plugin.video.torrenter/resources/scrapers/requests/adapters.py

438 lines
16 KiB
Python
Raw Normal View History

2015-01-09 14:11:21 +03:00
# -*- coding: utf-8 -*-
"""
requests.adapters
~~~~~~~~~~~~~~~~~
This module contains the transport adapters that Requests uses to define
and maintain connections.
"""
import socket
from .models import Response
from .packages.urllib3 import Retry
from .packages.urllib3.poolmanager import PoolManager, proxy_from_url
from .packages.urllib3.response import HTTPResponse
from .packages.urllib3.util import Timeout as TimeoutSauce
from .compat import urlparse, basestring
from .utils import (DEFAULT_CA_BUNDLE_PATH, get_encoding_from_headers,
prepend_scheme_if_needed, get_auth_from_url, urldefragauth)
from .structures import CaseInsensitiveDict
from .packages.urllib3.exceptions import ConnectTimeoutError
from .packages.urllib3.exceptions import HTTPError as _HTTPError
from .packages.urllib3.exceptions import MaxRetryError
from .packages.urllib3.exceptions import ProxyError as _ProxyError
from .packages.urllib3.exceptions import ProtocolError
from .packages.urllib3.exceptions import ReadTimeoutError
from .packages.urllib3.exceptions import SSLError as _SSLError
from .packages.urllib3.exceptions import ResponseError
from .cookies import extract_cookies_to_jar
from .exceptions import (ConnectionError, ConnectTimeout, ReadTimeout, SSLError,
ProxyError, RetryError)
from .auth import _basic_auth_str
DEFAULT_POOLBLOCK = False
DEFAULT_POOLSIZE = 10
DEFAULT_RETRIES = 0
class BaseAdapter(object):
"""The Base Transport Adapter"""
def __init__(self):
super(BaseAdapter, self).__init__()
def send(self):
raise NotImplementedError
def close(self):
raise NotImplementedError
class HTTPAdapter(BaseAdapter):
"""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 int 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)
"""
__attrs__ = ['max_retries', 'config', '_pool_connections', '_pool_maxsize',
'_pool_block']
def __init__(self, pool_connections=DEFAULT_POOLSIZE,
pool_maxsize=DEFAULT_POOLSIZE, max_retries=DEFAULT_RETRIES,
pool_block=DEFAULT_POOLBLOCK):
if max_retries == DEFAULT_RETRIES:
self.max_retries = Retry(0, read=False)
else:
self.max_retries = Retry.from_int(max_retries)
self.config = {}
self.proxy_manager = {}
super(HTTPAdapter, self).__init__()
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)
def __getstate__(self):
return dict((attr, getattr(self, attr, None)) for attr in
self.__attrs__)
def __setstate__(self, state):
# Can't handle by adding 'proxy_manager' to self.__attrs__ because
# because self.poolmanager uses a lambda function, which isn't pickleable.
self.proxy_manager = {}
self.config = {}
for attr, value in state.items():
setattr(self, attr, value)
self.init_poolmanager(self._pool_connections, self._pool_maxsize,
block=self._pool_block)
def init_poolmanager(self, connections, maxsize, block=DEFAULT_POOLBLOCK, **pool_kwargs):
"""Initializes a urllib3 PoolManager.
This method should not be called from user code, and is only
exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param connections: The number of urllib3 connection pools to cache.
:param maxsize: The maximum number of connections to save in the pool.
:param block: Block when no free connections are available.
:param pool_kwargs: Extra keyword arguments used to initialize the Pool Manager.
"""
# save these values for pickling
self._pool_connections = connections
self._pool_maxsize = maxsize
self._pool_block = block
self.poolmanager = PoolManager(num_pools=connections, maxsize=maxsize,
block=block, strict=True, **pool_kwargs)
def proxy_manager_for(self, proxy, **proxy_kwargs):
"""Return urllib3 ProxyManager for the given proxy.
This method should not be called from user code, and is only
exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param proxy: The proxy to return a urllib3 ProxyManager for.
:param proxy_kwargs: Extra keyword arguments used to configure the Proxy Manager.
:returns: ProxyManager
"""
if not proxy in self.proxy_manager:
proxy_headers = self.proxy_headers(proxy)
self.proxy_manager[proxy] = proxy_from_url(
proxy,
proxy_headers=proxy_headers,
num_pools=self._pool_connections,
maxsize=self._pool_maxsize,
block=self._pool_block,
**proxy_kwargs)
return self.proxy_manager[proxy]
def cert_verify(self, conn, url, verify, cert):
"""Verify a SSL certificate. This method should not be called from user
code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param conn: The urllib3 connection object associated with the cert.
:param url: The requested URL.
:param verify: Whether we should actually verify the certificate.
:param cert: The SSL certificate to verify.
"""
if url.lower().startswith('https') and verify:
cert_loc = None
# Allow self-specified cert location.
if verify is not True:
cert_loc = verify
if not cert_loc:
cert_loc = DEFAULT_CA_BUNDLE_PATH
if not cert_loc:
raise Exception("Could not find a suitable SSL CA certificate bundle.")
conn.cert_reqs = 'CERT_REQUIRED'
conn.ca_certs = cert_loc
else:
conn.cert_reqs = 'CERT_NONE'
conn.ca_certs = None
if cert:
if not isinstance(cert, basestring):
conn.cert_file = cert[0]
conn.key_file = cert[1]
else:
conn.cert_file = cert
def build_response(self, req, resp):
"""Builds a :class:`Response <requests.Response>` object from a urllib3
response. This should not be called from user code, and is only exposed
for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`
:param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response.
:param resp: The urllib3 response object.
"""
response = Response()
# Fallback to None if there's no status_code, for whatever reason.
response.status_code = getattr(resp, 'status', None)
# Make headers case-insensitive.
response.headers = CaseInsensitiveDict(getattr(resp, 'headers', {}))
# Set encoding.
response.encoding = get_encoding_from_headers(response.headers)
response.raw = resp
response.reason = response.raw.reason
if isinstance(req.url, bytes):
response.url = req.url.decode('utf-8')
else:
response.url = req.url
# Add new cookies from the server.
extract_cookies_to_jar(response.cookies, req, resp)
# Give the Response some context.
response.request = req
response.connection = self
return response
def get_connection(self, url, proxies=None):
"""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.
"""
proxies = proxies or {}
proxy = proxies.get(urlparse(url.lower()).scheme)
if proxy:
proxy = prepend_scheme_if_needed(proxy, 'http')
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)
return conn
def close(self):
"""Disposes of any internal state.
Currently, this just closes the PoolManager, which closes pooled
connections.
"""
self.poolmanager.clear()
def request_url(self, request, proxies):
"""Obtain the url to use when making the final request.
If the message is being sent through a HTTP proxy, the full URL has to
be used. Otherwise, we should only use the path portion of the URL.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param proxies: A dictionary of schemes to proxy URLs.
"""
proxies = proxies or {}
scheme = urlparse(request.url).scheme
proxy = proxies.get(scheme)
if proxy and scheme != 'https':
url = urldefragauth(request.url)
else:
url = request.path_url
return url
def add_headers(self, request, **kwargs):
"""Add any headers needed by the connection. As of v2.0 this does
nothing by default, but is left for overriding by users that subclass
the :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request: The :class:`PreparedRequest <PreparedRequest>` to add headers to.
:param kwargs: The keyword arguments from the call to send().
"""
pass
def proxy_headers(self, proxy):
"""Returns a dictionary of the headers to add to any request sent
through a proxy. This works with urllib3 magic to ensure that they are
correctly sent to the proxy, rather than in a tunnelled request if
CONNECT is being used.
This should not be called from user code, and is only exposed for use
when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param proxies: The url of the proxy being used for this request.
:param kwargs: Optional additional keyword arguments.
"""
headers = {}
username, password = get_auth_from_url(proxy)
if username and password:
headers['Proxy-Authorization'] = _basic_auth_str(username,
password)
return headers
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 (`connect timeout, read
timeout <user/advanced.html#timeouts>`_) tuple.
:type timeout: float or tuple
:param verify: (optional) Whether to verify SSL certificates.
:param cert: (optional) Any user-provided SSL certificate to be trusted.
:param proxies: (optional) The proxies dictionary to apply to the request.
"""
conn = self.get_connection(request.url, proxies)
self.cert_verify(conn, request.url, verify, cert)
url = self.request_url(request, proxies)
self.add_headers(request)
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 as e:
# this may raise a string formatting error.
err = ("Invalid timeout {0}. Pass a (connect, read) "
"timeout tuple, or a single float to set "
"both timeouts to the same value".format(timeout))
raise ValueError(err)
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=timeout)
try:
low_conn.putrequest(request.method,
url,
skip_accept_encoding=True)
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')
r = low_conn.getresponse()
resp = HTTPResponse.from_httplib(
r,
pool=conn,
connection=low_conn,
preload_content=False,
decode_content=False
)
except:
# If we hit any problems here, clean up the connection.
# Then, reraise so that we can handle the actual exception.
low_conn.close()
raise
else:
# All is well, return the connection to the pool.
conn._put_conn(low_conn)
except (ProtocolError, socket.error) as err:
raise ConnectionError(err, request=request)
except MaxRetryError as e:
if isinstance(e.reason, ConnectTimeoutError):
raise ConnectTimeout(e, request=request)
if isinstance(e.reason, ResponseError):
raise RetryError(e, request=request)
raise ConnectionError(e, request=request)
except _ProxyError as e:
raise ProxyError(e)
except (_SSLError, _HTTPError) as e:
if isinstance(e, _SSLError):
raise SSLError(e, request=request)
elif isinstance(e, ReadTimeoutError):
raise ReadTimeout(e, request=request)
else:
raise
return self.build_response(request, resp)