r"""HTTP/1.1 client library
<intro stuff goes here>
<o
ther stuff, too>
HTTPConnection goes through a num
ber of "states", which define when a client
may legally make a
nother request or fetch
the response for a particular
request. This diagram details
these state transitions
:
(null)
|
| HTTPConnection()
v
Idle
|
| putrequest()
v
Request-started
|
| ( pu
theader() )* 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() | | ( pu
theader() )* 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] can
not 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 whe
ther
the server
will close
the connection
UNTIL
the response headers have
been read; this means that fur
ther
requests can
not 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 errno
import http
import io
import re
import socket
import sys
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",
"Can
notSendRequest", "Can
notSendHeader", "Response
NotReady",
"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.__mem
bers__)
# a
nother hack to maintain backwards compatibility
# Mapping status codes to official W3C
names
responses = {v
: v.phr
ase for v in http.HTTPStatus.__mem
bers__.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 o
therwise 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. May
be move
the code
there so
# that it doesn't need to
be part of
the public API.
The API h
as
# 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. C
ase 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 num
ber 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 ra
ther 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.BufferedIOB
ase)
:
# 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 b
asic 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 num
ber 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) whe
ther
# 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.re
ason = _UNKNOWN # Re
ason-Phr
ase
self.chunked = _UNKNOWN # is "chunked"
being used?
self.chunk_left = _UNKNOWN # bytes left to read in current chunk
self.length = _UNKNOWN # num
ber 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, re
ason = line.split(None, 2)
except ValueError
:
try
:
version, status = line.split(None, 1)
re
ason = ""
except ValueError
:
# empty version
will cause next test to fail.
version = ""
if
not version.starts
with("HTTP/")
:
self._close_conn()
raise BadStatusLine(line)
#
The status code is a three-digit num
ber
try
:
status = int(status)
if status < 100 or status > 999
:
raise BadStatusLine(line)
except ValueError
:
raise BadStatusLine(line)
return version, status, re
ason
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, re
ason = 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.re
ason = re
ason.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.starts
with("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 w
as 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 le
ast Akamai returns a "Connection
: Keep-Alive" header,
# which w
as 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
# o
therwise,
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
# c
ase occurs when
will_close is TRUE, length is None, and we
# read up to
the l
ast byte, but
NOT p
ast 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 self.chunked
:
return self._read_chunked(amt)
if amt is
not None
:
if self.length is
not None and amt > self.length
:
# clip
the read to
the "end of response"
amt = self.length
s = self.fp.read(amt)
if
not s and amt
:
# Ideally, we would raise IncompleteRead if
the content-length
# w
asn't satisfied, but it might break compatibility.
self._close_conn()
elif self.length is
not None
:
self.length -= len(s)
if
not self.length
:
self._close_conn()
return s
else
:
# Amount is
not given (unbounded read) so we must check self.length
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 num
ber
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
# w
asn'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 num
ber 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 l
ast chunk h
as
#
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
:
# l
ast 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 _read_chunked(self, amt=None)
:
assert self.chunked != _UNKNOWN
value = []
try
:
while True
:
chunk_left = self._get_chunk_left()
if chunk_left is None
:
break
if amt is
not None and amt <= chunk_left
:
value.append(self._safe_read(amt))
self.chunk_left = chunk_left - amt
break
value.append(self._safe_read(chunk_left))
if amt is
not None
:
amt -= chunk_left
self.chunk_left = 0
return b''.join(value)
except IncompleteRead
as exc
:
raise IncompleteRead(b''.join(value)) from exc
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 num
ber 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 le
ast 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 IOB
ase.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 IOB
ase 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 ge
theader(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 comm
as 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.Response
NotReady.
'''
if self.headers is None
:
raise Response
NotReady()
headers = self.headers.get_all(
name) or default
if isinstance(headers, str) or
not h
asattr(headers, '__iter__')
:
return headers
else
:
return ', '.join(headers)
def ge
theaders(self)
:
"""Return list of (header, value) tuples."""
if self.headers is None
:
raise Response
NotReady()
return list(self.headers.items())
# We override IOB
ase.__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 p
assed 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 l
ast-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 c
ases,
the HTTP server redirects a client to a
nother
URL.
The urlopen() function handles this transparently, but in
some c
ases
the caller needs to know which URL
the client w
as
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 w
as 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 whe
ther a file-like object is a text or a binary stream.
"""
return isinstance(stream, io.TextIOB
ase)
@staticmethod
def _get_content_length(body, method)
:
"""Get
the content-length b
ased 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 h
asattr(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
:
p
ass
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 p
assed to
the
constructor is used
as a proxy server that relays all communication to
the endpoint p
assed 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 h
as 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 = b"CONNECT %s
:%d HTTP/1.0\r\n" % (
self._tunnel_host.encode("
ascii"), self._tunnel_port)
headers = [connect]
for header, value in self._tunnel_headers.items()
:
headers.append(f"{header}
: {value}\r\n".encode("latin-1"))
headers.append(b"\r\n")
# Making a single send() call instead of one per line encourages
#
the host OS to use a more optimal packet size instead of
# potentially emitting a series of small packets.
self.send(b"".join(headers))
del headers
response = self.response_
class(self.sock, method=self._method)
(version, code, message) = response._read_status()
if code != http.HTTPStatus.OK
:
self.close()
raise OSError(f"Tunnel connection failed
: {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__."""
sys.audit("http.client.connect", self, self.host, self.port)
self.sock = self._create_connection(
(self.host,self.port), self.timeout, self.source_address)
# Might fail in OSs that don't implement TCP_NODELAY
try
:
self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
except OSError
as e
:
if e.errno != errno.ENOPROTOOPT
:
raise
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 o
ther 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 h
asattr(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")
sys.audit("http.client.send", self, datablock)
self.sock.sendall(datablock)
return
sys.audit("http.client.send", self, data)
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 h
asattr(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 e
asier
# to capture if PyObject_CheckBuffer w
as 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 p
assed 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 h
as been completed,
then forget about it.
if self.__response and self.__response.isclosed()
:
self.__response = None
# in certain c
ases, we can
not issue a
nother 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 h
as signalled that it is going
# to close
the connection upon completion.
# 3)
the headers for
the previous response have
not been read, thus
# we can
not determine whe
ther 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 p
assed
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 Can
notSendRequest(self.__state)
self._validate_method(method)
# Save
the method for use later in
the response ph
ase
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.starts
with('http')
:
nil, netloc, nil, nil, nil = urlsplit(url)
if netloc
:
try
:
netloc_enc = netloc.encode("
ascii")
except UnicodeEncodeError
:
netloc_enc = netloc.encode("idna")
self.pu
theader('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.pu
theader('Host', host_enc)
else
:
host_enc = host_enc.decode("
ascii")
self.pu
theader('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 o
ther 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.pu
theader('Accept-Encoding', 'identity')
# we can accept "chunked" Transfer-Encodings, but no o
thers
#
NOTE
: no TE header implies *only* "chunked"
#self.pu
theader('TE', 'chunked')
# if TE is supplied in
the header,
then it must appear in a
# Connection header.
#self.pu
theader('Connection', 'TE')
else
:
# For HTTP/1.0,
the server
will assume "
not chunked"
p
ass
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 le
ast {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 le
ast {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 le
ast {match.group()!r})")
def pu
theader(self, header, *values)
:
"""Send a request header line to
the server.
For example
: h.pu
theader('Accept', 'text/html')
"""
if self.__state != _CS_REQ_STARTED
:
raise Can
notSendHeader()
if h
asattr(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 h
asattr(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 l
ast header line h
as been sent to
the server.
This method sends
the request to
the server.
The optional message_body
argument can
be used to p
ass a message body
associated
with the
request.
"""
if self.__state == _CS_REQ_STARTED
:
self.__state = _CS_REQ_SENT
else
:
raise Can
notSendHeader()
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 ei
ther
#
the caller p
asses encode_chunked=True or
the following
# conditions hold
:
# 1. content-length h
as not been explicitly set
# 2.
the body is a file or iterable, but
not a str or bytes-like
# 3. Transfer-Encoding h
as 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 can
not 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.pu
theader('Transfer-Encoding', 'chunked')
else
:
self.pu
theader('Content-Length', str(content_length))
else
:
encode_chunked = False
for hdr, value in headers.items()
:
self.pu
theader(hdr, value)
if isinstance(body, str)
:
# RFC 2616 Section 3.7.1 says that text default h
as 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 h
as not been sent or if a previous response h
as
not be handled, Response
NotReady 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 h
as 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 (o
therwise, we
# can
not read this response's header to determine
the connection-close
#
behavior)
#
#
note
: if a prior response existed, but w
as 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 w
as reset and
the prior socket and
# response operate independently
# 2) persistent
: the response w
as retained and we await its
# isclosed() status to
become true.
#
if self.__state != _CS_REQ_SENT or self.__response
:
raise Response
NotReady(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 p
asses
the connection to
the response
self.close()
else
:
# remem
ber this, so we can tell when it is complete
self.__response = response
return response
except
:
response.close()
raise
try
:
import ssl
except ImportError
:
p
ass
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_host
name=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_host
name is
not None)
:
import warnings
warnings.warn("key_file, cert_file and check_host
name 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()
# send ALPN extension to indicate HTTP/1.1 protocol
if self._http_vsn == 11
:
context.set_alpn_protocols(['http/1.1'])
# 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_host
name is None
:
check_host
name = context.check_host
name
if check_host
name and
not will_verify
:
raise ValueError("check_host
name needs a SSL context
with "
"ei
ther 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 au
thenticate.
# 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_host
name is
not None
:
self._context.check_host
name = check_host
name
def connect(self)
:
"Connect to a host on a given (SSL) port."
super().connect()
if self._tunnel_host
:
server_host
name = self._tunnel_host
else
:
server_host
name = self.host
self.sock = self._context.wrap_socket(self.sock,
server_host
name=server_host
name)
__all__.append("HTTPSConnection")
class HTTPException(Exception)
:
# Sub
classes that define an __init__ must call Exception.__init__
# or define self.args. O
therwise, str()
will fail.
p
ass
class NotConnected(HTTPException)
:
p
ass
class InvalidURL(HTTPException)
:
p
ass
class UnknownProtocol(HTTPException)
:
def __init__(self, version)
:
self.args = version,
self.version = version
class UnknownTransferEncoding(HTTPException)
:
p
ass
class UnimplementedFileMode(HTTPException)
:
p
ass
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)
:
p
ass
class Can
notSendRequest(ImproperConnectionState)
:
p
ass
class Can
notSendHeader(ImproperConnectionState)
:
p
ass
class Response
NotReady(ImproperConnectionState)
:
p
ass
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
解析这些代码 怎么联接这个服务器
本文讨论了PHP7.0及以后版本中对与类名相同构造方法的弃用，强调了应使用__construct()作为标准构造方法。通过一个具体示例，展示了如何将旧的构造方法更新为新的标准。
扫一扫
508
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
