Updated requests library to 2.4.1. Should fix #1915

This commit is contained in:
Bas Stottelaar
2014-09-25 13:58:06 +02:00
parent 574a76c231
commit 371401fa36
43 changed files with 2154 additions and 1417 deletions
+162 -56
View File
@@ -12,27 +12,28 @@ import os
from collections import Mapping
from datetime import datetime
from .auth import _basic_auth_str
from .compat import cookielib, OrderedDict, urljoin, urlparse, builtin_str
from .cookies import (
cookiejar_from_dict, extract_cookies_to_jar, RequestsCookieJar, merge_cookies)
from .models import Request, PreparedRequest
from .models import Request, PreparedRequest, DEFAULT_REDIRECT_LIMIT
from .hooks import default_hooks, dispatch_hook
from .utils import to_key_val_list, default_headers
from .exceptions import TooManyRedirects, InvalidSchema
from .utils import to_key_val_list, default_headers, to_native_string
from .exceptions import (
TooManyRedirects, InvalidSchema, ChunkedEncodingError, ContentDecodingError)
from .structures import CaseInsensitiveDict
from .adapters import HTTPAdapter
from .utils import requote_uri, get_environ_proxies, get_netrc_auth
from .utils import (
requote_uri, get_environ_proxies, get_netrc_auth, should_bypass_proxies,
get_auth_from_url
)
from .status_codes import codes
REDIRECT_STATI = (
codes.moved, # 301
codes.found, # 302
codes.other, # 303
codes.temporary_moved, # 307
)
DEFAULT_REDIRECT_LIMIT = 30
# formerly defined here, reexposed here for backward compatibility
from .models import REDIRECT_STATI
def merge_setting(request_setting, session_setting, dict_class=OrderedDict):
@@ -63,6 +64,8 @@ def merge_setting(request_setting, session_setting, dict_class=OrderedDict):
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
@@ -88,12 +91,21 @@ class SessionRedirectMixin(object):
"""Receives a Response. Returns a generator of Responses."""
i = 0
hist = [] # keep track of history
# ((resp.status_code is codes.see_other))
while ('location' in resp.headers and resp.status_code in REDIRECT_STATI):
while resp.is_redirect:
prepared_request = req.copy()
resp.content # Consume socket so it can be released
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)
@@ -113,7 +125,7 @@ class SessionRedirectMixin(object):
parsed = urlparse(url)
url = parsed.geturl()
# Facilitate non-RFC2616-compliant 'location' headers
# 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 urlparse(url).netloc:
@@ -121,9 +133,12 @@ class SessionRedirectMixin(object):
else:
url = requote_uri(url)
prepared_request.url = 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://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.3.4
# http://tools.ietf.org/html/rfc7231#section-6.4.4
if (resp.status_code == codes.see_other and
method != 'HEAD'):
method = 'GET'
@@ -141,7 +156,7 @@ class SessionRedirectMixin(object):
prepared_request.method = method
# https://github.com/kennethreitz/requests/issues/1084
if resp.status_code not in (codes.temporary, codes.resume):
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']
@@ -153,13 +168,19 @@ class SessionRedirectMixin(object):
except KeyError:
pass
extract_cookies_to_jar(prepared_request._cookies,
prepared_request, resp.raw)
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(
prepared_request,
req,
stream=stream,
timeout=timeout,
verify=verify,
@@ -173,6 +194,68 @@ class SessionRedirectMixin(object):
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.
@@ -190,7 +273,7 @@ class Session(SessionRedirectMixin):
__attrs__ = [
'headers', 'cookies', 'auth', 'timeout', 'proxies', 'hooks',
'params', 'verify', 'cert', 'prefetch', 'adapters', 'stream',
'trust_env', 'max_redirects']
'trust_env', 'max_redirects', 'redirect_cache']
def __init__(self):
@@ -243,6 +326,8 @@ class Session(SessionRedirectMixin):
self.mount('https://', HTTPAdapter())
self.mount('http://', HTTPAdapter())
self.redirect_cache = {}
def __enter__(self):
return self
@@ -315,13 +400,16 @@ class Session(SessionRedirectMixin):
:class:`Request`.
:param cookies: (optional) Dict or CookieJar object to send with the
:class:`Request`.
:param files: (optional) Dictionary of 'filename': file-like-objects
: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) Float describing the timeout of the
request.
:param allow_redirects: (optional) Boolean. Set to True by default.
: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
@@ -350,36 +438,16 @@ class Session(SessionRedirectMixin):
proxies = proxies or {}
# 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 configuration.
if not verify and verify is not False:
verify = os.environ.get('REQUESTS_CA_BUNDLE')
# Curl compatibility.
if not verify and verify is not False:
verify = 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)
settings = self.merge_environment_settings(
prep.url, proxies, stream, verify, cert
)
# Send the request.
send_kwargs = {
'stream': stream,
'timeout': timeout,
'verify': verify,
'cert': cert,
'proxies': proxies,
'allow_redirects': allow_redirects,
}
send_kwargs.update(settings)
resp = self.send(prep, **send_kwargs)
return resp
@@ -467,8 +535,10 @@ class Session(SessionRedirectMixin):
if not isinstance(request, PreparedRequest):
raise ValueError('You can only send PreparedRequests.')
# Set up variables needed for resolve_redirects and dispatching of
# hooks
while request.url in self.redirect_cache:
request.url = self.redirect_cache.get(request.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')
@@ -482,8 +552,10 @@ class Session(SessionRedirectMixin):
# 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
@@ -492,15 +564,20 @@ class Session(SessionRedirectMixin):
# 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)
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 []
@@ -511,10 +588,37 @@ class Session(SessionRedirectMixin):
history.insert(0, r)
# Get the last request made
r = history.pop()
r.history = tuple(history)
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():
@@ -534,8 +638,10 @@ class Session(SessionRedirectMixin):
"""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)