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

683 lines
24 KiB
Python
Raw Normal View History

2015-01-09 14:11:21 +03:00
# -*- coding: utf-8 -*-
"""
requests.session
~~~~~~~~~~~~~~~~
This module provides a Session object to manage and persist settings across
requests (cookies, auth, proxies).
"""
import os
from collections import Mapping
from datetime import datetime
from .auth import _basic_auth_str
from .compat import cookielib, OrderedDict, urljoin, urlparse
from .cookies import (
cookiejar_from_dict, extract_cookies_to_jar, RequestsCookieJar, merge_cookies)
from .models import Request, PreparedRequest, DEFAULT_REDIRECT_LIMIT
from .hooks import default_hooks, dispatch_hook
from .utils import to_key_val_list, default_headers, to_native_string
from .exceptions import (
TooManyRedirects, InvalidSchema, ChunkedEncodingError, ContentDecodingError)
from .packages.urllib3._collections import RecentlyUsedContainer
from .structures import CaseInsensitiveDict
from .adapters import HTTPAdapter
from .utils import (
requote_uri, get_environ_proxies, get_netrc_auth, should_bypass_proxies,
get_auth_from_url
)
from .status_codes import codes
# formerly defined here, reexposed here for backward compatibility
from .models import REDIRECT_STATI
REDIRECT_CACHE_SIZE = 1000
def merge_setting(request_setting, session_setting, dict_class=OrderedDict):
"""
Determines appropriate setting for a given request, taking into account the
explicit setting on that request, and the setting in the session. If a
setting is a dictionary, they will be merged together using `dict_class`
"""
if session_setting is None:
return request_setting
if request_setting is None:
return session_setting
# Bypass if not a dictionary (e.g. verify)
if not (
isinstance(session_setting, Mapping) and
isinstance(request_setting, Mapping)
):
return request_setting
merged_setting = dict_class(to_key_val_list(session_setting))
merged_setting.update(to_key_val_list(request_setting))
# Remove keys that are set to None.
for (k, v) in request_setting.items():
if v is None:
del merged_setting[k]
merged_setting = dict((k, v) for (k, v) in merged_setting.items() if v is not None)
return merged_setting
def merge_hooks(request_hooks, session_hooks, dict_class=OrderedDict):
"""
Properly merges both requests and session hooks.
This is necessary because when request_hooks == {'response': []}, the
merge breaks Session hooks entirely.
"""
if session_hooks is None or session_hooks.get('response') == []:
return request_hooks
if request_hooks is None or request_hooks.get('response') == []:
return session_hooks
return merge_setting(request_hooks, session_hooks, dict_class)
class SessionRedirectMixin(object):
def resolve_redirects(self, resp, req, stream=False, timeout=None,
verify=True, cert=None, proxies=None):
"""Receives a Response. Returns a generator of Responses."""
i = 0
hist = [] # keep track of history
while resp.is_redirect:
prepared_request = req.copy()
if i > 0:
# Update history and keep track of redirects.
hist.append(resp)
new_hist = list(hist)
resp.history = new_hist
try:
resp.content # Consume socket so it can be released
except (ChunkedEncodingError, ContentDecodingError, RuntimeError):
resp.raw.read(decode_content=False)
if i >= self.max_redirects:
raise TooManyRedirects('Exceeded %s redirects.' % self.max_redirects)
# Release the connection back into the pool.
resp.close()
url = resp.headers['location']
method = req.method
# Handle redirection without scheme (see: RFC 1808 Section 4)
if url.startswith('//'):
parsed_rurl = urlparse(resp.url)
url = '%s:%s' % (parsed_rurl.scheme, url)
# The scheme should be lower case...
parsed = urlparse(url)
url = parsed.geturl()
# Facilitate relative 'location' headers, as allowed by RFC 7231.
# (e.g. '/path/to/resource' instead of 'http://domain.tld/path/to/resource')
# Compliant with RFC3986, we percent encode the url.
if not parsed.netloc:
url = urljoin(resp.url, requote_uri(url))
else:
url = requote_uri(url)
prepared_request.url = to_native_string(url)
# Cache the url, unless it redirects to itself.
if resp.is_permanent_redirect and req.url != prepared_request.url:
self.redirect_cache[req.url] = prepared_request.url
# http://tools.ietf.org/html/rfc7231#section-6.4.4
if (resp.status_code == codes.see_other and
method != 'HEAD'):
method = 'GET'
# Do what the browsers do, despite standards...
# First, turn 302s into GETs.
if resp.status_code == codes.found and method != 'HEAD':
method = 'GET'
# Second, if a POST is responded to with a 301, turn it into a GET.
# This bizarre behaviour is explained in Issue 1704.
if resp.status_code == codes.moved and method == 'POST':
method = 'GET'
prepared_request.method = method
# https://github.com/kennethreitz/requests/issues/1084
if resp.status_code not in (codes.temporary_redirect, codes.permanent_redirect):
if 'Content-Length' in prepared_request.headers:
del prepared_request.headers['Content-Length']
prepared_request.body = None
headers = prepared_request.headers
try:
del headers['Cookie']
except KeyError:
pass
extract_cookies_to_jar(prepared_request._cookies, prepared_request, resp.raw)
prepared_request._cookies.update(self.cookies)
prepared_request.prepare_cookies(prepared_request._cookies)
# Rebuild auth and proxy information.
proxies = self.rebuild_proxies(prepared_request, proxies)
self.rebuild_auth(prepared_request, resp)
# Override the original request.
req = prepared_request
resp = self.send(
req,
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies,
allow_redirects=False,
)
extract_cookies_to_jar(self.cookies, prepared_request, resp.raw)
i += 1
yield resp
def rebuild_auth(self, prepared_request, response):
"""
When being redirected we may want to strip authentication from the
request to avoid leaking credentials. This method intelligently removes
and reapplies authentication where possible to avoid credential loss.
"""
headers = prepared_request.headers
url = prepared_request.url
if 'Authorization' in headers:
# If we get redirected to a new host, we should strip out any
# authentication headers.
original_parsed = urlparse(response.request.url)
redirect_parsed = urlparse(url)
if (original_parsed.hostname != redirect_parsed.hostname):
del headers['Authorization']
# .netrc might have more auth for us on our new host.
new_auth = get_netrc_auth(url) if self.trust_env else None
if new_auth is not None:
prepared_request.prepare_auth(new_auth)
return
def rebuild_proxies(self, prepared_request, proxies):
"""
This method re-evaluates the proxy configuration by considering the
environment variables. If we are redirected to a URL covered by
NO_PROXY, we strip the proxy configuration. Otherwise, we set missing
proxy keys for this URL (in case they were stripped by a previous
redirect).
This method also replaces the Proxy-Authorization header where
necessary.
"""
headers = prepared_request.headers
url = prepared_request.url
scheme = urlparse(url).scheme
new_proxies = proxies.copy() if proxies is not None else {}
if self.trust_env and not should_bypass_proxies(url):
environ_proxies = get_environ_proxies(url)
proxy = environ_proxies.get(scheme)
if proxy:
new_proxies.setdefault(scheme, environ_proxies[scheme])
if 'Proxy-Authorization' in headers:
del headers['Proxy-Authorization']
try:
username, password = get_auth_from_url(new_proxies[scheme])
except KeyError:
username, password = None, None
if username and password:
headers['Proxy-Authorization'] = _basic_auth_str(username, password)
return new_proxies
class Session(SessionRedirectMixin):
"""A Requests session.
Provides cookie persistence, connection-pooling, and configuration.
Basic Usage::
>>> import requests
>>> s = requests.Session()
>>> s.get('http://httpbin.org/get')
200
"""
__attrs__ = [
'headers', 'cookies', 'auth', 'proxies', 'hooks', 'params', 'verify',
'cert', 'prefetch', 'adapters', 'stream', 'trust_env',
'max_redirects',
]
def __init__(self):
#: A case-insensitive dictionary of headers to be sent on each
#: :class:`Request <Request>` sent from this
#: :class:`Session <Session>`.
self.headers = default_headers()
#: Default Authentication tuple or object to attach to
#: :class:`Request <Request>`.
self.auth = None
#: Dictionary mapping protocol to the URL of the proxy (e.g.
#: {'http': 'foo.bar:3128'}) to be used on each
#: :class:`Request <Request>`.
self.proxies = {}
#: Event-handling hooks.
self.hooks = default_hooks()
#: Dictionary of querystring data to attach to each
#: :class:`Request <Request>`. The dictionary values may be lists for
#: representing multivalued query parameters.
self.params = {}
#: Stream response content default.
self.stream = False
#: SSL Verification default.
self.verify = True
#: SSL certificate default.
self.cert = None
#: Maximum number of redirects allowed. If the request exceeds this
#: limit, a :class:`TooManyRedirects` exception is raised.
self.max_redirects = DEFAULT_REDIRECT_LIMIT
#: Should we trust the environment?
self.trust_env = True
#: A CookieJar containing all currently outstanding cookies set on this
#: session. By default it is a
#: :class:`RequestsCookieJar <requests.cookies.RequestsCookieJar>`, but
#: may be any other ``cookielib.CookieJar`` compatible object.
self.cookies = cookiejar_from_dict({})
# Default connection adapters.
self.adapters = OrderedDict()
self.mount('https://', HTTPAdapter())
self.mount('http://', HTTPAdapter())
# Only store 1000 redirects to prevent using infinite memory
self.redirect_cache = RecentlyUsedContainer(REDIRECT_CACHE_SIZE)
def __enter__(self):
return self
def __exit__(self, *args):
self.close()
def prepare_request(self, request):
"""Constructs a :class:`PreparedRequest <PreparedRequest>` for
transmission and returns it. The :class:`PreparedRequest` has settings
merged from the :class:`Request <Request>` instance and those of the
:class:`Session`.
:param request: :class:`Request` instance to prepare with this
session's settings.
"""
cookies = request.cookies or {}
# Bootstrap CookieJar.
if not isinstance(cookies, cookielib.CookieJar):
cookies = cookiejar_from_dict(cookies)
# Merge with session cookies
merged_cookies = merge_cookies(
merge_cookies(RequestsCookieJar(), self.cookies), cookies)
# Set environment's basic authentication if not explicitly set.
auth = request.auth
if self.trust_env and not auth and not self.auth:
auth = get_netrc_auth(request.url)
p = PreparedRequest()
p.prepare(
method=request.method.upper(),
url=request.url,
files=request.files,
data=request.data,
json=request.json,
headers=merge_setting(request.headers, self.headers, dict_class=CaseInsensitiveDict),
params=merge_setting(request.params, self.params),
auth=merge_setting(auth, self.auth),
cookies=merged_cookies,
hooks=merge_hooks(request.hooks, self.hooks),
)
return p
def request(self, method, url,
params=None,
data=None,
headers=None,
cookies=None,
files=None,
auth=None,
timeout=None,
allow_redirects=True,
proxies=None,
hooks=None,
stream=None,
verify=None,
cert=None,
json=None):
"""Constructs a :class:`Request <Request>`, prepares it and sends it.
Returns :class:`Response <Response>` object.
:param method: method for the new :class:`Request` object.
:param url: URL for the new :class:`Request` object.
:param params: (optional) Dictionary or bytes to be sent in the query
string for the :class:`Request`.
:param data: (optional) Dictionary or bytes to send in the body of the
:class:`Request`.
:param json: (optional) json to send in the body of the
:class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the
:class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the
:class:`Request`.
:param files: (optional) Dictionary of ``'filename': file-like-objects``
for multipart encoding upload.
:param auth: (optional) Auth tuple or callable to enable
Basic/Digest/Custom HTTP Auth.
: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 allow_redirects: (optional) Set to True by default.
:type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of
the proxy.
:param stream: (optional) whether to immediately download the response
content. Defaults to ``False``.
:param verify: (optional) if ``True``, the SSL cert will be verified.
A CA_BUNDLE path can also be provided.
:param cert: (optional) if String, path to ssl client cert file (.pem).
If Tuple, ('cert', 'key') pair.
"""
method = to_native_string(method)
# Create the Request.
req = Request(
method = method.upper(),
url = url,
headers = headers,
files = files,
data = data or {},
json = json,
params = params or {},
auth = auth,
cookies = cookies,
hooks = hooks,
)
prep = self.prepare_request(req)
proxies = proxies or {}
settings = self.merge_environment_settings(
prep.url, proxies, stream, verify, cert
)
# Send the request.
send_kwargs = {
'timeout': timeout,
'allow_redirects': allow_redirects,
}
send_kwargs.update(settings)
resp = self.send(prep, **send_kwargs)
return resp
def get(self, url, **kwargs):
"""Sends a GET request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
kwargs.setdefault('allow_redirects', True)
return self.request('GET', url, **kwargs)
def options(self, url, **kwargs):
"""Sends a OPTIONS request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
kwargs.setdefault('allow_redirects', True)
return self.request('OPTIONS', url, **kwargs)
def head(self, url, **kwargs):
"""Sends a HEAD request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
kwargs.setdefault('allow_redirects', False)
return self.request('HEAD', url, **kwargs)
def post(self, url, data=None, json=None, **kwargs):
"""Sends a POST request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param json: (optional) json to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
return self.request('POST', url, data=data, json=json, **kwargs)
def put(self, url, data=None, **kwargs):
"""Sends a PUT request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
return self.request('PUT', url, data=data, **kwargs)
def patch(self, url, data=None, **kwargs):
"""Sends a PATCH request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
return self.request('PATCH', url, data=data, **kwargs)
def delete(self, url, **kwargs):
"""Sends a DELETE request. Returns :class:`Response` object.
:param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes.
"""
return self.request('DELETE', url, **kwargs)
def send(self, request, **kwargs):
"""Send a given PreparedRequest."""
# Set defaults that the hooks can utilize to ensure they always have
# the correct parameters to reproduce the previous request.
kwargs.setdefault('stream', self.stream)
kwargs.setdefault('verify', self.verify)
kwargs.setdefault('cert', self.cert)
kwargs.setdefault('proxies', self.proxies)
# It's possible that users might accidentally send a Request object.
# Guard against that specific failure case.
if not isinstance(request, PreparedRequest):
raise ValueError('You can only send PreparedRequests.')
checked_urls = set()
while request.url in self.redirect_cache:
checked_urls.add(request.url)
new_url = self.redirect_cache.get(request.url)
if new_url in checked_urls:
break
request.url = new_url
# Set up variables needed for resolve_redirects and dispatching of hooks
allow_redirects = kwargs.pop('allow_redirects', True)
stream = kwargs.get('stream')
timeout = kwargs.get('timeout')
verify = kwargs.get('verify')
cert = kwargs.get('cert')
proxies = kwargs.get('proxies')
hooks = request.hooks
# Get the appropriate adapter to use
adapter = self.get_adapter(url=request.url)
# Start time (approximately) of the request
start = datetime.utcnow()
# Send the request
r = adapter.send(request, **kwargs)
# Total elapsed time of the request (approximately)
r.elapsed = datetime.utcnow() - start
# Response manipulation hooks
r = dispatch_hook('response', hooks, r, **kwargs)
# Persist cookies
if r.history:
# If the hooks create history then we want those cookies too
for resp in r.history:
extract_cookies_to_jar(self.cookies, resp.request, resp.raw)
extract_cookies_to_jar(self.cookies, request, r.raw)
# Redirect resolving generator.
gen = self.resolve_redirects(r, request,
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies)
# Resolve redirects if allowed.
history = [resp for resp in gen] if allow_redirects else []
# Shuffle things around if there's history.
if history:
# Insert the first (original) request at the start
history.insert(0, r)
# Get the last request made
r = history.pop()
r.history = history
if not stream:
r.content
return r
def merge_environment_settings(self, url, proxies, stream, verify, cert):
"""Check the environment and merge it with some settings."""
# Gather clues from the surrounding environment.
if self.trust_env:
# Set environment's proxies.
env_proxies = get_environ_proxies(url) or {}
for (k, v) in env_proxies.items():
proxies.setdefault(k, v)
# Look for requests environment configuration and be compatible
# with cURL.
if verify is True or verify is None:
verify = (os.environ.get('REQUESTS_CA_BUNDLE') or
os.environ.get('CURL_CA_BUNDLE'))
# Merge all the kwargs.
proxies = merge_setting(proxies, self.proxies)
stream = merge_setting(stream, self.stream)
verify = merge_setting(verify, self.verify)
cert = merge_setting(cert, self.cert)
return {'verify': verify, 'proxies': proxies, 'stream': stream,
'cert': cert}
def get_adapter(self, url):
"""Returns the appropriate connnection adapter for the given URL."""
for (prefix, adapter) in self.adapters.items():
if url.lower().startswith(prefix):
return adapter
# Nothing matches :-/
raise InvalidSchema("No connection adapters were found for '%s'" % url)
def close(self):
"""Closes all adapters and as such the session"""
for v in self.adapters.values():
v.close()
def mount(self, prefix, adapter):
"""Registers a connection adapter to a prefix.
Adapters are sorted in descending order by key length."""
self.adapters[prefix] = adapter
keys_to_move = [k for k in self.adapters if len(k) < len(prefix)]
for key in keys_to_move:
self.adapters[key] = self.adapters.pop(key)
def __getstate__(self):
state = dict((attr, getattr(self, attr, None)) for attr in self.__attrs__)
state['redirect_cache'] = dict(self.redirect_cache)
return state
def __setstate__(self, state):
redirect_cache = state.pop('redirect_cache', {})
for attr, value in state.items():
setattr(self, attr, value)
self.redirect_cache = RecentlyUsedContainer(REDIRECT_CACHE_SIZE)
for redirect, to in redirect_cache.items():
self.redirect_cache[redirect] = to
def session():
"""Returns a :class:`Session` for context-management."""
return Session()