12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346 |
- """HTTP/1.1 client library
- A backport of the Python 3.3 http/client.py module for python-future.
- <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
- |
- | response = getresponse()
- v
- Unread-response [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>
- """
- from __future__ import (absolute_import, division,
- print_function, unicode_literals)
- from future.builtins import bytes, int, str, super
- from future.utils import PY2
- from future.backports.email import parser as email_parser
- from future.backports.email import message as email_message
- from future.backports.misc import create_connection as socket_create_connection
- import io
- import os
- import socket
- from future.backports.urllib.parse import urlsplit
- import warnings
- from array import array
- if PY2:
- from collections import Iterable
- else:
- from collections.abc import Iterable
- __all__ = ["HTTPResponse", "HTTPConnection",
- "HTTPException", "NotConnected", "UnknownProtocol",
- "UnknownTransferEncoding", "UnimplementedFileMode",
- "IncompleteRead", "InvalidURL", "ImproperConnectionState",
- "CannotSendRequest", "CannotSendHeader", "ResponseNotReady",
- "BadStatusLine", "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'
- # status codes
- # informational
- CONTINUE = 100
- SWITCHING_PROTOCOLS = 101
- PROCESSING = 102
- # successful
- OK = 200
- CREATED = 201
- ACCEPTED = 202
- NON_AUTHORITATIVE_INFORMATION = 203
- NO_CONTENT = 204
- RESET_CONTENT = 205
- PARTIAL_CONTENT = 206
- MULTI_STATUS = 207
- IM_USED = 226
- # redirection
- MULTIPLE_CHOICES = 300
- MOVED_PERMANENTLY = 301
- FOUND = 302
- SEE_OTHER = 303
- NOT_MODIFIED = 304
- USE_PROXY = 305
- TEMPORARY_REDIRECT = 307
- # client error
- BAD_REQUEST = 400
- UNAUTHORIZED = 401
- PAYMENT_REQUIRED = 402
- FORBIDDEN = 403
- NOT_FOUND = 404
- METHOD_NOT_ALLOWED = 405
- NOT_ACCEPTABLE = 406
- PROXY_AUTHENTICATION_REQUIRED = 407
- REQUEST_TIMEOUT = 408
- CONFLICT = 409
- GONE = 410
- LENGTH_REQUIRED = 411
- PRECONDITION_FAILED = 412
- REQUEST_ENTITY_TOO_LARGE = 413
- REQUEST_URI_TOO_LONG = 414
- UNSUPPORTED_MEDIA_TYPE = 415
- REQUESTED_RANGE_NOT_SATISFIABLE = 416
- EXPECTATION_FAILED = 417
- UNPROCESSABLE_ENTITY = 422
- LOCKED = 423
- FAILED_DEPENDENCY = 424
- UPGRADE_REQUIRED = 426
- PRECONDITION_REQUIRED = 428
- TOO_MANY_REQUESTS = 429
- REQUEST_HEADER_FIELDS_TOO_LARGE = 431
- # server error
- INTERNAL_SERVER_ERROR = 500
- NOT_IMPLEMENTED = 501
- BAD_GATEWAY = 502
- SERVICE_UNAVAILABLE = 503
- GATEWAY_TIMEOUT = 504
- HTTP_VERSION_NOT_SUPPORTED = 505
- INSUFFICIENT_STORAGE = 507
- NOT_EXTENDED = 510
- NETWORK_AUTHENTICATION_REQUIRED = 511
- # Mapping status codes to official W3C names
- responses = {
- 100: 'Continue',
- 101: 'Switching Protocols',
- 200: 'OK',
- 201: 'Created',
- 202: 'Accepted',
- 203: 'Non-Authoritative Information',
- 204: 'No Content',
- 205: 'Reset Content',
- 206: 'Partial Content',
- 300: 'Multiple Choices',
- 301: 'Moved Permanently',
- 302: 'Found',
- 303: 'See Other',
- 304: 'Not Modified',
- 305: 'Use Proxy',
- 306: '(Unused)',
- 307: 'Temporary Redirect',
- 400: 'Bad Request',
- 401: 'Unauthorized',
- 402: 'Payment Required',
- 403: 'Forbidden',
- 404: 'Not Found',
- 405: 'Method Not Allowed',
- 406: 'Not Acceptable',
- 407: 'Proxy Authentication Required',
- 408: 'Request Timeout',
- 409: 'Conflict',
- 410: 'Gone',
- 411: 'Length Required',
- 412: 'Precondition Failed',
- 413: 'Request Entity Too Large',
- 414: 'Request-URI Too Long',
- 415: 'Unsupported Media Type',
- 416: 'Requested Range Not Satisfiable',
- 417: 'Expectation Failed',
- 428: 'Precondition Required',
- 429: 'Too Many Requests',
- 431: 'Request Header Fields Too Large',
- 500: 'Internal Server Error',
- 501: 'Not Implemented',
- 502: 'Bad Gateway',
- 503: 'Service Unavailable',
- 504: 'Gateway Timeout',
- 505: 'HTTP Version Not Supported',
- 511: 'Network Authentication Required',
- }
- # maximal amount of data to read at one time in _safe_read
- MAXAMOUNT = 1048576
- # maximal line length when calling readline().
- _MAXLINE = 65536
- _MAXHEADERS = 100
- 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 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 = []
- 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
- hstring = bytes(b'').join(headers).decode('iso-8859-1')
- return email_parser.Parser(_class=_class).parsestr(hstring)
- _strict_sentinel = object()
- class HTTPResponse(io.RawIOBase):
- # 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, strict=_strict_sentinel, 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
- if strict is not _strict_sentinel:
- warnings.warn("the 'strict' argument isn't supported anymore; "
- "http.client now always assumes HTTP/1.x compliant servers.",
- DeprecationWarning, 2)
- 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 BadStatusLine(line)
- 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
- while True:
- skip = self.fp.readline(_MAXLINE + 1)
- if len(skip) > _MAXLINE:
- raise LineTooLong("header line")
- skip = skip.strip()
- if not skip:
- break
- if self.debuglevel > 0:
- print("header:", skip)
- 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 in self.headers:
- print("header:", hdr, end=" ")
- # 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")
- # are we using the chunked-style of transfer encoding?
- tr_enc = self.headers.get("transfer-encoding")
- 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.
- conn = self.headers.get("connection")
- 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):
- super().close() # set "closed" flag
- 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):
- 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 bytes(b"")
- if self._method == "HEAD":
- self._close_conn()
- return bytes(b"")
- if amt is not None:
- # Amount is given, so call base class version
- # (which is implemented in terms of self.readinto)
- return bytes(super(HTTPResponse, self).read(amt))
- 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 bytes(s)
- def readinto(self, b):
- 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)
- if PY2:
- data = self.fp.read(len(b))
- n = len(data)
- b[:n] = data
- else:
- 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 _readall_chunked(self):
- assert self.chunked != _UNKNOWN
- chunk_left = self.chunk_left
- value = []
- while True:
- if chunk_left is None:
- try:
- chunk_left = self._read_next_chunk_size()
- if chunk_left == 0:
- break
- except ValueError:
- raise IncompleteRead(bytes(b'').join(value))
- value.append(self._safe_read(chunk_left))
- # we read the whole chunk, get another
- self._safe_read(2) # toss the CRLF at the end of the chunk
- chunk_left = None
- self._read_and_discard_trailer()
- # we read everything; close the "file"
- self._close_conn()
- return bytes(b'').join(value)
- def _readinto_chunked(self, b):
- assert self.chunked != _UNKNOWN
- chunk_left = self.chunk_left
- total_bytes = 0
- mvb = memoryview(b)
- while True:
- if chunk_left is None:
- try:
- chunk_left = self._read_next_chunk_size()
- if chunk_left == 0:
- break
- except ValueError:
- raise IncompleteRead(bytes(b[0:total_bytes]))
- if len(mvb) < chunk_left:
- n = self._safe_readinto(mvb)
- self.chunk_left = chunk_left - n
- return total_bytes + n
- elif len(mvb) == chunk_left:
- n = self._safe_readinto(mvb)
- self._safe_read(2) # toss the CRLF at the end of the chunk
- self.chunk_left = None
- return total_bytes + n
- else:
- temp_mvb = mvb[0:chunk_left]
- n = self._safe_readinto(temp_mvb)
- mvb = mvb[n:]
- total_bytes += n
- # we read the whole chunk, get another
- self._safe_read(2) # toss the CRLF at the end of the chunk
- chunk_left = None
- self._read_and_discard_trailer()
- # we read everything; close the "file"
- self._close_conn()
- return total_bytes
- def _safe_read(self, amt):
- """Read the number of bytes requested, compensating for partial reads.
- Normally, we have a blocking socket, but a read() can be interrupted
- by a signal (resulting in a partial read).
- Note that we cannot distinguish between EOF and an interrupt when zero
- bytes have been read. IncompleteRead() will be raised in this
- situation.
- 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.
- """
- s = []
- while amt > 0:
- chunk = self.fp.read(min(amt, MAXAMOUNT))
- if not chunk:
- raise IncompleteRead(bytes(b'').join(s), amt)
- s.append(chunk)
- amt -= len(chunk)
- return bytes(b"").join(s)
- def _safe_readinto(self, b):
- """Same as _safe_read, but for reading into a buffer."""
- total_bytes = 0
- mvb = memoryview(b)
- while total_bytes < len(b):
- if MAXAMOUNT < len(mvb):
- temp_mvb = mvb[0:MAXAMOUNT]
- if PY2:
- data = self.fp.read(len(temp_mvb))
- n = len(data)
- temp_mvb[:n] = data
- else:
- n = self.fp.readinto(temp_mvb)
- else:
- if PY2:
- data = self.fp.read(len(mvb))
- n = len(data)
- mvb[:n] = data
- else:
- n = self.fp.readinto(mvb)
- if not n:
- raise IncompleteRead(bytes(mvb[0:total_bytes]), len(b))
- mvb = mvb[n:]
- total_bytes += n
- return total_bytes
- def fileno(self):
- return self.fp.fileno()
- def getheader(self, name, default=None):
- 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):
- return self.headers
- def geturl(self):
- return self.url
- def getcode(self):
- return self.status
- class HTTPConnection(object):
- _http_vsn = 11
- _http_vsn_str = 'HTTP/1.1'
- response_class = HTTPResponse
- default_port = HTTP_PORT
- auto_open = 1
- debuglevel = 0
- def __init__(self, host, port=None, strict=_strict_sentinel,
- timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
- if strict is not _strict_sentinel:
- warnings.warn("the 'strict' argument isn't supported anymore; "
- "http.client now always assumes HTTP/1.x compliant servers.",
- DeprecationWarning, 2)
- self.timeout = timeout
- self.source_address = source_address
- 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._set_hostport(host, port)
- def set_tunnel(self, host, port=None, headers=None):
- """ Sets up the host and the port for the HTTP CONNECT Tunnelling.
- The headers argument should be a mapping of extra HTTP headers
- to send with the CONNECT request.
- """
- self._tunnel_host = host
- self._tunnel_port = port
- if headers:
- self._tunnel_headers = headers
- else:
- self._tunnel_headers.clear()
- def _set_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]
- self.host = host
- self.port = port
- def set_debuglevel(self, level):
- self.debuglevel = level
- def _tunnel(self):
- self._set_hostport(self._tunnel_host, self._tunnel_port)
- connect_str = "CONNECT %s:%d HTTP/1.0\r\n" % (self.host, self.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(bytes(b'\r\n'))
- response = self.response_class(self.sock, method=self._method)
- (version, code, message) = response._read_status()
- if code != 200:
- self.close()
- raise socket.error("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
- def connect(self):
- """Connect to the host and port specified in __init__."""
- self.sock = socket_create_connection((self.host,self.port),
- self.timeout, self.source_address)
- if self._tunnel_host:
- self._tunnel()
- def close(self):
- """Close the connection to the HTTP server."""
- if self.sock:
- self.sock.close() # close it manually... there may be other refs
- self.sock = None
- if self.__response:
- self.__response.close()
- self.__response = None
- self.__state = _CS_IDLE
- 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))
- blocksize = 8192
- # Python 2.7 array objects have a read method which is incompatible
- # with the 2-arg calling syntax below.
- if hasattr(data, "read") and not isinstance(data, array):
- if self.debuglevel > 0:
- print("sendIng a read()able")
- encode = False
- try:
- mode = data.mode
- except AttributeError:
- # io.BytesIO and other file-like objects don't have a `mode`
- # attribute.
- pass
- else:
- if "b" not in mode:
- encode = True
- if self.debuglevel > 0:
- print("encoding file using iso-8859-1")
- while 1:
- datablock = data.read(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, 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 _send_output(self, message_body=None):
- """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((bytes(b""), bytes(b"")))
- msg = bytes(b"\r\n").join(self._buffer)
- del self._buffer[:]
- # If msg and message_body are sent in a single send() call,
- # it will avoid performance problems caused by the interaction
- # between delayed ack and the Nagle algorithm.
- if isinstance(message_body, bytes):
- msg += message_body
- message_body = None
- self.send(msg)
- if message_body is not None:
- # message_body was not a string (i.e. it is a file), and
- # we must run the risk of Nagle.
- self.send(message_body)
- def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0):
- """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)
- # Save the method we use, we need it later in the response phase
- self._method = method
- if not url:
- url = '/'
- request = '%s %s %s' % (method, url, self._http_vsn_str)
- # Non-ASCII characters should have been eliminated earlier
- self._output(request.encode('ascii'))
- 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:
- try:
- host_enc = self.host.encode("ascii")
- except UnicodeEncodeError:
- host_enc = self.host.encode("idna")
- # As per RFC 273, IPv6 address should be wrapped with []
- # when used as Host header
- if self.host.find(':') >= 0:
- host_enc = bytes(b'[' + host_enc + b']')
- if self.port == self.default_port:
- self.putheader('Host', host_enc)
- else:
- host_enc = host_enc.decode("ascii")
- self.putheader('Host', "%s:%s" % (host_enc, self.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 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')
- 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')
- value = bytes(b'\r\n\t').join(values)
- header = header + bytes(b': ') + value
- self._output(header)
- def endheaders(self, message_body=None):
- """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. The message body will be sent in the same packet as the
- message headers if it is a string, otherwise it is sent as a separate
- packet.
- """
- if self.__state == _CS_REQ_STARTED:
- self.__state = _CS_REQ_SENT
- else:
- raise CannotSendHeader()
- self._send_output(message_body)
- def request(self, method, url, body=None, headers={}):
- """Send a complete request to the server."""
- self._send_request(method, url, body, headers)
- def _set_content_length(self, body):
- # Set the content-length based on the body.
- thelen = None
- try:
- thelen = str(len(body))
- except TypeError as te:
- # If this is a file-like object, try to
- # fstat its file descriptor
- try:
- thelen = str(os.fstat(body.fileno()).st_size)
- except (AttributeError, OSError):
- # Don't send a length if this failed
- if self.debuglevel > 0: print("Cannot stat!!")
- if thelen is not None:
- self.putheader('Content-Length', thelen)
- def _send_request(self, method, url, body, headers):
- # Honor explicitly requested Host: and Accept-Encoding: headers.
- header_names = dict.fromkeys([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)
- if body is not None and ('content-length' not in header_names):
- self._set_content_length(body)
- 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 = body.encode('iso-8859-1')
- self.endheaders(body)
- 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
- class 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)
- response.begin()
- 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
- try:
- import ssl
- from ssl import SSLContext
- 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,
- strict=_strict_sentinel, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
- source_address=None, **_3to2kwargs):
- if 'check_hostname' in _3to2kwargs: check_hostname = _3to2kwargs['check_hostname']; del _3to2kwargs['check_hostname']
- else: check_hostname = None
- if 'context' in _3to2kwargs: context = _3to2kwargs['context']; del _3to2kwargs['context']
- else: context = None
- super(HTTPSConnection, self).__init__(host, port, strict, timeout,
- source_address)
- self.key_file = key_file
- self.cert_file = cert_file
- if context is None:
- # Some reasonable defaults
- context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
- context.options |= ssl.OP_NO_SSLv2
- will_verify = context.verify_mode != ssl.CERT_NONE
- if check_hostname is None:
- check_hostname = will_verify
- elif 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)
- self._context = context
- self._check_hostname = check_hostname
- def connect(self):
- "Connect to a host on a given (SSL) port."
- sock = socket_create_connection((self.host, self.port),
- self.timeout, self.source_address)
- if self._tunnel_host:
- self.sock = sock
- self._tunnel()
- server_hostname = self.host if ssl.HAS_SNI else None
- self.sock = self._context.wrap_socket(sock,
- server_hostname=server_hostname)
- try:
- if self._check_hostname:
- ssl.match_hostname(self.sock.getpeercert(), self.host)
- except Exception:
- self.sock.shutdown(socket.SHUT_RDWR)
- self.sock.close()
- raise
- __all__.append("HTTPSConnection")
- # ######################################
- # # We use the old HTTPSConnection class from Py2.7, because ssl.SSLContext
- # # doesn't exist in the Py2.7 stdlib
- # class HTTPSConnection(HTTPConnection):
- # "This class allows communication via SSL."
- # default_port = HTTPS_PORT
- # def __init__(self, host, port=None, key_file=None, cert_file=None,
- # strict=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
- # source_address=None):
- # HTTPConnection.__init__(self, host, port, strict, timeout,
- # source_address)
- # self.key_file = key_file
- # self.cert_file = cert_file
- # def connect(self):
- # "Connect to a host on a given (SSL) port."
- # sock = socket_create_connection((self.host, self.port),
- # self.timeout, self.source_address)
- # if self._tunnel_host:
- # self.sock = sock
- # self._tunnel()
- # self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file)
- # __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 'IncompleteRead(%i bytes read%s)' % (len(self.partial), e)
- def __str__(self):
- return repr(self)
- 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))
- # for backwards compatibility
- error = HTTPException
|