exclude_badExits/https_adapter.py
2022-11-09 09:30:43 +00:00

331 lines
12 KiB
Python

# -*- mode: python; indent-tabs-mode: nil; py-indent-offset: 4; coding: utf-8 -*-
from requests import adapters
from requests.utils import (
DEFAULT_CA_BUNDLE_PATH,
get_auth_from_url,
get_encoding_from_headers,
prepend_scheme_if_needed,
select_proxy,
urldefragauth,
)
from urllib3.util import parse_url
from urllib3.util.retry import Retry
from urllib3.util import Timeout as TimeoutSauce
DEFAULT_POOLBLOCK = False
DEFAULT_POOLSIZE = 10
DEFAULT_RETRIES = 0
DEFAULT_POOL_TIMEOUT = None
class HTTPAdapter(adapters.HTTPAdapter):
def __init__(self,
pool_connections=DEFAULT_POOLSIZE,
pool_maxsize=DEFAULT_POOLSIZE,
max_retries=DEFAULT_RETRIES,
pool_block=DEFAULT_POOLBLOCK
):
self.config = {}
self.proxy_manager = {}
if isinstance(max_retries, Retry):
self.max_retries = max_retries
else:
max_retries = Retry.from_int(max_retries)
self.max_retries = max_retries
self._pool_connections = pool_connections
self._pool_maxsize = pool_maxsize
self._pool_block = pool_block
self.init_poolmanager(pool_connections, pool_maxsize, block=pool_block)
class HTTPSAdapter(HTTPAdapter):
"""The built-in HTTP Adapter for urllib3.
Provides a general-case interface for Requests sessions to contact HTTP and
HTTPS urls by implementing the Transport Adapter interface. This class will
usually be created by the :class:`Session <Session>` class under the
covers.
:param pool_connections: The number of urllib3 connection pools to cache.
:param pool_maxsize: The maximum number of connections to save in the pool.
:param max_retries: The maximum number of retries each connection
should attempt. Note, this applies only to failed DNS lookups, socket
connections and connection timeouts, never to requests where data has
made it to the server. By default, Requests does not retry failed
connections. If you need granular control over the conditions under
which we retry a request, import urllib3's ``Retry`` class and pass
that instead.
:param pool_block: Whether the connection pool should block for connections.
Usage::
>>> import requests
>>> s = requests.Session()
>>> a = requests.adapters.HTTPAdapter(max_retries=3)
>>> s.mount('http://', a)
"""
def __init__(
self,
pool_connections=DEFAULT_POOLSIZE,
pool_maxsize=1,
max_retries=3,
pool_block=DEFAULT_POOLBLOCK,
):
retries = Retry(connect=max_retries, read=2, redirect=0)
adapters.HTTPAdapter.__init__(self,
pool_connections=pool_connections,
pool_maxsize=pool_maxsize,
max_retries=retries,
pool_block=pool_block)
def get_connection(self, url, proxies=None, use_forwarding_for_https=True):
"""Returns a urllib3 connection for the given URL. This should not be
called from user code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param url: The URL to connect to.
:param proxies: (optional) A Requests-style dictionary of proxies used on this request.
:rtype: urllib3.ConnectionPool
"""
proxy = select_proxy(url, proxies)
if proxy:
proxy = prepend_scheme_if_needed(proxy, "http")
proxy_url = parse_url(proxy)
if not proxy_url.host:
raise InvalidProxyURL(
"Please check proxy URL. It is malformed "
"and could be missing the host."
)
proxy_manager = self.proxy_manager_for(proxy)
conn = proxy_manager.connection_from_url(url)
else:
# Only scheme should be lower case
parsed = urlparse(url)
url = parsed.geturl()
conn = self.poolmanager.connection_from_url(url, use_forwarding_for_https=True)
return conn
def send(
self, request, stream=False, timeout=None, verify=True, cert=None, proxies=None
):
"""Sends PreparedRequest object. Returns Response object.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param stream: (optional) Whether to stream the request content.
:param timeout: (optional) How long to wait for the server to send
data before giving up, as a float, or a :ref:`(connect timeout,
read timeout) <timeouts>` tuple.
:type timeout: float or tuple or urllib3 Timeout object
:param verify: (optional) Either a boolean, in which case it controls whether
we verify the server's TLS certificate, or a string, in which case it
must be a path to a CA bundle to use
:param cert: (optional) Any user-provided SSL certificate to be trusted.
:param proxies: (optional) The proxies dictionary to apply to the request.
:rtype: requests.Response
"""
try:
#? _socks_options
conn = self.get_connection(request.url, proxies, use_forwarding_for_https=True)
except LocationValueError as e:
raise InvalidURL(e, request=request)
self.cert_verify(conn, request.url, verify, cert)
url = self.request_url(request, proxies)
self.add_headers(
request,
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies,
)
chunked = not (request.body is None or "Content-Length" in request.headers)
if isinstance(timeout, tuple):
try:
connect, read = timeout
timeout = TimeoutSauce(connect=connect, read=read)
except ValueError:
raise ValueError(
f"Invalid timeout {timeout}. Pass a (connect, read) timeout tuple, "
f"or a single float to set both timeouts to the same value."
)
elif isinstance(timeout, TimeoutSauce):
pass
else:
timeout = TimeoutSauce(connect=timeout, read=timeout)
try:
if not chunked:
resp = conn.urlopen(
method=request.method,
url=url,
body=request.body,
headers=request.headers,
redirect=False,
assert_same_host=False,
preload_content=False,
decode_content=False,
retries=self.max_retries,
timeout=timeout,
)
# Send the request.
else:
if hasattr(conn, "proxy_pool"):
conn = conn.proxy_pool
low_conn = conn._get_conn(timeout=DEFAULT_POOL_TIMEOUT)
try:
skip_host = "Host" in request.headers
low_conn.putrequest(
request.method,
url,
skip_accept_encoding=True,
skip_host=skip_host,
)
for header, value in request.headers.items():
low_conn.putheader(header, value)
low_conn.endheaders()
for i in request.body:
low_conn.send(hex(len(i))[2:].encode("utf-8"))
low_conn.send(b"\r\n")
low_conn.send(i)
low_conn.send(b"\r\n")
low_conn.send(b"0\r\n\r\n")
# Receive the response from the server
r = low_conn.getresponse()
resp = HTTPResponse.from_httplib(
r,
pool=conn,
connection=low_conn,
preload_content=False,
decode_content=False,
)
except Exception:
# If we hit any problems here, clean up the connection.
# Then, raise so that we can handle the actual exception.
low_conn.close()
raise
except (ProtocolError, OSError) as err:
raise ConnectionError(err, request=request)
except MaxRetryError as e:
if isinstance(e.reason, ConnectTimeoutError):
# TODO: Remove this in 3.0.0: see #2811
if not isinstance(e.reason, NewConnectionError):
raise ConnectTimeout(e, request=request)
if isinstance(e.reason, ResponseError):
raise RetryError(e, request=request)
if isinstance(e.reason, _ProxyError):
raise ProxyError(e, request=request)
if isinstance(e.reason, _SSLError):
# This branch is for urllib3 v1.22 and later.
raise SSLError(e, request=request)
raise ConnectionError(e, request=request)
except ClosedPoolError as e:
raise ConnectionError(e, request=request)
except _ProxyError as e:
raise ProxyError(e)
except (_SSLError, _HTTPError) as e:
if isinstance(e, _SSLError):
# This branch is for urllib3 versions earlier than v1.22
raise SSLError(e, request=request)
elif isinstance(e, ReadTimeoutError):
raise ReadTimeout(e, request=request)
elif isinstance(e, _InvalidHeader):
raise InvalidHeader(e, request=request)
else:
raise
return self.build_response(request, resp)
from urllib3.util.ssl_match_hostname import match_hostname as _match_hostname
def match_hostname(cert, hostname):
"""Verify that *cert* (in decoded format as returned by
SSLSocket.getpeercert()) matches the *hostname*. RFC 2818 and RFC 6125
rules are followed, but IP addresses are not accepted for *hostname*.
CertificateError is raised on failure. On success, the function
returns nothing.
"""
if not cert:
raise ValueError(
"empty or no certificate, match_hostname needs a "
"SSL socket or SSL context with either "
"CERT_OPTIONAL or CERT_REQUIRED"
)
try:
# Divergence from upstream: ipaddress can't handle byte str
host_ip = ipaddress.ip_address(_to_unicode(hostname))
except (UnicodeError, ValueError):
# ValueError: Not an IP address (common case)
# UnicodeError: Divergence from upstream: Have to deal with ipaddress not taking
# byte strings. addresses should be all ascii, so we consider it not
# an ipaddress in this case
host_ip = None
except AttributeError:
# Divergence from upstream: Make ipaddress library optional
if ipaddress is None:
host_ip = None
else: # Defensive
raise
dnsnames = []
san = cert.get("subjectAltName", ())
for key, value in san:
if key == "DNS":
if host_ip is None and _dnsname_match(value, hostname):
return
dnsnames.append(value)
elif key == "IP Address":
if host_ip is not None and _ipaddress_match(value, host_ip):
return
dnsnames.append(value)
if not dnsnames:
# The subject is only checked when there is no dNSName entry
# in subjectAltName
for sub in cert.get("subject", ()):
for key, value in sub:
# XXX according to RFC 2818, the most specific Common Name
# must be used.
if key == "commonName":
if _dnsname_match(value, hostname):
return
dnsnames.append(value)
if len(dnsnames) > 1:
# soften this to allow subdomain matching
raise CertificateError(
"hostname %r "
"doesn't match any of %s" % (hostname, ", ".join(map(repr, dnsnames)))
)
elif len(dnsnames) == 1:
raise CertificateError("hostname %r doesn't match %r" % (hostname, dnsnames[0]))
else:
raise CertificateError(
"no appropriate commonName or subjectAltName fields were found"
)
from urllib3.util.ssl_match_hostname = match_hostname