.fp:
self.fp.flush()
def readable(self):
"""Always returns True"""
return True
# End of "raw stream" methods
def isclosed(self):
"""True if the connection is closed."""
# NOTE: it is possible that we will not ever call self.close(). This
# case occurs when will_close is TRUE, length is None, and we
# read up to the last byte, but NOT past it.
#
# IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be
# called, meaning self.isclosed() is meaningful.
return self.fp is None
def read(self, amt=None):
if self.fp is None:
return b""
if self._method == "HEAD":
self._close_conn()
return b""
if amt is not None:
# Amount is given, implement using readinto
b = bytearray(amt)
n = self.readinto(b)
return memoryview(b)[:n].tobytes()
else:
# Amount is not given (unbounded read) so we must check self.length
# and self.chunked
if self.chunked:
return self._readall_chunked()
if self.length is None:
s = self.fp.read()
else:
try:
s = self._safe_read(self.length)
except IncompleteRead:
self._close_conn()
raise
self.length = 0
self._close_conn() # we read everything
return s
def readinto(self, b):
"""Read up to len(b) bytes into bytearray b and return the number
of bytes read.
"""
if self.fp is None:
return 0
if self._method == "HEAD":
self._close_conn()
return 0
if self.chunked:
return self._readinto_chunked(b)
if self.length is not None:
if len(b) > self.length:
# clip the read to the "end of response"
b = memoryview(b)[0:self.length]
# we do not use _safe_read() here because this may be a .will_close
# connection, and the user is reading more bytes than will be provided
# (for example, reading in 1k chunks)
n = self.fp.readinto(b)
if not n and b:
# Ideally, we would raise IncompleteRead if the content-length
# wasn't satisfied, but it might break compatibility.
self._close_conn()
elif self.length is not None:
self.length -= n
if not self.length:
self._close_conn()
return n
def _read_next_chunk_size(self):
# Read the next chunk size from the file
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("chunk size")
i = line.find(b";")
if i >= 0:
line = line[:i] # strip chunk-extensions
try:
return int(line, 16)
except ValueError:
# close the connection as protocol synchronisation is
# probably lost
self._close_conn()
raise
def _read_and_discard_trailer(self):
# read and discard trailer up to the CRLF terminator
### note: we shouldn't have any trailers!
while True:
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("trailer line")
if not line:
# a vanishingly small number of sites EOF without
# sending the trailer
break
if line in (b'\r\n', b'\n', b''):
break
def _get_chunk_left(self):
# return self.chunk_left, reading a new chunk if necessary.
# chunk_left == 0: at the end of the current chunk, need to close it
# chunk_left == None: No current chunk, should read next.
# This function returns non-zero or None if the last chunk has
# been read.
chunk_left = self.chunk_left
if not chunk_left: # Can be 0 or None
if chunk_left is not None:
# We are at the end of chunk, discard chunk end
self._safe_read(2) # toss the CRLF at the end of the chunk
try:
chunk_left = self._read_next_chunk_size()
except ValueError:
raise IncompleteRead(b'')
if chunk_left == 0:
# last chunk: 1*("0") [ chunk-extension ] CRLF
self._read_and_discard_trailer()
# we read everything; close the "file"
self._close_conn()
chunk_left = None
self.chunk_left = chunk_left
return chunk_left
def _readall_chunked(self):
assert self.chunked != _UNKNOWN
value = []
try:
while True:
chunk_left = self._get_chunk_left()
if chunk_left is None:
break
value.append(self._safe_read(chunk_left))
self.chunk_left = 0
return b''.join(value)
except IncompleteRead:
raise IncompleteRead(b''.join(value))
def _readinto_chunked(self, b):
assert self.chunked != _UNKNOWN
total_bytes = 0
mvb = memoryview(b)
try:
while True:
chunk_left = self._get_chunk_left()
if chunk_left is None:
return total_bytes
if len(mvb) <= chunk_left:
n = self._safe_readinto(mvb)
self.chunk_left = chunk_left - n
return total_bytes + n
temp_mvb = mvb[:chunk_left]
n = self._safe_readinto(temp_mvb)
mvb = mvb[n:]
total_bytes += n
self.chunk_left = 0
except IncompleteRead:
raise IncompleteRead(bytes(b[0:total_bytes]))
def _safe_read(self, amt):
"""Read the number of bytes requested.
This function should be used when <amt> bytes "should" be present for
reading. If the bytes are truly not available (due to EOF), then the
IncompleteRead exception can be used to detect the problem.
"""
data = self.fp.read(amt)
if len(data) < amt:
raise IncompleteRead(data, amt-len(data))
return data
def _safe_readinto(self, b):
"""Same as _safe_read, but for reading into a buffer."""
amt = len(b)
n = self.fp.readinto(b)
if n < amt:
raise IncompleteRead(bytes(b[:n]), amt-n)
return n
def read1(self, n=-1):
"""Read with at most one underlying system call. If at least one
byte is buffered, return that instead.
"""
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
return self._read1_chunked(n)
if self.length is not None and (n < 0 or n > self.length):
n = self.length
result = self.fp.read1(n)
if not result and n:
self._close_conn()
elif self.length is not None:
self.length -= len(result)
return result
def peek(self, n=-1):
# Having this enables IOBase.readline() to read more than one
# byte at a time
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
return self._peek_chunked(n)
return self.fp.peek(n)
def readline(self, limit=-1):
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
# Fallback to IOBase readline which uses peek() and read()
return super().readline(limit)
if self.length is not None and (limit < 0 or limit > self.length):
limit = self.length
result = self.fp.readline(limit)
if not result and limit:
self._close_conn()
elif self.length is not None:
self.length -= len(result)
return result
def _read1_chunked(self, n):
# Strictly speaking, _get_chunk_left() may cause more than one read,
# but that is ok, since that is to satisfy the chunked protocol.
chunk_left = self._get_chunk_left()
if chunk_left is None or n == 0:
return b''
if not (0 <= n <= chunk_left):
n = chunk_left # if n is negative or larger than chunk_left
read = self.fp.read1(n)
self.chunk_left -= len(read)
if not read:
raise IncompleteRead(b"")
return read
def _peek_chunked(self, n):
# Strictly speaking, _get_chunk_left() may cause more than one read,
# but that is ok, since that is to satisfy the chunked protocol.
try:
chunk_left = self._get_chunk_left()
except IncompleteRead:
return b'' # peek doesn't worry about protocol
if chunk_left is None:
return b'' # eof
# peek is allowed to return more than requested. Just request the
# entire chunk, and truncate what we get.
return self.fp.peek(chunk_left)[:chunk_left]
def fileno(self):
return self.fp.fileno()
def getheader(self, name, default=None):
'''Returns the value of the header matching *name*.
If there are multiple matching headers, the values are
combined into a single string separated by commas and spaces.
If no matching header is found, returns *default* or None if
the *default* is not specified.
If the headers are unknown, raises http.client.ResponseNotReady.
'''
if self.headers is None:
raise ResponseNotReady()
headers = self.headers.get_all(name) or default
if isinstance(headers, str) or not hasattr(headers, '__iter__'):
return headers
else:
return ', '.join(headers)
def getheaders(self):
"""Return list of (header, value) tuples."""
if self.headers is None:
raise ResponseNotReady()
return list(self.headers.items())
# We override IOBase.__iter__ so that it doesn't check for closed-ness
def __iter__(self):
return self
# For compatibility with old-style urllib responses.
def info(self):
'''Returns an instance of the class mimetools.Message containing
meta-information associated with the URL.
When the method is HTTP, these headers are those returned by
the server at the head of the retrieved HTML page (including
Content-Length and Content-Type).
When the method is FTP, a Content-Length header will be
present if (as is now usual) the server passed back a file
length in response to the FTP retrieval request. A
Content-Type header will be present if the MIME type can be
guessed.
When the method is local-file, returned headers will include
a Date representing the file's last-modified time, a
Content-Length giving file size, and a Content-Type
containing a guess at the file's type. See also the
description of the mimetools module.
'''
return self.headers
def geturl(self):
'''Return the real URL of the page.
In some cases, the HTTP server redirects a client to another
URL. The urlopen() function handles this transparently, but in
some cases the caller needs to know which URL the client was
redirected to. The geturl() method can be used to get at this
redirected URL.
'''
return self.url
def getcode(self):
'''Return the HTTP status code that was sent with the response,
or None if the URL is not an HTTP URL.
'''
return self.status
class HTTPConnection:
_http_vsn = 11
_http_vsn_str = 'HTTP/1.1'
response_class = HTTPResponse
default_port = HTTP_PORT
auto_open = 1
debuglevel = 0
@staticmethod
def _is_textIO(stream):
"""Test whether a file-like object is a text or a binary stream.
"""
return isinstance(stream, io.TextIOBase)
@staticmethod
def _get_content_length(body, method):
"""Get the content-length based on the body.
If the body is None, we set Content-Length: 0 for methods that expect
a body (RFC 7230, Section 3.3.2). We also set the Content-Length for
any method if the body is a str or bytes-like object and not a file.
"""
if body is None:
# do an explicit check for not None here to distinguish
# between unset and set but empty
if method.upper() in _METHODS_EXPECTING_BODY:
return 0
else:
return None
if hasattr(body, 'read'):
# file-like object.
return None
try:
# does it implement the buffer protocol (bytes, bytearray, array)?
mv = memoryview(body)
return mv.nbytes
except TypeError:
pass
if isinstance(body, str):
return len(body)
return None
def __init__(self, host, port=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
source_address=None, blocksize=8192):
self.timeout = timeout
self.source_address = source_address
self.blocksize = blocksize
self.sock = None
self._buffer = []
self.__response = None
self.__state = _CS_IDLE
self._method = None
self._tunnel_host = None
self._tunnel_port = None
self._tunnel_headers = {}
(self.host, self.port) = self._get_hostport(host, port)
self._validate_host(self.host)
# This is stored as an instance variable to allow unit
# tests to replace it with a suitable mockup
self._create_connection = socket.create_connection
def set_tunnel(self, host, port=None, headers=None):
"""Set up host and port for HTTP CONNECT tunnelling.
In a connection that uses HTTP CONNECT tunneling, the host passed to the
constructor is used as a proxy server that relays all communication to
the endpoint passed to `set_tunnel`. This done by sending an HTTP
CONNECT request to the proxy server when the connection is established.
This method must be called before the HTTP connection has been
established.
The headers argument should be a mapping of extra HTTP headers to send
with the CONNECT request.
"""
if self.sock:
raise RuntimeError("Can't set up tunnel for established connection")
self._tunnel_host, self._tunnel_port = self._get_hostport(host, port)
if headers:
self._tunnel_headers = headers
else:
self._tunnel_headers.clear()
def _get_hostport(self, host, port):
if port is None:
i = host.rfind(':')
j = host.rfind(']') # ipv6 addresses have [...]
if i > j:
try:
port = int(host[i+1:])
except ValueError:
if host[i+1:] == "": # http://foo.com:/ == http://foo.com/
port = self.default_port
else:
raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
host = host[:i]
else:
port = self.default_port
if host and host[0] == '[' and host[-1] == ']':
host = host[1:-1]
return (host, port)
def set_debuglevel(self, level):
self.debuglevel = level
def _tunnel(self):
connect_str = "CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host,
self._tunnel_port)
connect_bytes = connect_str.encode("ascii")
self.send(connect_bytes)
for header, value in self._tunnel_headers.items():
header_str = "%s: %s\r\n" % (header, value)
header_bytes = header_str.encode("latin-1")
self.send(header_bytes)
self.send(b'\r\n')
response = self.response_class(self.sock, method=self._method)
(version, code, message) = response._read_status()
if code != http.HTTPStatus.OK:
self.close()
raise OSError("Tunnel connection failed: %d %s" % (code,
message.strip()))
while True:
line = response.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
if not line:
# for sites which EOF without sending a trailer
break
if line in (b'\r\n', b'\n', b''):
break
if self.debuglevel > 0:
print('header:', line.decode())
def connect(self):
"""Connect to the host and port specified in __init__."""
self.sock = self._create_connection(
(self.host,self.port), self.timeout, self.source_address)
self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
if self._tunnel_host:
self._tunnel()
def close(self):
"""Close the connection to the HTTP server."""
self.__state = _CS_IDLE
try:
sock = self.sock
if sock:
self.sock = None
sock.close() # close it manually... there may be other refs
finally:
response = self.__response
if response:
self.__response = None
response.close()
def send(self, data):
"""Send `data' to the server.
``data`` can be a string object, a bytes object, an array object, a
file-like object that supports a .read() method, or an iterable object.
"""
if self.sock is None:
if self.auto_open:
self.connect()
else:
raise NotConnected()
if self.debuglevel > 0:
print("send:", repr(data))
if hasattr(data, "read") :
if self.debuglevel > 0:
print("sendIng a read()able")
encode = self._is_textIO(data)
if encode and self.debuglevel > 0:
print("encoding file using iso-8859-1")
while 1:
datablock = data.read(self.blocksize)
if not datablock:
break
if encode:
datablock = datablock.encode("iso-8859-1")
self.sock.sendall(datablock)
return
try:
self.sock.sendall(data)
except TypeError:
if isinstance(data, collections.abc.Iterable):
for d in data:
self.sock.sendall(d)
else:
raise TypeError("data should be a bytes-like object "
"or an iterable, got %r" % type(data))
def _output(self, s):
"""Add a line of output to the current request buffer.
Assumes that the line does *not* end with \\r\\n.
"""
self._buffer.append(s)
def _read_readable(self, readable):
if self.debuglevel > 0:
print("sendIng a read()able")
encode = self._is_textIO(readable)
if encode and self.debuglevel > 0:
print("encoding file using iso-8859-1")
while True:
datablock = readable.read(self.blocksize)
if not datablock:
break
if encode:
datablock = datablock.encode("iso-8859-1")
yield datablock
def _send_output(self, message_body=None, encode_chunked=False):
"""Send the currently buffered request and clear the buffer.
Appends an extra \\r\\n to the buffer.
A message_body may be specified, to be appended to the request.
"""
self._buffer.extend((b"", b""))
msg = b"\r\n".join(self._buffer)
del self._buffer[:]
self.send(msg)
if message_body is not None:
# create a consistent interface to message_body
if hasattr(message_body, 'read'):
# Let file-like take precedence over byte-like. This
# is needed to allow the current position of mmap'ed
# files to be taken into account.
chunks = self._read_readable(message_body)
else:
try:
# this is solely to check to see if message_body
# implements the buffer API. it /would/ be easier
# to capture if PyObject_CheckBuffer was exposed
# to Python.
memoryview(message_body)
except TypeError:
try:
chunks = iter(message_body)
except TypeError:
raise TypeError("message_body should be a bytes-like "
"object or an iterable, got %r"
% type(message_body))
else:
# the object implements the buffer interface and
# can be passed directly into socket methods
chunks = (message_body,)
for chunk in chunks:
if not chunk:
if self.debuglevel > 0:
print('Zero length chunk ignored')
continue
if encode_chunked and self._http_vsn == 11:
# chunked encoding
chunk = f'{len(chunk):X}\r\n'.encode('ascii') + chunk \
+ b'\r\n'
self.send(chunk)
if encode_chunked and self._http_vsn == 11:
# end chunked transfer
self.send(b'0\r\n\r\n')
def putrequest(self, method, url, skip_host=False,
skip_accept_encoding=False):
"""Send a request to the server.
`method' specifies an HTTP request method, e.g. 'GET'.
`url' specifies the object being requested, e.g. '/index.html'.
`skip_host' if True does not add automatically a 'Host:' header
`skip_accept_encoding' if True does not add automatically an
'Accept-Encoding:' header
"""
# if a prior response has been completed, then forget about it.
if self.__response and self.__response.isclosed():
self.__response = None
# in certain cases, we cannot issue another request on this connection.
# this occurs when:
# 1) we are in the process of sending a request. (_CS_REQ_STARTED)
# 2) a response to a previous request has signalled that it is going
# to close the connection upon completion.
# 3) the headers for the previous response have not been read, thus
# we cannot determine whether point (2) is true. (_CS_REQ_SENT)
#
# if there is no prior response, then we can request at will.
#
# if point (2) is true, then we will have passed the socket to the
# response (effectively meaning, "there is no prior response"), and
# will open a new one when a new request is made.
#
# Note: if a prior response exists, then we *can* start a new request.
# We are not allowed to begin fetching the response to this new
# request, however, until that prior response is complete.
#
if self.__state == _CS_IDLE:
self.__state = _CS_REQ_STARTED
else:
raise CannotSendRequest(self.__state)
self._validate_method(method)
# Save the method for use later in the response phase
self._method = method
url = url or '/'
self._validate_path(url)
request = '%s %s %s' % (method, url, self._http_vsn_str)
self._output(self._encode_request(request))
if self._http_vsn == 11:
# Issue some standard headers for better HTTP/1.1 compliance
if not skip_host:
# this header is issued *only* for HTTP/1.1
# connections. more specifically, this means it is
# only issued when the client uses the new
# HTTPConnection() class. backwards-compat clients
# will be using HTTP/1.0 and those clients may be
# issuing this header themselves. we should NOT issue
# it twice; some web servers (such as Apache) barf
# when they see two Host: headers
# If we need a non-standard port,include it in the
# header. If the request is going through a proxy,
# but the host of the actual URL, not the host of the
# proxy.
netloc = ''
if url.startswith('http'):
nil, netloc, nil, nil, nil = urlsplit(url)
if netloc:
try:
netloc_enc = netloc.encode("ascii")
except UnicodeEncodeError:
netloc_enc = netloc.encode("idna")
self.putheader('Host', netloc_enc)
else:
if self._tunnel_host:
host = self._tunnel_host
port = self._tunnel_port
else:
host = self.host
port = self.port
try:
host_enc = host.encode("ascii")
except UnicodeEncodeError:
host_enc = host.encode("idna")
# As per RFC 273, IPv6 address should be wrapped with []
# when used as Host header
if host.find(':') >= 0:
host_enc = b'[' + host_enc + b']'
if port == self.default_port:
self.putheader('Host', host_enc)
else:
host_enc = host_enc.decode("ascii")
self.putheader('Host', "%s:%s" % (host_enc, port))
# note: we are assuming that clients will not attempt to set these
# headers since *this* library must deal with the
# consequences. this also means that when the supporting
# libraries are updated to recognize other forms, then this
# code should be changed (removed or updated).
# we only want a Content-Encoding of "identity" since we don't
# support encodings such as x-gzip or x-deflate.
if not skip_accept_encoding:
self.putheader('Accept-Encoding', 'identity')
# we can accept "chunked" Transfer-Encodings, but no others
# NOTE: no TE header implies *only* "chunked"
#self.putheader('TE', 'chunked')
# if TE is supplied in the header, then it must appear in a
# Connection header.
#self.putheader('Connection', 'TE')
else:
# For HTTP/1.0, the server will assume "not chunked"
pass
def _encode_request(self, request):
# ASCII also helps prevent CVE-2019-9740.
return request.encode('ascii')
def _validate_method(self, method):
"""Validate a method name for putrequest."""
# prevent http header injection
match = _contains_disallowed_method_pchar_re.search(method)
if match:
raise ValueError(
f"method can't contain control characters. {method!r} "
f"(found at least {match.group()!r})")
def _validate_path(self, url):
"""Validate a url for putrequest."""
# Prevent CVE-2019-9740.
match = _contains_disallowed_url_pchar_re.search(url)
if match:
raise InvalidURL(f"URL can't contain control characters. {url!r} "
f"(found at least {match.group()!r})")
def _validate_host(self, host):
"""Validate a host so it doesn't contain control characters."""
# Prevent CVE-2019-18348.
match = _contains_disallowed_url_pchar_re.search(host)
if match:
raise InvalidURL(f"URL can't contain control characters. {host!r} "
f"(found at least {match.group()!r})")
def putheader(self, header, *values):
"""Send a request header line to the server.
For example: h.putheader('Accept', 'text/html')
"""
if self.__state != _CS_REQ_STARTED:
raise CannotSendHeader()
if hasattr(header, 'encode'):
header = header.encode('ascii')
if not _is_legal_header_name(header):
raise ValueError('Invalid header name %r' % (header,))
values = list(values)
for i, one_value in enumerate(values):
if hasattr(one_value, 'encode'):
values[i] = one_value.encode('latin-1')
elif isinstance(one_value, int):
values[i] = str(one_value).encode('ascii')
if _is_illegal_header_value(values[i]):
raise ValueError('Invalid header value %r' % (values[i],))
value = b'\r\n\t'.join(values)
header = header + b': ' + value
self._output(header)
def endheaders(self, message_body=None, *, encode_chunked=False):
"""Indicate that the last header line has been sent to the server.
This method sends the request to the server. The optional message_body
argument can be used to pass a message body associated with the
request.
"""
if self.__state == _CS_REQ_STARTED:
self.__state = _CS_REQ_SENT
else:
raise CannotSendHeader()
self._send_output(message_body, encode_chunked=encode_chunked)
def request(self, method, url, body=None, headers={}, *,
encode_chunked=False):
"""Send a complete request to the server."""
self._send_request(method, url, body, headers, encode_chunked)
def _send_request(self, method, url, body, headers, encode_chunked):
# Honor explicitly requested Host: and Accept-Encoding: headers.
header_names = frozenset(k.lower() for k in headers)
skips = {}
if 'host' in header_names:
skips['skip_host'] = 1
if 'accept-encoding' in header_names:
skips['skip_accept_encoding'] = 1
self.putrequest(method, url, **skips)
# chunked encoding will happen if HTTP/1.1 is used and either
# the caller passes encode_chunked=True or the following
# conditions hold:
# 1. content-length has not been explicitly set
# 2. the body is a file or iterable, but not a str or bytes-like
# 3. Transfer-Encoding has NOT been explicitly set by the caller
if 'content-length' not in header_names:
# only chunk body if not explicitly set for backwards
# compatibility, assuming the client code is already handling the
# chunking
if 'transfer-encoding' not in header_names:
# if content-length cannot be automatically determined, fall
# back to chunked encoding
encode_chunked = False
content_length = self._get_content_length(body, method)
if content_length is None:
if body is not None:
if self.debuglevel > 0:
print('Unable to determine size of %r' % body)
encode_chunked = True
self.putheader('Transfer-Encoding', 'chunked')
else:
self.putheader('Content-Length', str(content_length))
else:
encode_chunked = False
for hdr, value in headers.items():
self.putheader(hdr, value)
if isinstance(body, str):
# RFC 2616 Section 3.7.1 says that text default has a
# default charset of iso-8859-1.
body = _encode(body, 'body')
self.endheaders(body, encode_chunked=encode_chunked)
def getresponse(self):
"""Get the response from the server.
If the HTTPConnection is in the correct state, returns an
instance of HTTPResponse or of whatever object is returned by
the response_class variable.
If a request has not been sent or if a previous response has
not be handled, ResponseNotReady is raised. If the HTTP
response indicates that the connection should be closed, then
it will be closed before the response is returned. When the
connection is closed, the underlying socket is closed.
"""
# if a prior response has been completed, then forget about it.
if self.__response and self.__response.isclosed():
self.__response = None
# if a prior response exists, then it must be completed (otherwise, we
# cannot read this response's header to determine the connection-close
# behavior)
#
# note: if a prior response existed, but was connection-close, then the
# socket and response were made independent of this HTTPConnection
# object since a new request requires that we open a whole new
# connection
#
# this means the prior response had one of two states:
# 1) will_close: this connection was reset and the prior socket and
# response operate independently
# 2) persistent: the response was retained and we await its
# isclosed() status to become true.
#
if self.__state != _CS_REQ_SENT or self.__response:
raise ResponseNotReady(self.__state)
if self.debuglevel > 0:
response = self.response_class(self.sock, self.debuglevel,
method=self._method)
else:
response = self.response_class(self.sock, method=self._method)
try:
try:
response.begin()
except ConnectionError:
self.close()
raise
assert response.will_close != _UNKNOWN
self.__state = _CS_IDLE
if response.will_close:
# this effectively passes the connection to the response
self.close()
else:
# remember this, so we can tell when it is complete
self.__response = response
return response
except:
response.close()
raise
try:
import ssl
except ImportError:
pass
else:
class HTTPSConnection(HTTPConnection):
"This class allows communication via SSL."
default_port = HTTPS_PORT
# XXX Should key_file and cert_file be deprecated in favour of context?
def __init__(self, host, port=None, key_file=None, cert_file=None,
timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
source_address=None, *, context=None,
check_hostname=None, blocksize=8192):
super(HTTPSConnection, self).__init__(host, port, timeout,
source_address,
blocksize=blocksize)
if (key_file is not None or cert_file is not None or
check_hostname is not None):
import warnings
warnings.warn("key_file, cert_file and check_hostname are "
"deprecated, use a custom context instead.",
DeprecationWarning, 2)
self.key_file = key_file
self.cert_file = cert_file
if context is None:
context = ssl._create_default_https_context()
# enable PHA for TLS 1.3 connections if available
if context.post_handshake_auth is not None:
context.post_handshake_auth = True
will_verify = context.verify_mode != ssl.CERT_NONE
if check_hostname is None:
check_hostname = context.check_hostname
if check_hostname and not will_verify:
raise ValueError("check_hostname needs a SSL context with "
"either CERT_OPTIONAL or CERT_REQUIRED")
if key_file or cert_file:
context.load_cert_chain(cert_file, key_file)
# cert and key file means the user wants to authenticate.
# enable TLS 1.3 PHA implicitly even for custom contexts.
if context.post_handshake_auth is not None:
context.post_handshake_auth = True
self._context = context
if check_hostname is not None:
self._context.check_hostname = check_hostname
def connect(self):
"Connect to a host on a given (SSL) port."
super().connect()
if self._tunnel_host:
server_hostname = self._tunnel_host
else:
server_hostname = self.host
self.sock = self._context.wrap_socket(self.sock,
server_hostname=server_hostname)
__all__.append("HTTPSConnection")
class HTTPException(Exception):
# Subclasses that define an __init__ must call Exception.__init__
# or define self.args. Otherwise, str() will fail.
pass
class NotConnected(HTTPException):
pass
class InvalidURL(HTTPException):
pass
class UnknownProtocol(HTTPException):
def __init__(self, version):
self.args = version,
self.version = version
class UnknownTransferEncoding(HTTPException):
pass
class UnimplementedFileMode(HTTPException):
pass
class IncompleteRead(HTTPException):
def __init__(self, partial, expected=None):
self.args = partial,
self.partial = partial
self.expected = expected
def __repr__(self):
if self.expected is not None:
e = ', %i more expected' % self.expected
else:
e = ''
return '%s(%i bytes read%s)' % (self.__class__.__name__,
len(self.partial), e)
__str__ = object.__str__
class ImproperConnectionState(HTTPException):
pass
class CannotSendRequest(ImproperConnectionState):
pass
class CannotSendHeader(ImproperConnectionState):
pass
class ResponseNotReady(ImproperConnectionState):
pass
class BadStatusLine(HTTPException):
def __init__(self, line):
if not line:
line = repr(line)
self.args = line,
self.line = line
class LineTooLong(HTTPException):
def __init__(self, line_type):
HTTPException.__init__(self, "got more than %d bytes when reading %s"
% (_MAXLINE, line_type))
class RemoteDisconnected(ConnectionResetError, BadStatusLine):
def __init__(self, *pos, **kw):
BadStatusLine.__init__(self, "")
ConnectionResetError.__init__(self, *pos, **kw)
# for backwards compatibility
error = HTTPException
cookies.py 0000644 00000047674 15032716522 0006577 0 ustar 00 ####
# Copyright 2000 by Timothy O'Malley <timo@alum.mit.edu>
#
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software
# and its documentation for any purpose and without fee is hereby
# granted, provided that the above copyright notice appear in all
# copies and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Timothy O'Malley not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# Timothy O'Malley DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS
# SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
# AND FITNESS, IN NO EVENT SHALL Timothy O'Malley BE LIABLE FOR
# ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
#
####
#
# Id: Cookie.py,v 2.29 2000/08/23 05:28:49 timo Exp
# by Timothy O'Malley <timo@alum.mit.edu>
#
# Cookie.py is a Python module for the handling of HTTP
# cookies as a Python dictionary. See RFC 2109 for more
# information on cookies.
#
# The original idea to treat Cookies as a dictionary came from
# Dave Mitchell (davem@magnet.com) in 1995, when he released the
# first version of nscookie.py.
#
####
r"""
Here's a sample session to show how to use this module.
At the moment, this is the only documentation.
The Basics
----------
Importing is easy...
>>> from http import cookies
Most of the time you start by creating a cookie.
>>> C = cookies.SimpleCookie()
Once you've created your Cookie, you can add values just as if it were
a dictionary.
>>> C = cookies.SimpleCookie()
>>> C["fig"] = "newton"
>>> C["sugar"] = "wafer"
>>> C.output()
'Set-Cookie: fig=newton\r\nSet-Cookie: sugar=wafer'
Notice that the printable representation of a Cookie is the
appropriate format for a Set-Cookie: header. This is the
default behavior. You can change the header and printed
attributes by using the .output() function
>>> C = cookies.SimpleCookie()
>>> C["rocky"] = "road"
>>> C["rocky"]["path"] = "/cookie"
>>> print(C.output(header="Cookie:"))
Cookie: rocky=road; Path=/cookie
>>> print(C.output(attrs=[], header="Cookie:"))
Cookie: rocky=road
The load() method of a Cookie extracts cookies from a string. In a
CGI script, you would use this method to extract the cookies from the
HTTP_COOKIE environment variable.
>>> C = cookies.SimpleCookie()
>>> C.load("chips=ahoy; vienna=finger")
>>> C.output()
'Set-Cookie: chips=ahoy\r\nSet-Cookie: vienna=finger'
The load() method is darn-tootin smart about identifying cookies
within a string. Escaped quotation marks, nested semicolons, and other
such trickeries do not confuse it.
>>> C = cookies.SimpleCookie()
>>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=\\012;";')
>>> print(C)
Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=\012;"
Each element of the Cookie also supports all of the RFC 2109
Cookie attributes. Here's an example which sets the Path
attribute.
>>> C = cookies.SimpleCookie()
>>> C["oreo"] = "doublestuff"
>>> C["oreo"]["path"] = "/"
>>> print(C)
Set-Cookie: oreo=doublestuff; Path=/
Each dictionary element has a 'value' attribute, which gives you
back the value associated with the key.
>>> C = cookies.SimpleCookie()
>>> C["twix"] = "none for you"
>>> C["twix"].value
'none for you'
The SimpleCookie expects that all values should be standard strings.
Just to be sure, SimpleCookie invokes the str() builtin to convert
the value to a string, when the values are set dictionary-style.
>>> C = cookies.SimpleCookie()
>>> C["number"] = 7
>>> C["string"] = "seven"
>>> C["number"].value
'7'
>>> C["string"].value
'seven'
>>> C.output()
'Set-Cookie: number=7\r\nSet-Cookie: string=seven'
Finis.
"""
#
# Import our required modules
#
import re
import string
__all__ = ["CookieError", "BaseCookie", "SimpleCookie"]
_nulljoin = ''.join
_semispacejoin = '; '.join
_spacejoin = ' '.join
#
# Define an exception visible to External modules
#
class CookieError(Exception):
pass
# These quoting routines conform to the RFC2109 specification, which in
# turn references the character definitions from RFC2068. They provide
# a two-way quoting algorithm. Any non-text character is translated
# into a 4 character sequence: a forward-slash followed by the
# three-digit octal equivalent of the character. Any '\' or '"' is
# quoted with a preceding '\' slash.
# Because of the way browsers really handle cookies (as opposed to what
# the RFC says) we also encode "," and ";".
#
# These are taken from RFC2068 and RFC2109.
# _LegalChars is the list of chars which don't require "'s
# _Translator hash-table for fast quoting
#
_LegalChars = string.ascii_letters + string.digits + "!#$%&'*+-.^_`|~:"
_UnescapedChars = _LegalChars + ' ()/<=>?@[]{}'
_Translator = {n: '\\%03o' % n
for n in set(range(256)) - set(map(ord, _UnescapedChars))}
_Translator.update({
ord('"'): '\\"',
ord('\\'): '\\\\',
})
_is_legal_key = re.compile('[%s]+' % re.escape(_LegalChars)).fullmatch
def _quote(str):
r"""Quote a string for use in a cookie header.
If the string does not need to be double-quoted, then just return the
string. Otherwise, surround the string in doublequotes and quote
(with a \) special characters.
"""
if str is None or _is_legal_key(str):
return str
else:
return '"' + str.translate(_Translator) + '"'
_OctalPatt = re.compile(r"\\[0-3][0-7][0-7]")
_QuotePatt = re.compile(r"[\\].")
def _unquote(str):
# If there aren't any doublequotes,
# then there can't be any special characters. See RFC 2109.
if str is None or len(str) < 2:
return str
if str[0] != '"' or str[-1] != '"':
return str
# We have to assume that we must decode this string.
# Down to work.
# Remove the "s
str = str[1:-1]
# Check for special sequences. Examples:
# \012 --> \n
# \" --> "
#
i = 0
n = len(str)
res = []
while 0 <= i < n:
o_match = _OctalPatt.search(str, i)
q_match = _QuotePatt.search(str, i)
if not o_match and not q_match: # Neither matched
res.append(str[i:])
break
# else:
j = k = -1
if o_match:
j = o_match.start(0)
if q_match:
k = q_match.start(0)
if q_match and (not o_match or k < j): # QuotePatt matched
res.append(str[i:k])
res.append(str[k+1])
i = k + 2
else: # OctalPatt matched
res.append(str[i:j])
res.append(chr(int(str[j+1:j+4], 8)))
i = j + 4
return _nulljoin(res)
# The _getdate() routine is used to set the expiration time in the cookie's HTTP
# header. By default, _getdate() returns the current time in the appropriate
# "expires" format for a Set-Cookie header. The one optional argument is an
# offset from now, in seconds. For example, an offset of -3600 means "one hour
# ago". The offset may be a floating point number.
#
_weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
_monthname = [None,
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
def _getdate(future=0, weekdayname=_weekdayname, monthname=_monthname):
from time import gmtime, time
now = time()
year, month, day, hh, mm, ss, wd, y, z = gmtime(now + future)
return "%s, %02d %3s %4d %02d:%02d:%02d GMT" % \
(weekdayname[wd], day, monthname[month], year, hh, mm, ss)
class Morsel(dict):
"""A class to hold ONE (key, value) pair.
In a cookie, each such pair may have several attributes, so this class is
used to keep the attributes associated with the appropriate key,value pair.
This class also includes a coded_value attribute, which is used to hold
the network representation of the value.
"""
# RFC 2109 lists these attributes as reserved:
# path comment domain
# max-age secure version
#
# For historical reasons, these attributes are also reserved:
# expires
#
# This is an extension from Microsoft:
# httponly
#
# This dictionary provides a mapping from the lowercase
# variant on the left to the appropriate traditional
# formatting on the right.
_reserved = {
"expires" : "expires",
"path" : "Path",
"comment" : "Comment",
"domain" : "Domain",
"max-age" : "Max-Age",
"secure" : "Secure",
"httponly" : "HttpOnly",
"version" : "Version",
"samesite" : "SameSite",
}
_flags = {'secure', 'httponly'}
def __init__(self):
# Set defaults
self._key = self._value = self._coded_value = None
# Set default attributes
for key in self._reserved:
dict.__setitem__(self, key, "")
@property
def key(self):
return self._key
@property
def value(self):
return self._value
@property
def coded_value(self):
return self._coded_value
def __setitem__(self, K, V):
K = K.lower()
if not K in self._reserved:
raise CookieError("Invalid attribute %r" % (K,))
dict.__setitem__(self, K, V)
def setdefault(self, key, val=None):
key = key.lower()
if key not in self._reserved:
raise CookieError("Invalid attribute %r" % (key,))
return dict.setdefault(self, key, val)
def __eq__(self, morsel):
if not isinstance(morsel, Morsel):
return NotImplemented
return (dict.__eq__(self, morsel) and
self._value == morsel._value and
self._key == morsel._key and
self._coded_value == morsel._coded_value)
__ne__ = object.__ne__
def copy(self):
morsel = Morsel()
dict.update(morsel, self)
morsel.__dict__.update(self.__dict__)
return morsel
def update(self, values):
data = {}
for key, val in dict(values).items():
key = key.lower()
if key not in self._reserved:
raise CookieError("Invalid attribute %r" % (key,))
data[key] = val
dict.update(self, data)
def isReservedKey(self, K):
return K.lower() in self._reserved
def set(self, key, val, coded_val):
if key.lower() in self._reserved:
raise CookieError('Attempt to set a reserved key %r' % (key,))
if not _is_legal_key(key):
raise CookieError('Illegal key %r' % (key,))
# It's a good key, so save it.
self._key = key
self._value = val
self._coded_value = coded_val
def __getstate__(self):
return {
'key': self._key,
'value': self._value,
'coded_value': self._coded_value,
}
def __setstate__(self, state):
self._key = state['key']
self._value = state['value']
self._coded_value = state['coded_value']
def output(self, attrs=None, header="Set-Cookie:"):
return "%s %s" % (header, self.OutputString(attrs))
__str__ = output
def __repr__(self):
return '<%s: %s>' % (self.__class__.__name__, self.OutputString())
def js_output(self, attrs=None):
# Print javascript
return """
<script type="text/javascript">
<!-- begin hiding
document.cookie = \"%s\";
// end hiding -->
</script>
""" % (self.OutputString(attrs).replace('"', r'\"'))
def OutputString(self, attrs=None):
# Build up our result
#
result = []
append = result.append
# First, the key=value pair
append("%s=%s" % (self.key, self.coded_value))
# Now add any defined attributes
if attrs is None:
attrs = self._reserved
items = sorted(self.items())
for key, value in items:
if value == "":
continue
if key not in attrs:
continue
if key == "expires" and isinstance(value, int):
append("%s=%s" % (self._reserved[key], _getdate(value)))
elif key == "max-age" and isinstance(value, int):
append("%s=%d" % (self._reserved[key], value))
elif key == "comment" and isinstance(value, str):
append("%s=%s" % (self._reserved[key], _quote(value)))
elif key in self._flags:
if value:
append(str(self._reserved[key]))
else:
append("%s=%s" % (self._reserved[key], value))
# Return the result
return _semispacejoin(result)
#
# Pattern for finding cookie
#
# This used to be strict parsing based on the RFC2109 and RFC2068
# specifications. I have since discovered that MSIE 3.0x doesn't
# follow the character rules outlined in those specs. As a
# result, the parsing rules here are less strict.
#
_LegalKeyChars = r"\w\d!#%&'~_`><@,:/\$\*\+\-\.\^\|\)\(\?\}\{\="
_LegalValueChars = _LegalKeyChars + r'\[\]'
_CookiePattern = re.compile(r"""
\s* # Optional whitespace at start of cookie
(?P<key> # Start of group 'key'
[""" + _LegalKeyChars + r"""]+? # Any word of at least one letter
) # End of group 'key'
( # Optional group: there may not be a value.
\s*=\s* # Equal Sign
(?P<val> # Start of group 'val'
"(?:[^\\"]|\\.)*" # Any doublequoted string
| # or
\w{3},\s[\w\d\s-]{9,11}\s[\d:]{8}\sGMT # Special case for "expires" attr
| # or
[""" + _LegalValueChars + r"""]* # Any word or empty string
) # End of group 'val'
)? # End of optional value group
\s* # Any number of spaces.
(\s+|;|$) # Ending either at space, semicolon, or EOS.
""", re.ASCII | re.VERBOSE) # re.ASCII may be removed if safe.
# At long last, here is the cookie class. Using this class is almost just like
# using a dictionary. See this module's docstring for example usage.
#
class BaseCookie(dict):
"""A container class for a set of Morsels."""
def value_decode(self, val):
"""real_value, coded_value = value_decode(STRING)
Called prior to setting a cookie's value from the network
representation. The VALUE is the value read from HTTP
header.
Override this function to modify the behavior of cookies.
"""
return val, val
def value_encode(self, val):
"""real_value, coded_value = value_encode(VALUE)
Called prior to setting a cookie's value from the dictionary
representation. The VALUE is the value being assigned.
Override this function to modify the behavior of cookies.
"""
strval = str(val)
return strval, strval
def __init__(self, input=None):
if input:
self.load(input)
def __set(self, key, real_value, coded_value):
"""Private method for setting a cookie's value"""
M = self.get(key, Morsel())
M.set(key, real_value, coded_value)
dict.__setitem__(self, key, M)
def __setitem__(self, key, value):
"""Dictionary style assignment."""
if isinstance(value, Morsel):
# allow assignment of constructed Morsels (e.g. for pickling)
dict.__setitem__(self, key, value)
else:
rval, cval = self.value_encode(value)
self.__set(key, rval, cval)
def output(self, attrs=None, header="Set-Cookie:", sep="\015\012"):
"""Return a string suitable for HTTP."""
result = []
items = sorted(self.items())
for key, value in items:
result.append(value.output(attrs, header))
return sep.join(result)
__str__ = output
def __repr__(self):
l = []
items = sorted(self.items())
for key, value in items:
l.append('%s=%s' % (key, repr(value.value)))
return '<%s: %s>' % (self.__class__.__name__, _spacejoin(l))
def js_output(self, attrs=None):
"""Return a string suitable for JavaScript."""
result = []
items = sorted(self.items())
for key, value in items:
result.append(value.js_output(attrs))
return _nulljoin(result)
def load(self, rawdata):
"""Load cookies from a string (presumably HTTP_COOKIE) or
from a dictionary. Loading cookies from a dictionary 'd'
is equivalent to calling:
map(Cookie.__setitem__, d.keys(), d.values())
"""
if isinstance(rawdata, str):
self.__parse_string(rawdata)
else:
# self.update() wouldn't call our custom __setitem__
for key, value in rawdata.items():
self[key] = value
return
def __parse_string(self, str, patt=_CookiePattern):
i = 0 # Our starting point
n = len(str) # Length of string
parsed_items = [] # Parsed (type, key, value) triples
morsel_seen = False # A key=value pair was previously encountered
TYPE_ATTRIBUTE = 1
TYPE_KEYVALUE = 2
# We first parse the whole cookie string and reject it if it's
# syntactically invalid (this helps avoid some classes of injection
# attacks).
while 0 <= i < n:
# Start looking for a cookie
match = patt.match(str, i)
if not match:
# No more cookies
break
key, value = match.group("key"), match.group("val")
i = match.end(0)
if key[0] == "$":
if not morsel_seen:
# We ignore attributes which pertain to the cookie
# mechanism as a whole, such as "$Version".
# See RFC 2965. (Does anyone care?)
continue
parsed_items.append((TYPE_ATTRIBUTE, key[1:], value))
elif key.lower() in Morsel._reserved:
if not morsel_seen:
# Invalid cookie string
return
if value is None:
if key.lower() in Morsel._flags:
parsed_items.append((TYPE_ATTRIBUTE, key, True))
else:
# Invalid cookie string
return
else:
parsed_items.append((TYPE_ATTRIBUTE, key, _unquote(value)))
elif value is not None:
parsed_items.append((TYPE_KEYVALUE, key, self.value_decode(value)))
morsel_seen = True
else:
# Invalid cookie string
return
# The cookie string is valid, apply it.
M = None # current morsel
for tp, key, value in parsed_items:
if tp == TYPE_ATTRIBUTE:
assert M is not None
M[key] = value
else:
assert tp == TYPE_KEYVALUE
rval, cval = value
self.__set(key, rval, cval)
M = self[key]
class SimpleCookie(BaseCookie):
"""
SimpleCookie supports strings as cookie values. When setting
the value using the dictionary assignment notation, SimpleCookie
calls the builtin str() to convert the value to a string. Values
received from HTTP are kept as strings.
"""
def value_decode(self, val):
return _unquote(val), val
def value_encode(self, val):
strval = str(val)
return strval, _quote(strval)
__pycache__/client.cpython-38.pyc 0000644 00000104135 15032716522 0012671 0 ustar 00 U
e5d�� � @ sf d Z ddlZddlZddlZddlZddlZddlZddlZ ddl
mZ dddddd d
ddd
ddddddddgZdZ
dZdZdZdZdZe� �ejj� dd� ejj�� D �ZdZdZe�d �jZe�d!�jZe�d"�Z e�d#�Z!d$d%d&hZ"dBd(d)�Z#G d*d+� d+ej$j%�Z&d,d-� Z'e&fd.d/�Z(G d0d� dej)�Z*G d1d� d�Z+zddl,Z,W n e-k
�r` Y nX G d2d3� d3e+�Z.e�/d3� G d4d� de0�Z1G d5d� de1�Z2G d6d� de1�Z3G d7d� de1�Z4G d8d � d e1�Z5G d9d
� d
e1�Z6G d:d� de1�Z7G d;d
� d
e1�Z8G d<d� de8�Z9G d=d� de8�Z:G d>d� de8�Z;G d?d� de1�Z<G d@d� de1�Z=G dAd� de>e<�Z?e1Z@dS )Ca�
HTTP/1.1 client library
<intro stuff goes here>
<other stuff, too>
HTTPConnection goes through a number of "states", which define when a client
may legally make another request or fetch the response for a particular
request. This diagram details these state transitions:
(null)
|
| HTTPConnection()
v
Idle
|
| putrequest()
v
Request-started
|
| ( putheader() )* endheaders()
v
Request-sent
|\_____________________________
| | getresponse() raises
| response = getresponse() | ConnectionError
v v
Unread-response Idle
[Response-headers-read]
|\____________________
| |
| response.read() | putrequest()
v v
Idle Req-started-unread-response
______/|
/ |
response.read() | | ( putheader() )* endheaders()
v v
Request-started Req-sent-unread-response
|
| response.read()
v
Request-sent
This diagram presents the following rules:
-- a second request may not be started until {response-headers-read}
-- a response [object] cannot be retrieved until {request-sent}
-- there is no differentiation between an unread response body and a
partially read response body
Note: this enforcement is applied by the HTTPConnection class. The
HTTPResponse class does not enforce this state machine, which
implies sophisticated clients may accelerate the request/response
pipeline. Caution should be taken, though: accelerating the states
beyond the above pattern may imply knowledge of the server's
connection-close behavior for certain requests. For example, it
is impossible to tell whether the server will close the connection
UNTIL the response headers have been read; this means that further
requests cannot be placed into the pipeline until it is known that
the server will NOT be closing the connection.
Logical State __state __response
------------- ------- ----------
Idle _CS_IDLE None
Request-started _CS_REQ_STARTED None
Request-sent _CS_REQ_SENT None
Unread-response _CS_IDLE <response_class>
Req-started-unread-response _CS_REQ_STARTED <response_class>
Req-sent-unread-response _CS_REQ_SENT <response_class>
� N)�urlsplit�HTTPResponse�HTTPConnection�
HTTPException�NotConnected�UnknownProtocol�UnknownTransferEncoding�UnimplementedFileMode�IncompleteRead�
InvalidURL�ImproperConnectionState�CannotSendRequest�CannotSendHeader�ResponseNotReady�
BadStatusLine�LineTooLong�RemoteDisconnected�error� responses�P i� ZUNKNOWNZIdlezRequest-startedzRequest-sentc C s i | ]}||j �qS � )�phrase)�.0�vr r �#/usr/lib64/python3.8/http/client.py�
<dictcomp>j s r i �d s [^:\s][^:\r\n]*s \n(?![ \t])|\r(?![ \t\n])z[ - ]z[ -]ZPATCHZPOSTZPUT�datac
C sh z| � d�W S tk
rb } z8t|j|j|j|jd|�� | |j|j� |f �d�W 5 d}~X Y nX dS )z<Call data.encode("latin-1") but show a better error message.�latin-1z`%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') if you want to send it encoded in UTF-8.N)�encode�UnicodeEncodeError�encoding�object�start�end�title)r �name�errr r r �_encode� s ���r( c @ s e Zd Zdd� ZdS )�HTTPMessagec C sj |� � d }t|�}g }d}| �� D ]@}|d|� � � |krBd}n|dd� �� sVd}|r$|�|� q$|S )a� Find all header lines matching a given header name.
Look through the list of headers and find all lines matching a given
header name (and their continuation lines). A list of the lines is
returned, without interpretation. If the header does not occur, an
empty list is returned. If the header occurs multiple times, all
occurrences are returned. Case is not important in the header name.
�:r N� )�lower�len�keys�isspace�append)�selfr&