lib-python.2.7.httplib.py Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of jython-standalone Show documentation
Show all versions of jython-standalone Show documentation
Jython is an implementation of the high-level, dynamic, object-oriented
language Python written in 100% Pure Java, and seamlessly integrated with
the Java platform. It thus allows you to run Python on any Java platform.
r"""HTTP/1.1 client library
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
Req-started-unread-response _CS_REQ_STARTED
Req-sent-unread-response _CS_REQ_SENT
"""
from array import array
import os
import re
import socket
from sys import py3kwarning
from urlparse import urlsplit
import warnings
with warnings.catch_warnings():
if py3kwarning:
warnings.filterwarnings("ignore", ".*mimetools has been removed",
DeprecationWarning)
import mimetools
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
__all__ = ["HTTP", "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
# 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
# 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',
500: 'Internal Server Error',
501: 'Not Implemented',
502: 'Bad Gateway',
503: 'Service Unavailable',
504: 'Gateway Timeout',
505: 'HTTP Version Not Supported',
}
# maximal amount of data to read at one time in _safe_read
MAXAMOUNT = 1048576
# maximal line length when calling readline().
_MAXLINE = 65536
# maximum amount of headers accepted
_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 = "!" / "#" / "$" / "%" / "&" / "'" / "*"
# / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
# / DIGIT / ALPHA
# ; any VCHAR, except delimiters
#
# VCHAR defined in http://tools.ietf.org/html/rfc5234#appendix-B.1
# the patterns for both name and value are more lenient than RFC
# definitions to allow for backwards compatibility
_is_legal_header_name = re.compile(r'\A[^:\s][^:\r\n]*\Z').match
_is_illegal_header_value = re.compile(r'\n(?![ \t])|\r(?![ \t\n])').search
# These characters are not allowed within HTTP URL paths.
# See https://tools.ietf.org/html/rfc3986#section-3.3 and the
# https://tools.ietf.org/html/rfc3986#appendix-A pchar definition.
# Prevents CVE-2019-9740. Includes control characters such as \r\n.
# Restrict non-ASCII characters above \x7f (0x80-0xff).
_contains_disallowed_url_pchar_re = re.compile('[\x00-\x20\x7f-\xff]')
# Arguably only these _should_ allowed:
# _is_allowed_url_pchars_re = re.compile(r"^[/!$&'()*+,;=:@%a-zA-Z0-9._~-]+$")
# We are more lenient for assumed real world compatibility purposes.
# 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'}
class HTTPMessage(mimetools.Message):
def addheader(self, key, value):
"""Add header for field key handling repeats."""
prev = self.dict.get(key)
if prev is None:
self.dict[key] = value
else:
combined = ", ".join((prev, value))
self.dict[key] = combined
def addcontinue(self, key, more):
"""Add more field data from a continuation line."""
prev = self.dict[key]
self.dict[key] = prev + "\n " + more
def readheaders(self):
"""Read header lines.
Read header lines up to the entirely blank line that terminates them.
The (normally blank) line that ends the headers is skipped, but not
included in the returned list. If an invalid line is found in the
header section, it is skipped, and further lines are processed.
The variable self.status is set to the empty string if all went well,
otherwise it is an error message. The variable self.headers is a
completely uninterpreted list of lines contained in the header (so
printing them will reproduce the header exactly as it appears in the
file).
If multiple header fields with the same name occur, they are combined
according to the rules in RFC 2616 sec 4.2:
Appending each subsequent field-value to the first, each separated
by a comma. The order in which header fields with the same field-name
are received is significant to the interpretation of the combined
field value.
"""
# XXX The implementation overrides the readheaders() method of
# rfc822.Message. The base class design isn't amenable to
# customized behavior here so the method here is a copy of the
# base class code with a few small changes.
self.dict = {}
self.unixfrom = ''
self.headers = hlist = []
self.status = ''
headerseen = ""
firstline = 1
tell = None
if not hasattr(self.fp, 'unread') and self.seekable:
tell = self.fp.tell
while True:
if len(hlist) > _MAXHEADERS:
raise HTTPException("got more than %d headers" % _MAXHEADERS)
if tell:
try:
tell()
except IOError:
tell = None
self.seekable = 0
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
if not line:
self.status = 'EOF in headers'
break
# Skip unix From name time lines
if firstline and line.startswith('From '):
self.unixfrom = self.unixfrom + line
continue
firstline = 0
if headerseen and line[0] in ' \t':
# XXX Not sure if continuation lines are handled properly
# for http and/or for repeating headers
# It's a continuation line.
hlist.append(line)
self.addcontinue(headerseen, line.strip())
continue
elif self.iscomment(line):
# It's a comment. Ignore it.
continue
elif self.islast(line):
# Note! No pushback here! The delimiter line gets eaten.
break
headerseen = self.isheader(line)
if headerseen:
# It's a legal header line, save it.
hlist.append(line)
self.addheader(headerseen, line[len(headerseen)+1:].strip())
elif headerseen is not None:
# An empty header name. These aren't allowed in HTTP, but it's
# probably a benign mistake. Don't add the header, just keep
# going.
pass
else:
# It's not a header line; skip it and try the next line.
self.status = 'Non-header line where header expected'
class HTTPResponse:
# strict: If true, raise BadStatusLine if the status line can't be
# parsed as a valid HTTP/1.0 or 1.1 status line. By default it is
# false because it prevents clients from talking to HTTP/0.9
# servers. Note that a response with a sufficiently corrupted
# status line will look like an HTTP/0.9 response.
# See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details.
def __init__(self, sock, debuglevel=0, strict=0, method=None, buffering=False):
if buffering:
# The caller won't be using any sock.recv() calls, so buffering
# is fine and recommended for performance.
self.fp = sock.makefile('rb')
else:
# The buffer size is specified as zero, because the headers of
# the response are read with readline(). If the reads were
# buffered the readline() calls could consume some of the
# response, which make be read via a recv() on the underlying
# socket.
self.fp = sock.makefile('rb', 0)
self.debuglevel = debuglevel
self.strict = strict
self._method = method
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):
# Initialize with Simple-Response defaults
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header 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("No status line received - the server has closed the connection")
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 and status
# will be treated as 0.9 response.
version = ""
if not version.startswith('HTTP/'):
if self.strict:
self.close()
raise BadStatusLine(line)
else:
# assume it's a Simple-Response from an 0.9 server
self.fp = LineAndFileWrapper(line, self.fp)
return "HTTP/0.9", 200, ""
# 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.msg 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.status = status
self.reason = reason.strip()
if version == 'HTTP/1.0':
self.version = 10
elif version.startswith('HTTP/1.'):
self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1
elif version == 'HTTP/0.9':
self.version = 9
else:
raise UnknownProtocol(version)
if self.version == 9:
self.length = None
self.chunked = 0
self.will_close = 1
self.msg = HTTPMessage(StringIO())
return
self.msg = HTTPMessage(self.fp, 0)
if self.debuglevel > 0:
for hdr in self.msg.headers:
print "header:", hdr,
# don't let the msg keep an fp
self.msg.fp = None
# are we using the chunked-style of transfer encoding?
tr_enc = self.msg.getheader('transfer-encoding')
if tr_enc and tr_enc.lower() == "chunked":
self.chunked = 1
self.chunk_left = None
else:
self.chunked = 0
# 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"
length = self.msg.getheader('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 = 1
def _check_close(self):
conn = self.msg.getheader('connection')
if self.version == 11:
# An HTTP/1.1 proxy is assumed to stay open unless
# explicitly closed.
conn = self.msg.getheader('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.msg.getheader('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.msg.getheader('proxy-connection')
if pconn and "keep-alive" in pconn.lower():
return False
# otherwise, assume it will close
return True
def close(self):
fp = self.fp
if fp:
self.fp = None
fp.close()
def isclosed(self):
# 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
# XXX It would be nice to have readline and __iter__ for this, too.
def read(self, amt=None):
if self.fp is None:
return ''
if self._method == 'HEAD':
self.close()
return ''
if self.chunked:
return self._read_chunked(amt)
if amt is None:
# unbounded read
if self.length is None:
s = self.fp.read()
else:
try:
s = self._safe_read(self.length)
except IncompleteRead:
self.close()
raise
self.length = 0
self.close() # we read everything
return s
if self.length is not None:
if amt > self.length:
# clip the read to the "end of response"
amt = 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)
s = self.fp.read(amt)
if not s and amt:
# Ideally, we would raise IncompleteRead if the content-length
# wasn't satisfied, but it might break compatibility.
self.close()
if self.length is not None:
self.length -= len(s)
if not self.length:
self.close()
return s
def _read_chunked(self, amt):
assert self.chunked != _UNKNOWN
chunk_left = self.chunk_left
value = []
while True:
if chunk_left is None:
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("chunk size")
i = line.find(';')
if i >= 0:
line = line[:i] # strip chunk-extensions
try:
chunk_left = int(line, 16)
except ValueError:
# close the connection as protocol synchronisation is
# probably lost
self.close()
raise IncompleteRead(''.join(value))
if chunk_left == 0:
break
if amt is None:
value.append(self._safe_read(chunk_left))
elif amt < chunk_left:
value.append(self._safe_read(amt))
self.chunk_left = chunk_left - amt
return ''.join(value)
elif amt == chunk_left:
value.append(self._safe_read(amt))
self._safe_read(2) # toss the CRLF at the end of the chunk
self.chunk_left = None
return ''.join(value)
else:
value.append(self._safe_read(chunk_left))
amt -= 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
# 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 == '\r\n':
break
# we read everything; close the "file"
self.close()
return ''.join(value)
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 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.
"""
# NOTE(gps): As of svn r74426 socket._fileobject.read(x) will never
# return less than x bytes unless EOF is encountered. It now handles
# signal interruptions (socket.error EINTR) internally. This code
# never caught that exception anyways. It seems largely pointless.
# self.fp.read(amt) will work fine.
s = []
while amt > 0:
chunk = self.fp.read(min(amt, MAXAMOUNT))
if not chunk:
raise IncompleteRead(''.join(s), amt)
s.append(chunk)
amt -= len(chunk)
return ''.join(s)
def fileno(self):
return self.fp.fileno()
def getheader(self, name, default=None):
if self.msg is None:
raise ResponseNotReady()
return self.msg.getheader(name, default)
def getheaders(self):
"""Return list of (header, value) tuples."""
if self.msg is None:
raise ResponseNotReady()
return self.msg.items()
class HTTPConnection:
_http_vsn = 11
_http_vsn_str = 'HTTP/1.1'
response_class = HTTPResponse
default_port = HTTP_PORT
auto_open = 1
debuglevel = 0
strict = 0
def __init__(self, host, port=None, strict=None,
timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
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 = {}
if strict is not None:
self.strict = strict
(self.host, self.port) = self._get_hostport(host, port)
self._validate_host(self.host)
# This is stored as an instance variable to allow unittests
# to replace with a suitable mock
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 proxy server that relays all communication to the
endpoint passed to set_tunnel. This is done by sending a 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.
"""
# Verify if this is required.
if self.sock:
raise RuntimeError("Can't setup 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):
self.send("CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host,
self._tunnel_port))
for header, value in self._tunnel_headers.iteritems():
self.send("%s: %s\r\n" % (header, value))
self.send("\r\n")
response = self.response_class(self.sock, strict = self.strict,
method = self._method)
(version, code, message) = response._read_status()
if version == "HTTP/0.9":
# HTTP/0.9 doesn't support the CONNECT verb, so if httplib has
# concluded HTTP/0.9 is being used something has gone wrong.
self.close()
raise socket.error("Invalid response from tunnel request")
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 trailer
break
if line == '\r\n':
break
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)
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."""
if self.sock is None:
if self.auto_open:
self.connect()
else:
raise NotConnected()
if self.debuglevel > 0:
print "send:", repr(data)
blocksize = 8192
if hasattr(data,'read') and not isinstance(data, array):
if self.debuglevel > 0: print "sendIng a read()able"
datablock = data.read(blocksize)
while datablock:
self.sock.sendall(datablock)
datablock = data.read(blocksize)
else:
self.sock.sendall(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(("", ""))
msg = "\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, str):
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()
# 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")
# Wrap the IPv6 Host Header with [] (RFC 2732)
if host_enc.find(':') >= 0:
host_enc = "[" + host_enc + "]"
if port == self.default_port:
self.putheader('Host', host_enc)
else:
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):
# On Python 2, request is already encoded (default)
return request
def _validate_path(self, url):
"""Validate a url for putrequest."""
# Prevent CVE-2019-9740.
match = _contains_disallowed_url_pchar_re.search(url)
if match:
msg = (
"URL can't contain control characters. {url!r} "
"(found at least {matched!r})"
).format(matched=match.group(), url=url)
raise InvalidURL(msg)
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:
msg = (
"URL can't contain control characters. {host!r} "
"(found at least {matched!r})"
).format(matched=match.group(), host=host)
raise InvalidURL(msg)
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()
header = '%s' % header
if not _is_legal_header_name(header):
raise ValueError('Invalid header name %r' % (header,))
values = [str(v) for v in values]
for one_value in values:
if _is_illegal_header_value(one_value):
raise ValueError('Invalid header value %r' % (one_value,))
hdr = '%s: %s' % (header, '\r\n\t'.join(values))
self._output(hdr)
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 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, method):
# Set the content-length based on the body. If the body is "empty", we
# set Content-Length: 0 for methods that expect a body (RFC 7230,
# Section 3.3.2). If the body is set for other methods, we set the
# header provided we can figure out what the length is.
thelen = None
if body is None and method.upper() in _METHODS_EXPECTING_BODY:
thelen = '0'
elif body is not None:
try:
thelen = str(len(body))
except (TypeError, AttributeError):
# 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 'content-length' not in header_names:
self._set_content_length(body, method)
for hdr, value in headers.iteritems():
self.putheader(hdr, value)
self.endheaders(body)
def getresponse(self, buffering=False):
"Get the response from the server."
# 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()
args = (self.sock,)
kwds = {"strict":self.strict, "method":self._method}
if self.debuglevel > 0:
args += (self.debuglevel,)
if buffering:
#only add this keyword if non-default, for compatibility with
#other response_classes.
kwds["buffering"] = True;
response = self.response_class(*args, **kwds)
try:
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
except:
response.close()
raise
class HTTP:
"Compatibility class with httplib.py from 1.5."
_http_vsn = 10
_http_vsn_str = 'HTTP/1.0'
debuglevel = 0
_connection_class = HTTPConnection
def __init__(self, host='', port=None, strict=None):
"Provide a default host, since the superclass requires one."
# some joker passed 0 explicitly, meaning default port
if port == 0:
port = None
# Note that we may pass an empty string as the host; this will raise
# an error when we attempt to connect. Presumably, the client code
# will call connect before then, with a proper host.
self._setup(self._connection_class(host, port, strict))
def _setup(self, conn):
self._conn = conn
# set up delegation to flesh out interface
self.send = conn.send
self.putrequest = conn.putrequest
self.putheader = conn.putheader
self.endheaders = conn.endheaders
self.set_debuglevel = conn.set_debuglevel
conn._http_vsn = self._http_vsn
conn._http_vsn_str = self._http_vsn_str
self.file = None
def connect(self, host=None, port=None):
"Accept arguments to set the host/port, since the superclass doesn't."
if host is not None:
(self._conn.host, self._conn.port) = self._conn._get_hostport(host, port)
self._conn.connect()
def getfile(self):
"Provide a getfile, since the superclass' does not use this concept."
return self.file
def getreply(self, buffering=False):
"""Compat definition since superclass does not define it.
Returns a tuple consisting of:
- server status code (e.g. '200' if all goes well)
- server "reason" corresponding to status code
- any RFC822 headers in the response from the server
"""
try:
if not buffering:
response = self._conn.getresponse()
else:
#only add this keyword if non-default for compatibility
#with other connection classes
response = self._conn.getresponse(buffering)
except BadStatusLine, e:
### hmm. if getresponse() ever closes the socket on a bad request,
### then we are going to have problems with self.sock
### should we keep this behavior? do people use it?
# keep the socket open (as a file), and return it
self.file = self._conn.sock.makefile('rb', 0)
# close our socket -- we want to restart after any protocol error
self.close()
self.headers = None
return -1, e.line, None
self.headers = response.msg
self.file = response.fp
return response.status, response.reason, response.msg
def close(self):
self._conn.close()
# note that self.file == response.fp, which gets closed by the
# superclass. just clear the object ref here.
### hmm. messy. if status==-1, then self.file is owned by us.
### well... we aren't explicitly closing, but losing this ref will
### do it
self.file = None
try:
import ssl
except ImportError:
pass
else:
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, context=None):
HTTPConnection.__init__(self, host, port, strict, timeout,
source_address)
self.key_file = key_file
self.cert_file = cert_file
if context is None:
context = ssl._create_default_https_context()
if key_file or cert_file:
context.load_cert_chain(cert_file, key_file)
self._context = context
def connect(self):
"Connect to a host on a given (SSL) port."
HTTPConnection.connect(self)
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 HTTPS(HTTP):
"""Compatibility with 1.5 httplib interface
Python 1.5.2 did not have an HTTPS class, but it defined an
interface for sending http requests that is also useful for
https.
"""
_connection_class = HTTPSConnection
def __init__(self, host='', port=None, key_file=None, cert_file=None,
strict=None, context=None):
# provide a default host, pass the X509 cert info
# urf. compensate for bad input.
if port == 0:
port = None
self._setup(self._connection_class(host, port, key_file,
cert_file, strict,
context=context))
# we never actually use these for anything, but we keep them
# here for compatibility with post-1.5.2 CVS.
self.key_file = key_file
self.cert_file = cert_file
def FakeSocket (sock, sslobj):
warnings.warn("FakeSocket is deprecated, and won't be in 3.x. " +
"Use the result of ssl.wrap_socket() directly instead.",
DeprecationWarning, stacklevel=2)
return sslobj
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
class LineAndFileWrapper:
"""A limited file-like object for HTTP/0.9 responses."""
# The status-line parsing code calls readline(), which normally
# get the HTTP status line. For a 0.9 response, however, this is
# actually the first line of the body! Clients need to get a
# readable file object that contains that line.
def __init__(self, line, file):
self._line = line
self._file = file
self._line_consumed = 0
self._line_offset = 0
self._line_left = len(line)
def __getattr__(self, attr):
return getattr(self._file, attr)
def _done(self):
# called when the last byte is read from the line. After the
# call, all read methods are delegated to the underlying file
# object.
self._line_consumed = 1
self.read = self._file.read
self.readline = self._file.readline
self.readlines = self._file.readlines
def read(self, amt=None):
if self._line_consumed:
return self._file.read(amt)
assert self._line_left
if amt is None or amt > self._line_left:
s = self._line[self._line_offset:]
self._done()
if amt is None:
return s + self._file.read()
else:
return s + self._file.read(amt - len(s))
else:
assert amt <= self._line_left
i = self._line_offset
j = i + amt
s = self._line[i:j]
self._line_offset = j
self._line_left -= amt
if self._line_left == 0:
self._done()
return s
def readline(self):
if self._line_consumed:
return self._file.readline()
assert self._line_left
s = self._line[self._line_offset:]
self._done()
return s
def readlines(self, size=None):
if self._line_consumed:
return self._file.readlines(size)
assert self._line_left
L = [self._line[self._line_offset:]]
self._done()
if size is None:
return L + self._file.readlines()
else:
return L + self._file.readlines(size)