Update urllib3-1.26.7

This commit is contained in:
JonnyWong16 2021-10-14 21:00:02 -07:00
parent a3bfabb5f6
commit b6595232d2
No known key found for this signature in database
GPG key ID: B1F1F9807184697A
38 changed files with 4375 additions and 2823 deletions

View file

@ -1,51 +1,53 @@
from __future__ import absolute_import
import errno
import logging
import socket
import sys
import warnings
from socket import error as SocketError
from socket import timeout as SocketTimeout
from socket import error as SocketError, timeout as SocketTimeout
import socket
from .connection import (
BaseSSLError,
BrokenPipeError,
DummyConnection,
HTTPConnection,
HTTPException,
HTTPSConnection,
VerifiedHTTPSConnection,
port_by_scheme,
)
from .exceptions import (
ClosedPoolError,
ProtocolError,
EmptyPoolError,
HeaderParsingError,
HostChangedError,
InsecureRequestWarning,
LocationValueError,
MaxRetryError,
NewConnectionError,
ProtocolError,
ProxyError,
ReadTimeoutError,
SSLError,
TimeoutError,
InsecureRequestWarning,
NewConnectionError,
)
from .packages.ssl_match_hostname import CertificateError
from .packages import six
from .packages.six.moves import queue
from .connection import (
port_by_scheme,
DummyConnection,
HTTPConnection, HTTPSConnection, VerifiedHTTPSConnection,
HTTPException, BaseSSLError,
)
from .packages.ssl_match_hostname import CertificateError
from .request import RequestMethods
from .response import HTTPResponse
from .util.connection import is_connection_dropped
from .util.proxy import connection_requires_http_tunnel
from .util.queue import LifoQueue
from .util.request import set_file_position
from .util.response import assert_header_parsing
from .util.retry import Retry
from .util.timeout import Timeout
from .util.url import get_host, Url
if six.PY2:
# Queue is imported for side effects on MS Windows
import Queue as _unused_module_Queue # noqa: F401
from .util.url import Url, _encode_target
from .util.url import _normalize_host as normalize_host
from .util.url import get_host, parse_url
xrange = six.moves.xrange
@ -59,22 +61,26 @@ class ConnectionPool(object):
"""
Base class for all connection pools, such as
:class:`.HTTPConnectionPool` and :class:`.HTTPSConnectionPool`.
.. note::
ConnectionPool.urlopen() does not normalize or percent-encode target URIs
which is useful if your target server doesn't support percent-encoded
target URIs.
"""
scheme = None
QueueCls = queue.LifoQueue
QueueCls = LifoQueue
def __init__(self, host, port=None):
if not host:
raise LocationValueError("No host specified.")
self.host = _ipv6_host(host).lower()
self.host = _normalize_host(host, scheme=self.scheme)
self._proxy_host = host.lower()
self.port = port
def __str__(self):
return '%s(host=%r, port=%r)' % (type(self).__name__,
self.host, self.port)
return "%s(host=%r, port=%r)" % (type(self).__name__, self.host, self.port)
def __enter__(self):
return self
@ -92,7 +98,7 @@ class ConnectionPool(object):
# This is taken from http://hg.python.org/cpython/file/7aaba721ebc0/Lib/socket.py#l252
_blocking_errnos = set([errno.EAGAIN, errno.EWOULDBLOCK])
_blocking_errnos = {errno.EAGAIN, errno.EWOULDBLOCK}
class HTTPConnectionPool(ConnectionPool, RequestMethods):
@ -101,16 +107,16 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
:param host:
Host used for this HTTP Connection (e.g. "localhost"), passed into
:class:`httplib.HTTPConnection`.
:class:`http.client.HTTPConnection`.
:param port:
Port used for this HTTP Connection (None is equivalent to 80), passed
into :class:`httplib.HTTPConnection`.
into :class:`http.client.HTTPConnection`.
:param strict:
Causes BadStatusLine to be raised if the status line can't be parsed
as a valid HTTP/1.0 or 1.1 status line, passed into
:class:`httplib.HTTPConnection`.
:class:`http.client.HTTPConnection`.
.. note::
Only works in Python 2. This parameter is ignored in Python 3.
@ -144,26 +150,36 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
:param _proxy:
Parsed proxy URL, should not be used directly, instead, see
:class:`urllib3.connectionpool.ProxyManager`"
:class:`urllib3.ProxyManager`
:param _proxy_headers:
A dictionary with proxy headers, should not be used directly,
instead, see :class:`urllib3.connectionpool.ProxyManager`"
instead, see :class:`urllib3.ProxyManager`
:param \\**conn_kw:
Additional parameters are used to create fresh :class:`urllib3.connection.HTTPConnection`,
:class:`urllib3.connection.HTTPSConnection` instances.
"""
scheme = 'http'
scheme = "http"
ConnectionCls = HTTPConnection
ResponseCls = HTTPResponse
def __init__(self, host, port=None, strict=False,
timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1, block=False,
headers=None, retries=None,
_proxy=None, _proxy_headers=None,
**conn_kw):
def __init__(
self,
host,
port=None,
strict=False,
timeout=Timeout.DEFAULT_TIMEOUT,
maxsize=1,
block=False,
headers=None,
retries=None,
_proxy=None,
_proxy_headers=None,
_proxy_config=None,
**conn_kw
):
ConnectionPool.__init__(self, host, port)
RequestMethods.__init__(self, headers)
@ -183,6 +199,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
self.proxy = _proxy
self.proxy_headers = _proxy_headers or {}
self.proxy_config = _proxy_config
# Fill the queue up so that doing get() on it will block properly
for _ in xrange(maxsize):
@ -197,19 +214,30 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# Enable Nagle's algorithm for proxies, to avoid packet fragmentation.
# We cannot know if the user has added default socket options, so we cannot replace the
# list.
self.conn_kw.setdefault('socket_options', [])
self.conn_kw.setdefault("socket_options", [])
self.conn_kw["proxy"] = self.proxy
self.conn_kw["proxy_config"] = self.proxy_config
def _new_conn(self):
"""
Return a fresh :class:`HTTPConnection`.
"""
self.num_connections += 1
log.debug("Starting new HTTP connection (%d): %s",
self.num_connections, self.host)
log.debug(
"Starting new HTTP connection (%d): %s:%s",
self.num_connections,
self.host,
self.port or "80",
)
conn = self.ConnectionCls(host=self.host, port=self.port,
timeout=self.timeout.connect_timeout,
strict=self.strict, **self.conn_kw)
conn = self.ConnectionCls(
host=self.host,
port=self.port,
timeout=self.timeout.connect_timeout,
strict=self.strict,
**self.conn_kw
)
return conn
def _get_conn(self, timeout=None):
@ -233,18 +261,19 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
except queue.Empty:
if self.block:
raise EmptyPoolError(self,
"Pool reached maximum size and no more "
"connections are allowed.")
raise EmptyPoolError(
self,
"Pool reached maximum size and no more connections are allowed.",
)
pass # Oh well, we'll create a new connection then
# If this is a persistent connection, check if it got disconnected
if conn and is_connection_dropped(conn):
log.debug("Resetting dropped connection: %s", self.host)
conn.close()
if getattr(conn, 'auto_open', 1) == 0:
if getattr(conn, "auto_open", 1) == 0:
# This is a proxied connection that has been mutated by
# httplib._tunnel() and cannot be reused (since it would
# http.client._tunnel() and cannot be reused (since it would
# attempt to bypass the proxy)
conn = None
@ -272,9 +301,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
pass
except queue.Full:
# This should never happen if self.block == True
log.warning(
"Connection pool is full, discarding connection: %s",
self.host)
log.warning("Connection pool is full, discarding connection: %s", self.host)
# Connection never got put back into the pool, close it.
if conn:
@ -291,7 +318,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
pass
def _get_timeout(self, timeout):
""" Helper that always returns a :class:`urllib3.util.Timeout` """
"""Helper that always returns a :class:`urllib3.util.Timeout`"""
if timeout is _Default:
return self.timeout.clone()
@ -306,21 +333,30 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
"""Is the error actually a timeout? Will raise a ReadTimeout or pass"""
if isinstance(err, SocketTimeout):
raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)
raise ReadTimeoutError(
self, url, "Read timed out. (read timeout=%s)" % timeout_value
)
# See the above comment about EAGAIN in Python 3. In Python 2 we have
# to specifically catch it and throw the timeout error
if hasattr(err, 'errno') and err.errno in _blocking_errnos:
raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)
if hasattr(err, "errno") and err.errno in _blocking_errnos:
raise ReadTimeoutError(
self, url, "Read timed out. (read timeout=%s)" % timeout_value
)
# Catch possible read timeouts thrown as SSL errors. If not the
# case, rethrow the original. We need to do this because of:
# http://bugs.python.org/issue10272
if 'timed out' in str(err) or 'did not complete (read)' in str(err): # Python 2.6
raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)
if "timed out" in str(err) or "did not complete (read)" in str(
err
): # Python < 2.7.4
raise ReadTimeoutError(
self, url, "Read timed out. (read timeout=%s)" % timeout_value
)
def _make_request(self, conn, method, url, timeout=_Default, chunked=False,
**httplib_request_kw):
def _make_request(
self, conn, method, url, timeout=_Default, chunked=False, **httplib_request_kw
):
"""
Perform a request on a given urllib connection object taken from our
pool.
@ -349,18 +385,36 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
self._raise_timeout(err=e, url=url, timeout_value=conn.timeout)
raise
# conn.request() calls httplib.*.request, not the method in
# conn.request() calls http.client.*.request, not the method in
# urllib3.request. It also calls makefile (recv) on the socket.
if chunked:
conn.request_chunked(method, url, **httplib_request_kw)
else:
conn.request(method, url, **httplib_request_kw)
try:
if chunked:
conn.request_chunked(method, url, **httplib_request_kw)
else:
conn.request(method, url, **httplib_request_kw)
# We are swallowing BrokenPipeError (errno.EPIPE) since the server is
# legitimately able to close the connection after sending a valid response.
# With this behaviour, the received response is still readable.
except BrokenPipeError:
# Python 3
pass
except IOError as e:
# Python 2 and macOS/Linux
# EPIPE and ESHUTDOWN are BrokenPipeError on Python 2, and EPROTOTYPE is needed on macOS
# https://erickt.github.io/blog/2014/11/19/adventures-in-debugging-a-potential-osx-kernel-bug/
if e.errno not in {
errno.EPIPE,
errno.ESHUTDOWN,
errno.EPROTOTYPE,
}:
raise
# Reset the timeout for the recv() on the socket
read_timeout = timeout_obj.read_timeout
# App Engine doesn't have a sock attr
if getattr(conn, 'sock', None):
if getattr(conn, "sock", None):
# In Python 3 socket.py will catch EAGAIN and return None when you
# try and read into the file pointer created by http.client, which
# instead raises a BadStatusLine exception. Instead of catching
@ -368,7 +422,8 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# timeouts, check for a zero timeout before making the request.
if read_timeout == 0:
raise ReadTimeoutError(
self, url, "Read timed out. (read timeout=%s)" % read_timeout)
self, url, "Read timed out. (read timeout=%s)" % read_timeout
)
if read_timeout is Timeout.DEFAULT_TIMEOUT:
conn.sock.settimeout(socket.getdefaulttimeout())
else: # None or a value
@ -376,31 +431,45 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# Receive the response from the server
try:
try: # Python 2.7, use buffering of HTTP responses
try:
# Python 2.7, use buffering of HTTP responses
httplib_response = conn.getresponse(buffering=True)
except TypeError: # Python 2.6 and older, Python 3
except TypeError:
# Python 3
try:
httplib_response = conn.getresponse()
except Exception as e:
# Remove the TypeError from the exception chain in Python 3;
# otherwise it looks like a programming error was the cause.
except BaseException as e:
# Remove the TypeError from the exception chain in
# Python 3 (including for exceptions like SystemExit).
# Otherwise it looks like a bug in the code.
six.raise_from(e, None)
except (SocketTimeout, BaseSSLError, SocketError) as e:
self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
raise
# AppEngine doesn't have a version attr.
http_version = getattr(conn, '_http_vsn_str', 'HTTP/?')
log.debug("%s://%s:%s \"%s %s %s\" %s %s", self.scheme, self.host, self.port,
method, url, http_version, httplib_response.status,
httplib_response.length)
http_version = getattr(conn, "_http_vsn_str", "HTTP/?")
log.debug(
'%s://%s:%s "%s %s %s" %s %s',
self.scheme,
self.host,
self.port,
method,
url,
http_version,
httplib_response.status,
httplib_response.length,
)
try:
assert_header_parsing(httplib_response.msg)
except (HeaderParsingError, TypeError) as hpe: # Platform-specific: Python 3
log.warning(
'Failed to parse headers (url=%s): %s',
self._absolute_url(url), hpe, exc_info=True)
"Failed to parse headers (url=%s): %s",
self._absolute_url(url),
hpe,
exc_info=True,
)
return httplib_response
@ -411,6 +480,8 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
"""
Close all pooled connections and disable the pool.
"""
if self.pool is None:
return
# Disable access to the pool
old_pool, self.pool = self.pool, None
@ -428,13 +499,13 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
Check if the given ``url`` is a member of the same host as this
connection pool.
"""
if url.startswith('/'):
if url.startswith("/"):
return True
# TODO: Add optional support for socket.gethostbyname checking.
scheme, host, port = get_host(url)
host = _ipv6_host(host).lower()
if host is not None:
host = _normalize_host(host, scheme=scheme)
# Use explicit default port for comparison when none is given
if self.port and not port:
@ -444,10 +515,22 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
return (scheme, host, port) == (self.scheme, self.host, self.port)
def urlopen(self, method, url, body=None, headers=None, retries=None,
redirect=True, assert_same_host=True, timeout=_Default,
pool_timeout=None, release_conn=None, chunked=False,
body_pos=None, **response_kw):
def urlopen(
self,
method,
url,
body=None,
headers=None,
retries=None,
redirect=True,
assert_same_host=True,
timeout=_Default,
pool_timeout=None,
release_conn=None,
chunked=False,
body_pos=None,
**response_kw
):
"""
Get a connection from the pool and perform an HTTP request. This is the
lowest level call for making a request, so you'll need to specify all
@ -468,10 +551,12 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
:param method:
HTTP request method (such as GET, POST, PUT, etc.)
:param url:
The URL to perform the request on.
:param body:
Data to send in the request body (useful for creating
POST requests, see HTTPConnectionPool.post_url for
more convenience).
Data to send in the request body, either :class:`str`, :class:`bytes`,
an iterable of :class:`str`/:class:`bytes`, or a file-like object.
:param headers:
Dictionary of custom headers to send, such as User-Agent,
@ -501,7 +586,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
:param assert_same_host:
If ``True``, will make sure that the host of the pool requests is
consistent else will raise HostChangedError. When False, you can
consistent else will raise HostChangedError. When ``False``, you can
use the pool on an HTTP proxy and request foreign hosts.
:param timeout:
@ -538,6 +623,10 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
Additional parameters are passed to
:meth:`urllib3.response.HTTPResponse.from_httplib`
"""
parsed_url = parse_url(url)
destination_scheme = parsed_url.scheme
if headers is None:
headers = self.headers
@ -545,12 +634,18 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
retries = Retry.from_int(retries, redirect=redirect, default=self.retries)
if release_conn is None:
release_conn = response_kw.get('preload_content', True)
release_conn = response_kw.get("preload_content", True)
# Check host
if assert_same_host and not self.is_same_host(url):
raise HostChangedError(self, url, retries)
# Ensure that the URL we're connecting to is properly encoded
if url.startswith("/"):
url = six.ensure_str(_encode_target(url))
else:
url = six.ensure_str(parsed_url.url)
conn = None
# Track whether `conn` needs to be released before
@ -561,13 +656,17 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
#
# See issue #651 [1] for details.
#
# [1] <https://github.com/shazow/urllib3/issues/651>
# [1] <https://github.com/urllib3/urllib3/issues/651>
release_this_conn = release_conn
# Merge the proxy headers. Only do this in HTTP. We have to copy the
# headers dict so we can safely change it without those changes being
# reflected in anyone else's copy.
if self.scheme == 'http':
http_tunnel_required = connection_requires_http_tunnel(
self.proxy, self.proxy_config, destination_scheme
)
# Merge the proxy headers. Only done when not using HTTP CONNECT. We
# have to copy the headers dict so we can safely change it without those
# changes being reflected in anyone else's copy.
if not http_tunnel_required:
headers = headers.copy()
headers.update(self.proxy_headers)
@ -590,15 +689,22 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
conn.timeout = timeout_obj.connect_timeout
is_new_proxy_conn = self.proxy is not None and not getattr(conn, 'sock', None)
if is_new_proxy_conn:
is_new_proxy_conn = self.proxy is not None and not getattr(
conn, "sock", None
)
if is_new_proxy_conn and http_tunnel_required:
self._prepare_proxy(conn)
# Make the request on the httplib connection object.
httplib_response = self._make_request(conn, method, url,
timeout=timeout_obj,
body=body, headers=headers,
chunked=chunked)
httplib_response = self._make_request(
conn,
method,
url,
timeout=timeout_obj,
body=body,
headers=headers,
chunked=chunked,
)
# If we're going to release the connection in ``finally:``, then
# the response doesn't need to know about the connection. Otherwise
@ -607,36 +713,48 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
response_conn = conn if not release_conn else None
# Pass method to Response for length checking
response_kw['request_method'] = method
response_kw["request_method"] = method
# Import httplib's response into our own wrapper object
response = self.ResponseCls.from_httplib(httplib_response,
pool=self,
connection=response_conn,
retries=retries,
**response_kw)
response = self.ResponseCls.from_httplib(
httplib_response,
pool=self,
connection=response_conn,
retries=retries,
**response_kw
)
# Everything went great!
clean_exit = True
except queue.Empty:
# Timed out by queue.
raise EmptyPoolError(self, "No pool connections are available.")
except EmptyPoolError:
# Didn't get a connection from the pool, no need to clean up
clean_exit = True
release_this_conn = False
raise
except (TimeoutError, HTTPException, SocketError, ProtocolError,
BaseSSLError, SSLError, CertificateError) as e:
except (
TimeoutError,
HTTPException,
SocketError,
ProtocolError,
BaseSSLError,
SSLError,
CertificateError,
) as e:
# Discard the connection for these exceptions. It will be
# replaced during the next _get_conn() call.
clean_exit = False
if isinstance(e, (BaseSSLError, CertificateError)):
e = SSLError(e)
elif isinstance(e, (SocketError, NewConnectionError)) and self.proxy:
e = ProxyError('Cannot connect to proxy.', e)
e = ProxyError("Cannot connect to proxy.", e)
elif isinstance(e, (SocketError, HTTPException)):
e = ProtocolError('Connection aborted.', e)
e = ProtocolError("Connection aborted.", e)
retries = retries.increment(method, url, error=e, _pool=self,
_stacktrace=sys.exc_info()[2])
retries = retries.increment(
method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2]
)
retries.sleep()
# Keep track of the error for the retry warning.
@ -659,77 +777,87 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
if not conn:
# Try again
log.warning("Retrying (%r) after connection "
"broken by '%r': %s", retries, err, url)
return self.urlopen(method, url, body, headers, retries,
redirect, assert_same_host,
timeout=timeout, pool_timeout=pool_timeout,
release_conn=release_conn, body_pos=body_pos,
**response_kw)
def drain_and_release_conn(response):
try:
# discard any remaining response body, the connection will be
# released back to the pool once the entire response is read
response.read()
except (TimeoutError, HTTPException, SocketError, ProtocolError,
BaseSSLError, SSLError) as e:
pass
log.warning(
"Retrying (%r) after connection broken by '%r': %s", retries, err, url
)
return self.urlopen(
method,
url,
body,
headers,
retries,
redirect,
assert_same_host,
timeout=timeout,
pool_timeout=pool_timeout,
release_conn=release_conn,
chunked=chunked,
body_pos=body_pos,
**response_kw
)
# Handle redirect?
redirect_location = redirect and response.get_redirect_location()
if redirect_location:
if response.status == 303:
method = 'GET'
method = "GET"
try:
retries = retries.increment(method, url, response=response, _pool=self)
except MaxRetryError:
if retries.raise_on_redirect:
# Drain and release the connection for this response, since
# we're not returning it to be released manually.
drain_and_release_conn(response)
response.drain_conn()
raise
return response
# drain and return the connection to the pool before recursing
drain_and_release_conn(response)
response.drain_conn()
retries.sleep_for_retry(response)
log.debug("Redirecting %s -> %s", url, redirect_location)
return self.urlopen(
method, redirect_location, body, headers,
retries=retries, redirect=redirect,
method,
redirect_location,
body,
headers,
retries=retries,
redirect=redirect,
assert_same_host=assert_same_host,
timeout=timeout, pool_timeout=pool_timeout,
release_conn=release_conn, body_pos=body_pos,
**response_kw)
timeout=timeout,
pool_timeout=pool_timeout,
release_conn=release_conn,
chunked=chunked,
body_pos=body_pos,
**response_kw
)
# Check if we should retry the HTTP response.
has_retry_after = bool(response.getheader('Retry-After'))
has_retry_after = bool(response.getheader("Retry-After"))
if retries.is_retry(method, response.status, has_retry_after):
try:
retries = retries.increment(method, url, response=response, _pool=self)
except MaxRetryError:
if retries.raise_on_status:
# Drain and release the connection for this response, since
# we're not returning it to be released manually.
drain_and_release_conn(response)
response.drain_conn()
raise
return response
# drain and return the connection to the pool before recursing
drain_and_release_conn(response)
response.drain_conn()
retries.sleep(response)
log.debug("Retry: %s", url)
return self.urlopen(
method, url, body, headers,
retries=retries, redirect=redirect,
method,
url,
body,
headers,
retries=retries,
redirect=redirect,
assert_same_host=assert_same_host,
timeout=timeout, pool_timeout=pool_timeout,
timeout=timeout,
pool_timeout=pool_timeout,
release_conn=release_conn,
body_pos=body_pos, **response_kw)
chunked=chunked,
body_pos=body_pos,
**response_kw
)
return response
@ -738,42 +866,62 @@ class HTTPSConnectionPool(HTTPConnectionPool):
"""
Same as :class:`.HTTPConnectionPool`, but HTTPS.
When Python is compiled with the :mod:`ssl` module, then
:class:`.VerifiedHTTPSConnection` is used, which *can* verify certificates,
instead of :class:`.HTTPSConnection`.
:class:`.VerifiedHTTPSConnection` uses one of ``assert_fingerprint``,
:class:`.HTTPSConnection` uses one of ``assert_fingerprint``,
``assert_hostname`` and ``host`` in this order to verify connections.
If ``assert_hostname`` is False, no verification is done.
The ``key_file``, ``cert_file``, ``cert_reqs``, ``ca_certs``,
``ca_cert_dir``, and ``ssl_version`` are only used if :mod:`ssl` is
available and are fed into :meth:`urllib3.util.ssl_wrap_socket` to upgrade
``ca_cert_dir``, ``ssl_version``, ``key_password`` are only used if :mod:`ssl`
is available and are fed into :meth:`urllib3.util.ssl_wrap_socket` to upgrade
the connection socket into an SSL socket.
"""
scheme = 'https'
scheme = "https"
ConnectionCls = HTTPSConnection
def __init__(self, host, port=None,
strict=False, timeout=Timeout.DEFAULT_TIMEOUT, maxsize=1,
block=False, headers=None, retries=None,
_proxy=None, _proxy_headers=None,
key_file=None, cert_file=None, cert_reqs=None,
ca_certs=None, ssl_version=None,
assert_hostname=None, assert_fingerprint=None,
ca_cert_dir=None, **conn_kw):
def __init__(
self,
host,
port=None,
strict=False,
timeout=Timeout.DEFAULT_TIMEOUT,
maxsize=1,
block=False,
headers=None,
retries=None,
_proxy=None,
_proxy_headers=None,
key_file=None,
cert_file=None,
cert_reqs=None,
key_password=None,
ca_certs=None,
ssl_version=None,
assert_hostname=None,
assert_fingerprint=None,
ca_cert_dir=None,
**conn_kw
):
HTTPConnectionPool.__init__(self, host, port, strict, timeout, maxsize,
block, headers, retries, _proxy, _proxy_headers,
**conn_kw)
if ca_certs and cert_reqs is None:
cert_reqs = 'CERT_REQUIRED'
HTTPConnectionPool.__init__(
self,
host,
port,
strict,
timeout,
maxsize,
block,
headers,
retries,
_proxy,
_proxy_headers,
**conn_kw
)
self.key_file = key_file
self.cert_file = cert_file
self.cert_reqs = cert_reqs
self.key_password = key_password
self.ca_certs = ca_certs
self.ca_cert_dir = ca_cert_dir
self.ssl_version = ssl_version
@ -787,45 +935,50 @@ class HTTPSConnectionPool(HTTPConnectionPool):
"""
if isinstance(conn, VerifiedHTTPSConnection):
conn.set_cert(key_file=self.key_file,
cert_file=self.cert_file,
cert_reqs=self.cert_reqs,
ca_certs=self.ca_certs,
ca_cert_dir=self.ca_cert_dir,
assert_hostname=self.assert_hostname,
assert_fingerprint=self.assert_fingerprint)
conn.set_cert(
key_file=self.key_file,
key_password=self.key_password,
cert_file=self.cert_file,
cert_reqs=self.cert_reqs,
ca_certs=self.ca_certs,
ca_cert_dir=self.ca_cert_dir,
assert_hostname=self.assert_hostname,
assert_fingerprint=self.assert_fingerprint,
)
conn.ssl_version = self.ssl_version
return conn
def _prepare_proxy(self, conn):
"""
Establish tunnel connection early, because otherwise httplib
would improperly set Host: header to proxy's IP:port.
"""
# Python 2.7+
try:
set_tunnel = conn.set_tunnel
except AttributeError: # Platform-specific: Python 2.6
set_tunnel = conn._set_tunnel
Establishes a tunnel connection through HTTP CONNECT.
if sys.version_info <= (2, 6, 4) and not self.proxy_headers: # Python 2.6.4 and older
set_tunnel(self._proxy_host, self.port)
else:
set_tunnel(self._proxy_host, self.port, self.proxy_headers)
Tunnel connection is established early because otherwise httplib would
improperly set Host: header to proxy's IP:port.
"""
conn.set_tunnel(self._proxy_host, self.port, self.proxy_headers)
if self.proxy.scheme == "https":
conn.tls_in_tls_required = True
conn.connect()
def _new_conn(self):
"""
Return a fresh :class:`httplib.HTTPSConnection`.
Return a fresh :class:`http.client.HTTPSConnection`.
"""
self.num_connections += 1
log.debug("Starting new HTTPS connection (%d): %s",
self.num_connections, self.host)
log.debug(
"Starting new HTTPS connection (%d): %s:%s",
self.num_connections,
self.host,
self.port or "443",
)
if not self.ConnectionCls or self.ConnectionCls is DummyConnection:
raise SSLError("Can't connect to HTTPS URL because the SSL "
"module is not available.")
raise SSLError(
"Can't connect to HTTPS URL because the SSL module is not available."
)
actual_host = self.host
actual_port = self.port
@ -833,9 +986,16 @@ class HTTPSConnectionPool(HTTPConnectionPool):
actual_host = self.proxy.host
actual_port = self.proxy.port
conn = self.ConnectionCls(host=actual_host, port=actual_port,
timeout=self.timeout.connect_timeout,
strict=self.strict, **self.conn_kw)
conn = self.ConnectionCls(
host=actual_host,
port=actual_port,
timeout=self.timeout.connect_timeout,
strict=self.strict,
cert_file=self.cert_file,
key_file=self.key_file,
key_password=self.key_password,
**self.conn_kw
)
return self._prepare_conn(conn)
@ -846,16 +1006,30 @@ class HTTPSConnectionPool(HTTPConnectionPool):
super(HTTPSConnectionPool, self)._validate_conn(conn)
# Force connect early to allow us to validate the connection.
if not getattr(conn, 'sock', None): # AppEngine might not have `.sock`
if not getattr(conn, "sock", None): # AppEngine might not have `.sock`
conn.connect()
if not conn.is_verified:
warnings.warn((
'Unverified HTTPS request is being made. '
'Adding certificate verification is strongly advised. See: '
'https://urllib3.readthedocs.io/en/latest/advanced-usage.html'
'#ssl-warnings'),
InsecureRequestWarning)
warnings.warn(
(
"Unverified HTTPS request is being made to host '%s'. "
"Adding certificate verification is strongly advised. See: "
"https://urllib3.readthedocs.io/en/1.26.x/advanced-usage.html"
"#ssl-warnings" % conn.host
),
InsecureRequestWarning,
)
if getattr(conn, "proxy_is_verified", None) is False:
warnings.warn(
(
"Unverified HTTPS connection done to an HTTPS proxy. "
"Adding certificate verification is strongly advised. See: "
"https://urllib3.readthedocs.io/en/1.26.x/advanced-usage.html"
"#ssl-warnings"
),
InsecureRequestWarning,
)
def connection_from_url(url, **kw):
@ -880,26 +1054,25 @@ def connection_from_url(url, **kw):
"""
scheme, host, port = get_host(url)
port = port or port_by_scheme.get(scheme, 80)
if scheme == 'https':
if scheme == "https":
return HTTPSConnectionPool(host, port=port, **kw)
else:
return HTTPConnectionPool(host, port=port, **kw)
def _ipv6_host(host):
def _normalize_host(host, scheme):
"""
Process IPv6 address literals
Normalize hosts for comparisons and use with sockets.
"""
host = normalize_host(host, scheme)
# httplib doesn't like it when we include brackets in IPv6 addresses
# Specifically, if we include brackets but also pass the port then
# httplib crazily doubles up the square brackets on the Host header.
# Instead, we need to make sure we never pass ``None`` as the port.
# However, for backward compatibility reasons we can't actually
# *assert* that. See http://bugs.python.org/issue28539
#
# Also if an IPv6 address literal has a zone identifier, the
# percent sign might be URIencoded, convert it back into ASCII
if host.startswith('[') and host.endswith(']'):
host = host.replace('%25', '%').strip('[]')
if host.startswith("[") and host.endswith("]"):
host = host[1:-1]
return host