Update requests package to 2.10.0

This commit is contained in:
JonnyWong16 2016-05-02 23:26:10 -07:00
parent 7be651f5cf
commit 4043398e01
41 changed files with 3585 additions and 1534 deletions

View file

@ -6,7 +6,7 @@
# / # /
""" """
requests HTTP library Requests HTTP library
~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~
Requests is an HTTP library, written in Python, for human beings. Basic GET Requests is an HTTP library, written in Python, for human beings. Basic GET
@ -36,17 +36,17 @@ usage:
The other HTTP methods are supported - see `requests.api`. Full documentation The other HTTP methods are supported - see `requests.api`. Full documentation
is at <http://python-requests.org>. is at <http://python-requests.org>.
:copyright: (c) 2014 by Kenneth Reitz. :copyright: (c) 2016 by Kenneth Reitz.
:license: Apache 2.0, see LICENSE for more details. :license: Apache 2.0, see LICENSE for more details.
""" """
__title__ = 'requests' __title__ = 'requests'
__version__ = '2.5.1' __version__ = '2.10.0'
__build__ = 0x020501 __build__ = 0x021000
__author__ = 'Kenneth Reitz' __author__ = 'Kenneth Reitz'
__license__ = 'Apache 2.0' __license__ = 'Apache 2.0'
__copyright__ = 'Copyright 2014 Kenneth Reitz' __copyright__ = 'Copyright 2016 Kenneth Reitz'
# Attempt to enable urllib3's SNI support, if possible # Attempt to enable urllib3's SNI support, if possible
try: try:
@ -55,6 +55,12 @@ try:
except ImportError: except ImportError:
pass pass
import warnings
# urllib3's DependencyWarnings should be silenced.
from .packages.urllib3.exceptions import DependencyWarning
warnings.simplefilter('ignore', DependencyWarning)
from . import utils from . import utils
from .models import Request, Response, PreparedRequest from .models import Request, Response, PreparedRequest
from .api import request, get, head, post, patch, put, delete, options from .api import request, get, head, post, patch, put, delete, options
@ -62,7 +68,8 @@ from .sessions import session, Session
from .status_codes import codes from .status_codes import codes
from .exceptions import ( from .exceptions import (
RequestException, Timeout, URLRequired, RequestException, Timeout, URLRequired,
TooManyRedirects, HTTPError, ConnectionError TooManyRedirects, HTTPError, ConnectionError,
FileModeWarning, ConnectTimeout, ReadTimeout
) )
# Set default logging handler to avoid "No handler found" warnings. # Set default logging handler to avoid "No handler found" warnings.
@ -75,3 +82,8 @@ except ImportError:
pass pass
logging.getLogger(__name__).addHandler(NullHandler()) logging.getLogger(__name__).addHandler(NullHandler())
import warnings
# FileModeWarnings go off per the default.
warnings.simplefilter('default', FileModeWarning, append=True)

View file

@ -8,20 +8,24 @@ This module contains the transport adapters that Requests uses to define
and maintain connections. and maintain connections.
""" """
import os.path
import socket import socket
from .models import Response from .models import Response
from .packages.urllib3 import Retry
from .packages.urllib3.poolmanager import PoolManager, proxy_from_url from .packages.urllib3.poolmanager import PoolManager, proxy_from_url
from .packages.urllib3.response import HTTPResponse from .packages.urllib3.response import HTTPResponse
from .packages.urllib3.util import Timeout as TimeoutSauce from .packages.urllib3.util import Timeout as TimeoutSauce
from .packages.urllib3.util.retry import Retry
from .compat import urlparse, basestring from .compat import urlparse, basestring
from .utils import (DEFAULT_CA_BUNDLE_PATH, get_encoding_from_headers, from .utils import (DEFAULT_CA_BUNDLE_PATH, get_encoding_from_headers,
prepend_scheme_if_needed, get_auth_from_url, urldefragauth) prepend_scheme_if_needed, get_auth_from_url, urldefragauth,
select_proxy, to_native_string)
from .structures import CaseInsensitiveDict from .structures import CaseInsensitiveDict
from .packages.urllib3.exceptions import ClosedPoolError
from .packages.urllib3.exceptions import ConnectTimeoutError from .packages.urllib3.exceptions import ConnectTimeoutError
from .packages.urllib3.exceptions import HTTPError as _HTTPError from .packages.urllib3.exceptions import HTTPError as _HTTPError
from .packages.urllib3.exceptions import MaxRetryError from .packages.urllib3.exceptions import MaxRetryError
from .packages.urllib3.exceptions import NewConnectionError
from .packages.urllib3.exceptions import ProxyError as _ProxyError from .packages.urllib3.exceptions import ProxyError as _ProxyError
from .packages.urllib3.exceptions import ProtocolError from .packages.urllib3.exceptions import ProtocolError
from .packages.urllib3.exceptions import ReadTimeoutError from .packages.urllib3.exceptions import ReadTimeoutError
@ -29,12 +33,19 @@ from .packages.urllib3.exceptions import SSLError as _SSLError
from .packages.urllib3.exceptions import ResponseError from .packages.urllib3.exceptions import ResponseError
from .cookies import extract_cookies_to_jar from .cookies import extract_cookies_to_jar
from .exceptions import (ConnectionError, ConnectTimeout, ReadTimeout, SSLError, from .exceptions import (ConnectionError, ConnectTimeout, ReadTimeout, SSLError,
ProxyError, RetryError) ProxyError, RetryError, InvalidSchema)
from .auth import _basic_auth_str from .auth import _basic_auth_str
try:
from .packages.urllib3.contrib.socks import SOCKSProxyManager
except ImportError:
def SOCKSProxyManager(*args, **kwargs):
raise InvalidSchema("Missing dependencies for SOCKS support.")
DEFAULT_POOLBLOCK = False DEFAULT_POOLBLOCK = False
DEFAULT_POOLSIZE = 10 DEFAULT_POOLSIZE = 10
DEFAULT_RETRIES = 0 DEFAULT_RETRIES = 0
DEFAULT_POOL_TIMEOUT = None
class BaseAdapter(object): class BaseAdapter(object):
@ -60,7 +71,7 @@ class HTTPAdapter(BaseAdapter):
:param pool_connections: The number of urllib3 connection pools to cache. :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 pool_maxsize: The maximum number of connections to save in the pool.
:param int max_retries: The maximum number of retries each connection :param max_retries: The maximum number of retries each connection
should attempt. Note, this applies only to failed DNS lookups, socket should attempt. Note, this applies only to failed DNS lookups, socket
connections and connection timeouts, never to requests where data has connections and connection timeouts, never to requests where data has
made it to the server. By default, Requests does not retry failed made it to the server. By default, Requests does not retry failed
@ -103,7 +114,7 @@ class HTTPAdapter(BaseAdapter):
def __setstate__(self, state): def __setstate__(self, state):
# Can't handle by adding 'proxy_manager' to self.__attrs__ because # Can't handle by adding 'proxy_manager' to self.__attrs__ because
# because self.poolmanager uses a lambda function, which isn't pickleable. # self.poolmanager uses a lambda function, which isn't pickleable.
self.proxy_manager = {} self.proxy_manager = {}
self.config = {} self.config = {}
@ -144,9 +155,22 @@ class HTTPAdapter(BaseAdapter):
:param proxy_kwargs: Extra keyword arguments used to configure the Proxy Manager. :param proxy_kwargs: Extra keyword arguments used to configure the Proxy Manager.
:returns: ProxyManager :returns: ProxyManager
""" """
if not proxy in self.proxy_manager: if proxy in self.proxy_manager:
manager = self.proxy_manager[proxy]
elif proxy.lower().startswith('socks'):
username, password = get_auth_from_url(proxy)
manager = self.proxy_manager[proxy] = SOCKSProxyManager(
proxy,
username=username,
password=password,
num_pools=self._pool_connections,
maxsize=self._pool_maxsize,
block=self._pool_block,
**proxy_kwargs
)
else:
proxy_headers = self.proxy_headers(proxy) proxy_headers = self.proxy_headers(proxy)
self.proxy_manager[proxy] = proxy_from_url( manager = self.proxy_manager[proxy] = proxy_from_url(
proxy, proxy,
proxy_headers=proxy_headers, proxy_headers=proxy_headers,
num_pools=self._pool_connections, num_pools=self._pool_connections,
@ -154,7 +178,7 @@ class HTTPAdapter(BaseAdapter):
block=self._pool_block, block=self._pool_block,
**proxy_kwargs) **proxy_kwargs)
return self.proxy_manager[proxy] return manager
def cert_verify(self, conn, url, verify, cert): def cert_verify(self, conn, url, verify, cert):
"""Verify a SSL certificate. This method should not be called from user """Verify a SSL certificate. This method should not be called from user
@ -181,10 +205,15 @@ class HTTPAdapter(BaseAdapter):
raise Exception("Could not find a suitable SSL CA certificate bundle.") raise Exception("Could not find a suitable SSL CA certificate bundle.")
conn.cert_reqs = 'CERT_REQUIRED' conn.cert_reqs = 'CERT_REQUIRED'
conn.ca_certs = cert_loc
if not os.path.isdir(cert_loc):
conn.ca_certs = cert_loc
else:
conn.ca_cert_dir = cert_loc
else: else:
conn.cert_reqs = 'CERT_NONE' conn.cert_reqs = 'CERT_NONE'
conn.ca_certs = None conn.ca_certs = None
conn.ca_cert_dir = None
if cert: if cert:
if not isinstance(cert, basestring): if not isinstance(cert, basestring):
@ -237,8 +266,7 @@ class HTTPAdapter(BaseAdapter):
:param url: The URL to connect to. :param url: The URL to connect to.
:param proxies: (optional) A Requests-style dictionary of proxies used on this request. :param proxies: (optional) A Requests-style dictionary of proxies used on this request.
""" """
proxies = proxies or {} proxy = select_proxy(url, proxies)
proxy = proxies.get(urlparse(url.lower()).scheme)
if proxy: if proxy:
proxy = prepend_scheme_if_needed(proxy, 'http') proxy = prepend_scheme_if_needed(proxy, 'http')
@ -255,10 +283,12 @@ class HTTPAdapter(BaseAdapter):
def close(self): def close(self):
"""Disposes of any internal state. """Disposes of any internal state.
Currently, this just closes the PoolManager, which closes pooled Currently, this closes the PoolManager and any active ProxyManager,
connections. which closes any pooled connections.
""" """
self.poolmanager.clear() self.poolmanager.clear()
for proxy in self.proxy_manager.values():
proxy.clear()
def request_url(self, request, proxies): def request_url(self, request, proxies):
"""Obtain the url to use when making the final request. """Obtain the url to use when making the final request.
@ -271,16 +301,20 @@ class HTTPAdapter(BaseAdapter):
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`. :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent. :param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param proxies: A dictionary of schemes to proxy URLs. :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs.
""" """
proxies = proxies or {} proxy = select_proxy(request.url, proxies)
scheme = urlparse(request.url).scheme scheme = urlparse(request.url).scheme
proxy = proxies.get(scheme)
if proxy and scheme != 'https': is_proxied_http_request = (proxy and scheme != 'https')
using_socks_proxy = False
if proxy:
proxy_scheme = urlparse(proxy).scheme.lower()
using_socks_proxy = proxy_scheme.startswith('socks')
url = request.path_url
if is_proxied_http_request and not using_socks_proxy:
url = urldefragauth(request.url) url = urldefragauth(request.url)
else:
url = request.path_url
return url return url
@ -309,7 +343,6 @@ class HTTPAdapter(BaseAdapter):
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`. :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param proxies: The url of the proxy being used for this request. :param proxies: The url of the proxy being used for this request.
:param kwargs: Optional additional keyword arguments.
""" """
headers = {} headers = {}
username, password = get_auth_from_url(proxy) username, password = get_auth_from_url(proxy)
@ -326,8 +359,8 @@ class HTTPAdapter(BaseAdapter):
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent. :param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
:param stream: (optional) Whether to stream the request content. :param stream: (optional) Whether to stream the request content.
:param timeout: (optional) How long to wait for the server to send :param timeout: (optional) How long to wait for the server to send
data before giving up, as a float, or a (`connect timeout, read data before giving up, as a float, or a :ref:`(connect timeout,
timeout <user/advanced.html#timeouts>`_) tuple. read timeout) <timeouts>` tuple.
:type timeout: float or tuple :type timeout: float or tuple
:param verify: (optional) Whether to verify SSL certificates. :param verify: (optional) Whether to verify SSL certificates.
:param cert: (optional) Any user-provided SSL certificate to be trusted. :param cert: (optional) Any user-provided SSL certificate to be trusted.
@ -375,7 +408,7 @@ class HTTPAdapter(BaseAdapter):
if hasattr(conn, 'proxy_pool'): if hasattr(conn, 'proxy_pool'):
conn = conn.proxy_pool conn = conn.proxy_pool
low_conn = conn._get_conn(timeout=timeout) low_conn = conn._get_conn(timeout=DEFAULT_POOL_TIMEOUT)
try: try:
low_conn.putrequest(request.method, low_conn.putrequest(request.method,
@ -394,7 +427,15 @@ class HTTPAdapter(BaseAdapter):
low_conn.send(b'\r\n') low_conn.send(b'\r\n')
low_conn.send(b'0\r\n\r\n') low_conn.send(b'0\r\n\r\n')
r = low_conn.getresponse() # Receive the response from the server
try:
# For Python 2.7+ versions, use buffering of HTTP
# responses
r = low_conn.getresponse(buffering=True)
except TypeError:
# For compatibility with Python 2.6 versions and back
r = low_conn.getresponse()
resp = HTTPResponse.from_httplib( resp = HTTPResponse.from_httplib(
r, r,
pool=conn, pool=conn,
@ -407,20 +448,25 @@ class HTTPAdapter(BaseAdapter):
# Then, reraise so that we can handle the actual exception. # Then, reraise so that we can handle the actual exception.
low_conn.close() low_conn.close()
raise raise
else:
# All is well, return the connection to the pool.
conn._put_conn(low_conn)
except (ProtocolError, socket.error) as err: except (ProtocolError, socket.error) as err:
raise ConnectionError(err, request=request) raise ConnectionError(err, request=request)
except MaxRetryError as e: except MaxRetryError as e:
if isinstance(e.reason, ConnectTimeoutError): if isinstance(e.reason, ConnectTimeoutError):
raise ConnectTimeout(e, request=request) # 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): if isinstance(e.reason, ResponseError):
raise RetryError(e, request=request) raise RetryError(e, request=request)
if isinstance(e.reason, _ProxyError):
raise ProxyError(e, request=request)
raise ConnectionError(e, request=request)
except ClosedPoolError as e:
raise ConnectionError(e, request=request) raise ConnectionError(e, request=request)
except _ProxyError as e: except _ProxyError as e:

View file

@ -16,7 +16,6 @@ from . import sessions
def request(method, url, **kwargs): def request(method, url, **kwargs):
"""Constructs and sends a :class:`Request <Request>`. """Constructs and sends a :class:`Request <Request>`.
Returns :class:`Response <Response>` object.
:param method: method for the new :class:`Request` object. :param method: method for the new :class:`Request` object.
:param url: URL for the new :class:`Request` object. :param url: URL for the new :class:`Request` object.
@ -25,18 +24,24 @@ def request(method, url, **kwargs):
:param json: (optional) json data to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with 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 cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
:param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': ('filename', fileobj)}``) for multipart encoding upload. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload.
``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')``
or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string
defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers
to add for the file.
:param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How long to wait for the server to send data :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 before giving up, as a float, or a :ref:`(connect timeout, read
<user/advanced.html#timeouts>`_) tuple. timeout) <timeouts>` tuple.
:type timeout: float or tuple :type timeout: float or tuple
:param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
:type allow_redirects: bool :type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
:param verify: (optional) if ``True``, the SSL cert will be verified. A CA_BUNDLE path can also be provided. :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``.
:param stream: (optional) if ``False``, the response content will be immediately downloaded. :param stream: (optional) if ``False``, the response content will be immediately downloaded.
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
:return: :class:`Response <Response>` object
:rtype: requests.Response
Usage:: Usage::
@ -45,31 +50,34 @@ def request(method, url, **kwargs):
<Response [200]> <Response [200]>
""" """
session = sessions.Session() # By using the 'with' statement we are sure the session is closed, thus we
response = session.request(method=method, url=url, **kwargs) # avoid leaving sockets open which can trigger a ResourceWarning in some
# By explicitly closing the session, we avoid leaving sockets open which # cases, and look like a memory leak in others.
# can trigger a ResourceWarning in some cases, and look like a memory leak with sessions.Session() as session:
# in others. return session.request(method=method, url=url, **kwargs)
session.close()
return response
def get(url, **kwargs): def get(url, params=None, **kwargs):
"""Sends a GET request. Returns :class:`Response` object. """Sends a GET request.
:param url: URL 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 \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
kwargs.setdefault('allow_redirects', True) kwargs.setdefault('allow_redirects', True)
return request('get', url, **kwargs) return request('get', url, params=params, **kwargs)
def options(url, **kwargs): def options(url, **kwargs):
"""Sends a OPTIONS request. Returns :class:`Response` object. """Sends a OPTIONS request.
:param url: URL for the new :class:`Request` object. :param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
kwargs.setdefault('allow_redirects', True) kwargs.setdefault('allow_redirects', True)
@ -77,10 +85,12 @@ def options(url, **kwargs):
def head(url, **kwargs): def head(url, **kwargs):
"""Sends a HEAD request. Returns :class:`Response` object. """Sends a HEAD request.
:param url: URL for the new :class:`Request` object. :param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
kwargs.setdefault('allow_redirects', False) kwargs.setdefault('allow_redirects', False)
@ -88,44 +98,52 @@ def head(url, **kwargs):
def post(url, data=None, json=None, **kwargs): def post(url, data=None, json=None, **kwargs):
"""Sends a POST request. Returns :class:`Response` object. """Sends a POST request.
:param url: URL for the new :class:`Request` 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 data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param json: (optional) json data to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
return request('post', url, data=data, json=json, **kwargs) return request('post', url, data=data, json=json, **kwargs)
def put(url, data=None, **kwargs): def put(url, data=None, **kwargs):
"""Sends a PUT request. Returns :class:`Response` object. """Sends a PUT request.
:param url: URL for the new :class:`Request` 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 data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
return request('put', url, data=data, **kwargs) return request('put', url, data=data, **kwargs)
def patch(url, data=None, **kwargs): def patch(url, data=None, **kwargs):
"""Sends a PATCH request. Returns :class:`Response` object. """Sends a PATCH request.
:param url: URL for the new :class:`Request` 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 data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
return request('patch', url, data=data, **kwargs) return request('patch', url, data=data, **kwargs)
def delete(url, **kwargs): def delete(url, **kwargs):
"""Sends a DELETE request. Returns :class:`Response` object. """Sends a DELETE request.
:param url: URL for the new :class:`Request` object. :param url: URL for the new :class:`Request` object.
:param \*\*kwargs: Optional arguments that ``request`` takes. :param \*\*kwargs: Optional arguments that ``request`` takes.
:return: :class:`Response <Response>` object
:rtype: requests.Response
""" """
return request('delete', url, **kwargs) return request('delete', url, **kwargs)

View file

@ -11,6 +11,7 @@ import os
import re import re
import time import time
import hashlib import hashlib
import threading
from base64 import b64encode from base64 import b64encode
@ -46,6 +47,15 @@ class HTTPBasicAuth(AuthBase):
self.username = username self.username = username
self.password = password self.password = password
def __eq__(self, other):
return all([
self.username == getattr(other, 'username', None),
self.password == getattr(other, 'password', None)
])
def __ne__(self, other):
return not self == other
def __call__(self, r): def __call__(self, r):
r.headers['Authorization'] = _basic_auth_str(self.username, self.password) r.headers['Authorization'] = _basic_auth_str(self.username, self.password)
return r return r
@ -63,19 +73,27 @@ class HTTPDigestAuth(AuthBase):
def __init__(self, username, password): def __init__(self, username, password):
self.username = username self.username = username
self.password = password self.password = password
self.last_nonce = '' # Keep state in per-thread local storage
self.nonce_count = 0 self._thread_local = threading.local()
self.chal = {}
self.pos = None def init_per_thread_state(self):
self.num_401_calls = 1 # Ensure state is initialized just once per-thread
if not hasattr(self._thread_local, 'init'):
self._thread_local.init = True
self._thread_local.last_nonce = ''
self._thread_local.nonce_count = 0
self._thread_local.chal = {}
self._thread_local.pos = None
self._thread_local.num_401_calls = None
def build_digest_header(self, method, url): def build_digest_header(self, method, url):
realm = self.chal['realm'] realm = self._thread_local.chal['realm']
nonce = self.chal['nonce'] nonce = self._thread_local.chal['nonce']
qop = self.chal.get('qop') qop = self._thread_local.chal.get('qop')
algorithm = self.chal.get('algorithm') algorithm = self._thread_local.chal.get('algorithm')
opaque = self.chal.get('opaque') opaque = self._thread_local.chal.get('opaque')
hash_utf8 = None
if algorithm is None: if algorithm is None:
_algorithm = 'MD5' _algorithm = 'MD5'
@ -103,7 +121,8 @@ class HTTPDigestAuth(AuthBase):
# XXX not implemented yet # XXX not implemented yet
entdig = None entdig = None
p_parsed = urlparse(url) p_parsed = urlparse(url)
path = p_parsed.path #: path is request-uri defined in RFC 2616 which should not be empty
path = p_parsed.path or "/"
if p_parsed.query: if p_parsed.query:
path += '?' + p_parsed.query path += '?' + p_parsed.query
@ -113,30 +132,32 @@ class HTTPDigestAuth(AuthBase):
HA1 = hash_utf8(A1) HA1 = hash_utf8(A1)
HA2 = hash_utf8(A2) HA2 = hash_utf8(A2)
if nonce == self.last_nonce: if nonce == self._thread_local.last_nonce:
self.nonce_count += 1 self._thread_local.nonce_count += 1
else: else:
self.nonce_count = 1 self._thread_local.nonce_count = 1
ncvalue = '%08x' % self.nonce_count ncvalue = '%08x' % self._thread_local.nonce_count
s = str(self.nonce_count).encode('utf-8') s = str(self._thread_local.nonce_count).encode('utf-8')
s += nonce.encode('utf-8') s += nonce.encode('utf-8')
s += time.ctime().encode('utf-8') s += time.ctime().encode('utf-8')
s += os.urandom(8) s += os.urandom(8)
cnonce = (hashlib.sha1(s).hexdigest()[:16]) cnonce = (hashlib.sha1(s).hexdigest()[:16])
noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, HA2)
if _algorithm == 'MD5-SESS': if _algorithm == 'MD5-SESS':
HA1 = hash_utf8('%s:%s:%s' % (HA1, nonce, cnonce)) HA1 = hash_utf8('%s:%s:%s' % (HA1, nonce, cnonce))
if qop is None: if not qop:
respdig = KD(HA1, "%s:%s" % (nonce, HA2)) respdig = KD(HA1, "%s:%s" % (nonce, HA2))
elif qop == 'auth' or 'auth' in qop.split(','): elif qop == 'auth' or 'auth' in qop.split(','):
noncebit = "%s:%s:%s:%s:%s" % (
nonce, ncvalue, cnonce, 'auth', HA2
)
respdig = KD(HA1, noncebit) respdig = KD(HA1, noncebit)
else: else:
# XXX handle auth-int. # XXX handle auth-int.
return None return None
self.last_nonce = nonce self._thread_local.last_nonce = nonce
# XXX should the partial digests be encoded too? # XXX should the partial digests be encoded too?
base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \ base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
@ -155,28 +176,27 @@ class HTTPDigestAuth(AuthBase):
def handle_redirect(self, r, **kwargs): def handle_redirect(self, r, **kwargs):
"""Reset num_401_calls counter on redirects.""" """Reset num_401_calls counter on redirects."""
if r.is_redirect: if r.is_redirect:
self.num_401_calls = 1 self._thread_local.num_401_calls = 1
def handle_401(self, r, **kwargs): def handle_401(self, r, **kwargs):
"""Takes the given response and tries digest-auth, if needed.""" """Takes the given response and tries digest-auth, if needed."""
if self.pos is not None: if self._thread_local.pos is not None:
# Rewind the file position indicator of the body to where # Rewind the file position indicator of the body to where
# it was to resend the request. # it was to resend the request.
r.request.body.seek(self.pos) r.request.body.seek(self._thread_local.pos)
num_401_calls = getattr(self, 'num_401_calls', 1)
s_auth = r.headers.get('www-authenticate', '') s_auth = r.headers.get('www-authenticate', '')
if 'digest' in s_auth.lower() and num_401_calls < 2: if 'digest' in s_auth.lower() and self._thread_local.num_401_calls < 2:
self.num_401_calls += 1 self._thread_local.num_401_calls += 1
pat = re.compile(r'digest ', flags=re.IGNORECASE) pat = re.compile(r'digest ', flags=re.IGNORECASE)
self.chal = parse_dict_header(pat.sub('', s_auth, count=1)) self._thread_local.chal = parse_dict_header(pat.sub('', s_auth, count=1))
# Consume content and release the original connection # Consume content and release the original connection
# to allow our new request to reuse the same one. # to allow our new request to reuse the same one.
r.content r.content
r.raw.release_conn() r.close()
prep = r.request.copy() prep = r.request.copy()
extract_cookies_to_jar(prep._cookies, r.request, r.raw) extract_cookies_to_jar(prep._cookies, r.request, r.raw)
prep.prepare_cookies(prep._cookies) prep.prepare_cookies(prep._cookies)
@ -189,21 +209,34 @@ class HTTPDigestAuth(AuthBase):
return _r return _r
self.num_401_calls = 1 self._thread_local.num_401_calls = 1
return r return r
def __call__(self, r): def __call__(self, r):
# Initialize per-thread state, if needed
self.init_per_thread_state()
# If we have a saved nonce, skip the 401 # If we have a saved nonce, skip the 401
if self.last_nonce: if self._thread_local.last_nonce:
r.headers['Authorization'] = self.build_digest_header(r.method, r.url) r.headers['Authorization'] = self.build_digest_header(r.method, r.url)
try: try:
self.pos = r.body.tell() self._thread_local.pos = r.body.tell()
except AttributeError: except AttributeError:
# In the case of HTTPDigestAuth being reused and the body of # In the case of HTTPDigestAuth being reused and the body of
# the previous request was a file-like object, pos has the # the previous request was a file-like object, pos has the
# file position of the previous body. Ensure it's set to # file position of the previous body. Ensure it's set to
# None. # None.
self.pos = None self._thread_local.pos = None
r.register_hook('response', self.handle_401) r.register_hook('response', self.handle_401)
r.register_hook('response', self.handle_redirect) r.register_hook('response', self.handle_redirect)
self._thread_local.num_401_calls = 1
return r return r
def __eq__(self, other):
return all([
self.username == getattr(other, 'username', None),
self.password == getattr(other, 'password', None)
])
def __ne__(self, other):
return not self == other

File diff suppressed because it is too large Load diff

View file

@ -21,58 +21,6 @@ is_py2 = (_ver[0] == 2)
#: Python 3.x? #: Python 3.x?
is_py3 = (_ver[0] == 3) is_py3 = (_ver[0] == 3)
#: Python 3.0.x
is_py30 = (is_py3 and _ver[1] == 0)
#: Python 3.1.x
is_py31 = (is_py3 and _ver[1] == 1)
#: Python 3.2.x
is_py32 = (is_py3 and _ver[1] == 2)
#: Python 3.3.x
is_py33 = (is_py3 and _ver[1] == 3)
#: Python 3.4.x
is_py34 = (is_py3 and _ver[1] == 4)
#: Python 2.7.x
is_py27 = (is_py2 and _ver[1] == 7)
#: Python 2.6.x
is_py26 = (is_py2 and _ver[1] == 6)
#: Python 2.5.x
is_py25 = (is_py2 and _ver[1] == 5)
#: Python 2.4.x
is_py24 = (is_py2 and _ver[1] == 4) # I'm assuming this is not by choice.
# ---------
# Platforms
# ---------
# Syntax sugar.
_ver = sys.version.lower()
is_pypy = ('pypy' in _ver)
is_jython = ('jython' in _ver)
is_ironpython = ('iron' in _ver)
# Assume CPython, if nothing else.
is_cpython = not any((is_pypy, is_jython, is_ironpython))
# Windows-based system.
is_windows = 'win32' in str(sys.platform).lower()
# Standard Linux 2+ system.
is_linux = ('linux' in str(sys.platform).lower())
is_osx = ('darwin' in str(sys.platform).lower())
is_hpux = ('hpux' in str(sys.platform).lower()) # Complete guess.
is_solaris = ('solar==' in str(sys.platform).lower()) # Complete guess.
try: try:
import simplejson as json import simplejson as json
except (ImportError, SyntaxError): except (ImportError, SyntaxError):
@ -99,7 +47,6 @@ if is_py2:
basestring = basestring basestring = basestring
numeric_types = (int, long, float) numeric_types = (int, long, float)
elif is_py3: elif is_py3:
from urllib.parse import urlparse, urlunparse, urljoin, urlsplit, urlencode, quote, unquote, quote_plus, unquote_plus, urldefrag from urllib.parse import urlparse, urlunparse, urljoin, urlsplit, urlencode, quote, unquote, quote_plus, unquote_plus, urldefrag
from urllib.request import parse_http_list, getproxies, proxy_bypass from urllib.request import parse_http_list, getproxies, proxy_bypass

View file

@ -6,7 +6,9 @@ Compatibility code to be able to use `cookielib.CookieJar` with requests.
requests.utils imports from here, so be careful with imports. requests.utils imports from here, so be careful with imports.
""" """
import copy
import time import time
import calendar
import collections import collections
from .compat import cookielib, urlparse, urlunparse, Morsel from .compat import cookielib, urlparse, urlunparse, Morsel
@ -142,10 +144,13 @@ def remove_cookie_by_name(cookiejar, name, domain=None, path=None):
""" """
clearables = [] clearables = []
for cookie in cookiejar: for cookie in cookiejar:
if cookie.name == name: if cookie.name != name:
if domain is None or domain == cookie.domain: continue
if path is None or path == cookie.path: if domain is not None and domain != cookie.domain:
clearables.append((cookie.domain, cookie.path, cookie.name)) continue
if path is not None and path != cookie.path:
continue
clearables.append((cookie.domain, cookie.path, cookie.name))
for domain, path, name in clearables: for domain, path, name in clearables:
cookiejar.clear(domain, path, name) cookiejar.clear(domain, path, name)
@ -157,26 +162,28 @@ class CookieConflictError(RuntimeError):
class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping): class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
"""Compatibility class; is a cookielib.CookieJar, but exposes a dict interface. """Compatibility class; is a cookielib.CookieJar, but exposes a dict
interface.
This is the CookieJar we create by default for requests and sessions that This is the CookieJar we create by default for requests and sessions that
don't specify one, since some clients may expect response.cookies and don't specify one, since some clients may expect response.cookies and
session.cookies to support dict operations. session.cookies to support dict operations.
Don't use the dict interface internally; it's just for compatibility with Requests does not use the dict interface internally; it's just for
with external client code. All `requests` code should work out of the box compatibility with external client code. All requests code should work
with externally provided instances of CookieJar, e.g., LWPCookieJar and out of the box with externally provided instances of ``CookieJar``, e.g.
FileCookieJar. ``LWPCookieJar`` and ``FileCookieJar``.
Caution: dictionary operations that are normally O(1) may be O(n).
Unlike a regular CookieJar, this class is pickleable. Unlike a regular CookieJar, this class is pickleable.
"""
.. warning:: dictionary operations that are normally O(1) may be O(n).
"""
def get(self, name, default=None, domain=None, path=None): def get(self, name, default=None, domain=None, path=None):
"""Dict-like get() that also supports optional domain and path args in """Dict-like get() that also supports optional domain and path args in
order to resolve naming collisions from using one cookie jar over order to resolve naming collisions from using one cookie jar over
multiple domains. Caution: operation is O(n), not O(1).""" multiple domains.
.. warning:: operation is O(n), not O(1)."""
try: try:
return self._find_no_duplicates(name, domain, path) return self._find_no_duplicates(name, domain, path)
except KeyError: except KeyError:
@ -199,37 +206,38 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
return c return c
def iterkeys(self): def iterkeys(self):
"""Dict-like iterkeys() that returns an iterator of names of cookies from the jar. """Dict-like iterkeys() that returns an iterator of names of cookies
See itervalues() and iteritems().""" from the jar. See itervalues() and iteritems()."""
for cookie in iter(self): for cookie in iter(self):
yield cookie.name yield cookie.name
def keys(self): def keys(self):
"""Dict-like keys() that returns a list of names of cookies from the jar. """Dict-like keys() that returns a list of names of cookies from the
See values() and items().""" jar. See values() and items()."""
return list(self.iterkeys()) return list(self.iterkeys())
def itervalues(self): def itervalues(self):
"""Dict-like itervalues() that returns an iterator of values of cookies from the jar. """Dict-like itervalues() that returns an iterator of values of cookies
See iterkeys() and iteritems().""" from the jar. See iterkeys() and iteritems()."""
for cookie in iter(self): for cookie in iter(self):
yield cookie.value yield cookie.value
def values(self): def values(self):
"""Dict-like values() that returns a list of values of cookies from the jar. """Dict-like values() that returns a list of values of cookies from the
See keys() and items().""" jar. See keys() and items()."""
return list(self.itervalues()) return list(self.itervalues())
def iteritems(self): def iteritems(self):
"""Dict-like iteritems() that returns an iterator of name-value tuples from the jar. """Dict-like iteritems() that returns an iterator of name-value tuples
See iterkeys() and itervalues().""" from the jar. See iterkeys() and itervalues()."""
for cookie in iter(self): for cookie in iter(self):
yield cookie.name, cookie.value yield cookie.name, cookie.value
def items(self): def items(self):
"""Dict-like items() that returns a list of name-value tuples from the jar. """Dict-like items() that returns a list of name-value tuples from the
See keys() and values(). Allows client-code to call "dict(RequestsCookieJar) jar. See keys() and values(). Allows client-code to call
and get a vanilla python dict of key value pairs.""" ``dict(RequestsCookieJar)`` and get a vanilla python dict of key value
pairs."""
return list(self.iteritems()) return list(self.iteritems())
def list_domains(self): def list_domains(self):
@ -259,8 +267,9 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
return False # there is only one domain in jar return False # there is only one domain in jar
def get_dict(self, domain=None, path=None): def get_dict(self, domain=None, path=None):
"""Takes as an argument an optional domain and path and returns a plain old """Takes as an argument an optional domain and path and returns a plain
Python dict of name-value pairs of cookies that meet the requirements.""" old Python dict of name-value pairs of cookies that meet the
requirements."""
dictionary = {} dictionary = {}
for cookie in iter(self): for cookie in iter(self):
if (domain is None or cookie.domain == domain) and (path is None if (domain is None or cookie.domain == domain) and (path is None
@ -268,22 +277,31 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
dictionary[cookie.name] = cookie.value dictionary[cookie.name] = cookie.value
return dictionary return dictionary
def __contains__(self, name):
try:
return super(RequestsCookieJar, self).__contains__(name)
except CookieConflictError:
return True
def __getitem__(self, name): def __getitem__(self, name):
"""Dict-like __getitem__() for compatibility with client code. Throws exception """Dict-like __getitem__() for compatibility with client code. Throws
if there are more than one cookie with name. In that case, use the more exception if there are more than one cookie with name. In that case,
explicit get() method instead. Caution: operation is O(n), not O(1).""" use the more explicit get() method instead.
.. warning:: operation is O(n), not O(1)."""
return self._find_no_duplicates(name) return self._find_no_duplicates(name)
def __setitem__(self, name, value): def __setitem__(self, name, value):
"""Dict-like __setitem__ for compatibility with client code. Throws exception """Dict-like __setitem__ for compatibility with client code. Throws
if there is already a cookie of that name in the jar. In that case, use the more exception if there is already a cookie of that name in the jar. In that
explicit set() method instead.""" case, use the more explicit set() method instead."""
self.set(name, value) self.set(name, value)
def __delitem__(self, name): def __delitem__(self, name):
"""Deletes a cookie given a name. Wraps cookielib.CookieJar's remove_cookie_by_name().""" """Deletes a cookie given a name. Wraps ``cookielib.CookieJar``'s
``remove_cookie_by_name()``."""
remove_cookie_by_name(self, name) remove_cookie_by_name(self, name)
def set_cookie(self, cookie, *args, **kwargs): def set_cookie(self, cookie, *args, **kwargs):
@ -295,15 +313,16 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
"""Updates this jar with cookies from another CookieJar or dict-like""" """Updates this jar with cookies from another CookieJar or dict-like"""
if isinstance(other, cookielib.CookieJar): if isinstance(other, cookielib.CookieJar):
for cookie in other: for cookie in other:
self.set_cookie(cookie) self.set_cookie(copy.copy(cookie))
else: else:
super(RequestsCookieJar, self).update(other) super(RequestsCookieJar, self).update(other)
def _find(self, name, domain=None, path=None): def _find(self, name, domain=None, path=None):
"""Requests uses this method internally to get cookie values. Takes as args name """Requests uses this method internally to get cookie values. Takes as
and optional domain and path. Returns a cookie.value. If there are conflicting cookies, args name and optional domain and path. Returns a cookie.value. If
_find arbitrarily chooses one. See _find_no_duplicates if you want an exception thrown there are conflicting cookies, _find arbitrarily chooses one. See
if there are conflicting cookies.""" _find_no_duplicates if you want an exception thrown if there are
conflicting cookies."""
for cookie in iter(self): for cookie in iter(self):
if cookie.name == name: if cookie.name == name:
if domain is None or cookie.domain == domain: if domain is None or cookie.domain == domain:
@ -313,10 +332,11 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
raise KeyError('name=%r, domain=%r, path=%r' % (name, domain, path)) raise KeyError('name=%r, domain=%r, path=%r' % (name, domain, path))
def _find_no_duplicates(self, name, domain=None, path=None): def _find_no_duplicates(self, name, domain=None, path=None):
"""__get_item__ and get call _find_no_duplicates -- never used in Requests internally. """Both ``__get_item__`` and ``get`` call this function: it's never
Takes as args name and optional domain and path. Returns a cookie.value. used elsewhere in Requests. Takes as args name and optional domain and
Throws KeyError if cookie is not found and CookieConflictError if there are path. Returns a cookie.value. Throws KeyError if cookie is not found
multiple cookies that match name and optionally domain and path.""" and CookieConflictError if there are multiple cookies that match name
and optionally domain and path."""
toReturn = None toReturn = None
for cookie in iter(self): for cookie in iter(self):
if cookie.name == name: if cookie.name == name:
@ -350,6 +370,21 @@ class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
return new_cj return new_cj
def _copy_cookie_jar(jar):
if jar is None:
return None
if hasattr(jar, 'copy'):
# We're dealing with an instance of RequestsCookieJar
return jar.copy()
# We're dealing with a generic CookieJar instance
new_jar = copy.copy(jar)
new_jar.clear()
for cookie in jar:
new_jar.set_cookie(copy.copy(cookie))
return new_jar
def create_cookie(name, value, **kwargs): def create_cookie(name, value, **kwargs):
"""Make a cookie from underspecified parameters. """Make a cookie from underspecified parameters.
@ -390,11 +425,15 @@ def morsel_to_cookie(morsel):
expires = None expires = None
if morsel['max-age']: if morsel['max-age']:
expires = time.time() + morsel['max-age'] try:
expires = int(time.time() + int(morsel['max-age']))
except ValueError:
raise TypeError('max-age: %s must be integer' % morsel['max-age'])
elif morsel['expires']: elif morsel['expires']:
time_template = '%a, %d-%b-%Y %H:%M:%S GMT' time_template = '%a, %d-%b-%Y %H:%M:%S GMT'
expires = time.mktime( expires = calendar.timegm(
time.strptime(morsel['expires'], time_template)) - time.timezone time.strptime(morsel['expires'], time_template)
)
return create_cookie( return create_cookie(
comment=morsel['comment'], comment=morsel['comment'],
comment_url=bool(morsel['comment']), comment_url=bool(morsel['comment']),

View file

@ -97,3 +97,18 @@ class StreamConsumedError(RequestException, TypeError):
class RetryError(RequestException): class RetryError(RequestException):
"""Custom retries logic failed""" """Custom retries logic failed"""
# Warnings
class RequestsWarning(Warning):
"""Base warning for Requests."""
pass
class FileModeWarning(RequestsWarning, DeprecationWarning):
"""
A file was opened in text mode, but Requests determined its binary length.
"""
pass

View file

@ -12,34 +12,23 @@ Available hooks:
The response generated from a Request. The response generated from a Request.
""" """
HOOKS = ['response'] HOOKS = ['response']
def default_hooks(): def default_hooks():
hooks = {} return dict((event, []) for event in HOOKS)
for event in HOOKS:
hooks[event] = []
return hooks
# TODO: response is the only one # TODO: response is the only one
def dispatch_hook(key, hooks, hook_data, **kwargs): def dispatch_hook(key, hooks, hook_data, **kwargs):
"""Dispatches a hook dictionary on a given piece of data.""" """Dispatches a hook dictionary on a given piece of data."""
hooks = hooks or dict() hooks = hooks or dict()
hooks = hooks.get(key)
if key in hooks: if hooks:
hooks = hooks.get(key)
if hasattr(hooks, '__call__'): if hasattr(hooks, '__call__'):
hooks = [hooks] hooks = [hooks]
for hook in hooks: for hook in hooks:
_hook_data = hook(hook_data, **kwargs) _hook_data = hook(hook_data, **kwargs)
if _hook_data is not None: if _hook_data is not None:
hook_data = _hook_data hook_data = _hook_data
return hook_data return hook_data

View file

@ -15,7 +15,7 @@ from .hooks import default_hooks
from .structures import CaseInsensitiveDict from .structures import CaseInsensitiveDict
from .auth import HTTPBasicAuth from .auth import HTTPBasicAuth
from .cookies import cookiejar_from_dict, get_cookie_header from .cookies import cookiejar_from_dict, get_cookie_header, _copy_cookie_jar
from .packages.urllib3.fields import RequestField from .packages.urllib3.fields import RequestField
from .packages.urllib3.filepost import encode_multipart_formdata from .packages.urllib3.filepost import encode_multipart_formdata
from .packages.urllib3.util import parse_url from .packages.urllib3.util import parse_url
@ -30,7 +30,8 @@ from .utils import (
iter_slices, guess_json_utf, super_len, to_native_string) iter_slices, guess_json_utf, super_len, to_native_string)
from .compat import ( from .compat import (
cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO, cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO,
is_py2, chardet, json, builtin_str, basestring) is_py2, chardet, builtin_str, basestring)
from .compat import json as complexjson
from .status_codes import codes from .status_codes import codes
#: The set of HTTP status codes that indicate an automatically #: The set of HTTP status codes that indicate an automatically
@ -42,12 +43,11 @@ REDIRECT_STATI = (
codes.temporary_redirect, # 307 codes.temporary_redirect, # 307
codes.permanent_redirect, # 308 codes.permanent_redirect, # 308
) )
DEFAULT_REDIRECT_LIMIT = 30 DEFAULT_REDIRECT_LIMIT = 30
CONTENT_CHUNK_SIZE = 10 * 1024 CONTENT_CHUNK_SIZE = 10 * 1024
ITER_CHUNK_SIZE = 512 ITER_CHUNK_SIZE = 512
json_dumps = json.dumps
class RequestEncodingMixin(object): class RequestEncodingMixin(object):
@property @property
@ -103,8 +103,10 @@ class RequestEncodingMixin(object):
"""Build the body for a multipart/form-data request. """Build the body for a multipart/form-data request.
Will successfully encode files when passed as a dict or a list of Will successfully encode files when passed as a dict or a list of
2-tuples. Order is retained if data is a list of 2-tuples but arbitrary tuples. Order is retained if data is a list of tuples but arbitrary
if parameters are supplied as a dict. if parameters are supplied as a dict.
The tuples may be 2-tuples (filename, fileobj), 3-tuples (filename, fileobj, contentype)
or 4-tuples (filename, fileobj, contentype, custom_headers).
""" """
if (not files): if (not files):
@ -143,13 +145,13 @@ class RequestEncodingMixin(object):
else: else:
fn = guess_filename(v) or k fn = guess_filename(v) or k
fp = v fp = v
if isinstance(fp, str):
fp = StringIO(fp)
if isinstance(fp, bytes):
fp = BytesIO(fp)
rf = RequestField(name=k, data=fp.read(), if isinstance(fp, (str, bytes, bytearray)):
filename=fn, headers=fh) fdata = fp
else:
fdata = fp.read()
rf = RequestField(name=k, data=fdata, filename=fn, headers=fh)
rf.make_multipart(content_type=ft) rf.make_multipart(content_type=ft)
new_fields.append(rf) new_fields.append(rf)
@ -192,7 +194,7 @@ class Request(RequestHooksMixin):
:param headers: dictionary of headers to send. :param headers: dictionary of headers to send.
:param files: dictionary of {filename: fileobject} files to multipart upload. :param files: dictionary of {filename: fileobject} files to multipart upload.
:param data: the body to attach to the request. If a dictionary is provided, form-encoding will take place. :param data: the body to attach to the request. If a dictionary is provided, form-encoding will take place.
:param json: json for the body to attach to the request (if data is not specified). :param json: json for the body to attach to the request (if files or data is not specified).
:param params: dictionary of URL parameters to append to the URL. :param params: dictionary of URL parameters to append to the URL.
:param auth: Auth handler or (user, pass) tuple. :param auth: Auth handler or (user, pass) tuple.
:param cookies: dictionary or CookieJar of cookies to attach to this request. :param cookies: dictionary or CookieJar of cookies to attach to this request.
@ -206,17 +208,8 @@ class Request(RequestHooksMixin):
<PreparedRequest [GET]> <PreparedRequest [GET]>
""" """
def __init__(self, def __init__(self, method=None, url=None, headers=None, files=None,
method=None, data=None, params=None, auth=None, cookies=None, hooks=None, json=None):
url=None,
headers=None,
files=None,
data=None,
params=None,
auth=None,
cookies=None,
hooks=None,
json=None):
# Default empty dicts for dict params. # Default empty dicts for dict params.
data = [] if data is None else data data = [] if data is None else data
@ -295,8 +288,7 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
self.hooks = default_hooks() self.hooks = default_hooks()
def prepare(self, method=None, url=None, headers=None, files=None, def prepare(self, method=None, url=None, headers=None, files=None,
data=None, params=None, auth=None, cookies=None, hooks=None, data=None, params=None, auth=None, cookies=None, hooks=None, json=None):
json=None):
"""Prepares the entire request with the given parameters.""" """Prepares the entire request with the given parameters."""
self.prepare_method(method) self.prepare_method(method)
@ -305,6 +297,7 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
self.prepare_cookies(cookies) self.prepare_cookies(cookies)
self.prepare_body(data, files, json) self.prepare_body(data, files, json)
self.prepare_auth(auth, url) self.prepare_auth(auth, url)
# Note that prepare_auth must be last to enable authentication schemes # Note that prepare_auth must be last to enable authentication schemes
# such as OAuth to work on a fully prepared request. # such as OAuth to work on a fully prepared request.
@ -319,7 +312,7 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
p.method = self.method p.method = self.method
p.url = self.url p.url = self.url
p.headers = self.headers.copy() if self.headers is not None else None p.headers = self.headers.copy() if self.headers is not None else None
p._cookies = self._cookies.copy() if self._cookies is not None else None p._cookies = _copy_cookie_jar(self._cookies)
p.body = self.body p.body = self.body
p.hooks = self.hooks p.hooks = self.hooks
return p return p
@ -328,12 +321,12 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
"""Prepares the given HTTP method.""" """Prepares the given HTTP method."""
self.method = method self.method = method
if self.method is not None: if self.method is not None:
self.method = self.method.upper() self.method = to_native_string(self.method.upper())
def prepare_url(self, url, params): def prepare_url(self, url, params):
"""Prepares the given HTTP URL.""" """Prepares the given HTTP URL."""
#: Accept objects that have string representations. #: Accept objects that have string representations.
#: We're unable to blindy call unicode/str functions #: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'') #: as this will include the bytestring indicator (b'')
#: on python 3.x. #: on python 3.x.
#: https://github.com/kennethreitz/requests/pull/2238 #: https://github.com/kennethreitz/requests/pull/2238
@ -356,8 +349,10 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
raise InvalidURL(*e.args) raise InvalidURL(*e.args)
if not scheme: if not scheme:
raise MissingSchema("Invalid URL {0!r}: No schema supplied. " error = ("Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?")
"Perhaps you meant http://{0}?".format(url)) error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host: if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url) raise InvalidURL("Invalid URL %r: No host supplied" % url)
@ -392,6 +387,9 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
if isinstance(fragment, str): if isinstance(fragment, str):
fragment = fragment.encode('utf-8') fragment = fragment.encode('utf-8')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = self._encode_params(params) enc_params = self._encode_params(params)
if enc_params: if enc_params:
if query: if query:
@ -421,9 +419,9 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
content_type = None content_type = None
length = None length = None
if json is not None: if not data and json is not None:
content_type = 'application/json' content_type = 'application/json'
body = json_dumps(json) body = complexjson.dumps(json)
is_stream = all([ is_stream = all([
hasattr(data, '__iter__'), hasattr(data, '__iter__'),
@ -441,7 +439,7 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
if files: if files:
raise NotImplementedError('Streamed bodies and files are mutually exclusive.') raise NotImplementedError('Streamed bodies and files are mutually exclusive.')
if length is not None: if length:
self.headers['Content-Length'] = builtin_str(length) self.headers['Content-Length'] = builtin_str(length)
else: else:
self.headers['Transfer-Encoding'] = 'chunked' self.headers['Transfer-Encoding'] = 'chunked'
@ -450,7 +448,7 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
if files: if files:
(body, content_type) = self._encode_files(files, data) (body, content_type) = self._encode_files(files, data)
else: else:
if data and json is None: if data:
body = self._encode_params(data) body = self._encode_params(data)
if isinstance(data, basestring) or hasattr(data, 'read'): if isinstance(data, basestring) or hasattr(data, 'read'):
content_type = None content_type = None
@ -467,9 +465,11 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
def prepare_content_length(self, body): def prepare_content_length(self, body):
if hasattr(body, 'seek') and hasattr(body, 'tell'): if hasattr(body, 'seek') and hasattr(body, 'tell'):
curr_pos = body.tell()
body.seek(0, 2) body.seek(0, 2)
self.headers['Content-Length'] = builtin_str(body.tell()) end_pos = body.tell()
body.seek(0, 0) self.headers['Content-Length'] = builtin_str(max(0, end_pos - curr_pos))
body.seek(curr_pos, 0)
elif body is not None: elif body is not None:
l = super_len(body) l = super_len(body)
if l: if l:
@ -500,7 +500,15 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
self.prepare_content_length(self.body) self.prepare_content_length(self.body)
def prepare_cookies(self, cookies): def prepare_cookies(self, cookies):
"""Prepares the given HTTP cookie data.""" """Prepares the given HTTP cookie data.
This function eventually generates a ``Cookie`` header from the
given cookies using cookielib. Due to cookielib's design, the header
will not be regenerated if it already exists, meaning this function
can only be called once for the life of the
:class:`PreparedRequest <PreparedRequest>` object. Any subsequent calls
to ``prepare_cookies`` will have no actual effect, unless the "Cookie"
header is removed beforehand."""
if isinstance(cookies, cookielib.CookieJar): if isinstance(cookies, cookielib.CookieJar):
self._cookies = cookies self._cookies = cookies
@ -513,6 +521,10 @@ class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
def prepare_hooks(self, hooks): def prepare_hooks(self, hooks):
"""Prepares the given hooks.""" """Prepares the given hooks."""
# hooks can be passed as None to the prepare method and to this
# method. To prevent iterating over None, simply use an empty list
# if hooks is False-y
hooks = hooks or []
for event in hooks: for event in hooks:
self.register_hook(event, hooks[event]) self.register_hook(event, hooks[event])
@ -523,16 +535,8 @@ class Response(object):
""" """
__attrs__ = [ __attrs__ = [
'_content', '_content', 'status_code', 'headers', 'url', 'history',
'status_code', 'encoding', 'reason', 'cookies', 'elapsed', 'request'
'headers',
'url',
'history',
'encoding',
'reason',
'cookies',
'elapsed',
'request',
] ]
def __init__(self): def __init__(self):
@ -572,7 +576,11 @@ class Response(object):
self.cookies = cookiejar_from_dict({}) self.cookies = cookiejar_from_dict({})
#: The amount of time elapsed between sending the request #: The amount of time elapsed between sending the request
#: and the arrival of the response (as a timedelta) #: and the arrival of the response (as a timedelta).
#: This property specifically measures the time taken between sending
#: the first byte of the request and finishing parsing the headers. It
#: is therefore unaffected by consuming the response content or the
#: value of the ``stream`` keyword argument.
self.elapsed = datetime.timedelta(0) self.elapsed = datetime.timedelta(0)
#: The :class:`PreparedRequest <PreparedRequest>` object to which this #: The :class:`PreparedRequest <PreparedRequest>` object to which this
@ -630,7 +638,7 @@ class Response(object):
@property @property
def is_permanent_redirect(self): def is_permanent_redirect(self):
"""True if this Response one of the permanant versions of redirect""" """True if this Response one of the permanent versions of redirect"""
return ('location' in self.headers and self.status_code in (codes.moved_permanently, codes.permanent_redirect)) return ('location' in self.headers and self.status_code in (codes.moved_permanently, codes.permanent_redirect))
@property @property
@ -648,9 +656,10 @@ class Response(object):
If decode_unicode is True, content will be decoded using the best If decode_unicode is True, content will be decoded using the best
available encoding based on the response. available encoding based on the response.
""" """
def generate(): def generate():
try: # Special case for urllib3.
# Special case for urllib3. if hasattr(self.raw, 'stream'):
try: try:
for chunk in self.raw.stream(chunk_size, decode_content=True): for chunk in self.raw.stream(chunk_size, decode_content=True):
yield chunk yield chunk
@ -660,7 +669,7 @@ class Response(object):
raise ContentDecodingError(e) raise ContentDecodingError(e)
except ReadTimeoutError as e: except ReadTimeoutError as e:
raise ConnectionError(e) raise ConnectionError(e)
except AttributeError: else:
# Standard file-like object. # Standard file-like object.
while True: while True:
chunk = self.raw.read(chunk_size) chunk = self.raw.read(chunk_size)
@ -688,6 +697,8 @@ class Response(object):
"""Iterates over the response data, one line at a time. When """Iterates over the response data, one line at a time. When
stream=True is set on the request, this avoids reading the stream=True is set on the request, this avoids reading the
content at once into memory for large responses. content at once into memory for large responses.
.. note:: This method is not reentrant safe.
""" """
pending = None pending = None
@ -789,14 +800,16 @@ class Response(object):
encoding = guess_json_utf(self.content) encoding = guess_json_utf(self.content)
if encoding is not None: if encoding is not None:
try: try:
return json.loads(self.content.decode(encoding), **kwargs) return complexjson.loads(
self.content.decode(encoding), **kwargs
)
except UnicodeDecodeError: except UnicodeDecodeError:
# Wrong UTF codec detected; usually because it's not UTF-8 # Wrong UTF codec detected; usually because it's not UTF-8
# but some other 8-bit codec. This is an RFC violation, # but some other 8-bit codec. This is an RFC violation,
# and the server didn't bother to tell us what codec *was* # and the server didn't bother to tell us what codec *was*
# used. # used.
pass pass
return json.loads(self.text, **kwargs) return complexjson.loads(self.text, **kwargs)
@property @property
def links(self): def links(self):
@ -822,10 +835,10 @@ class Response(object):
http_error_msg = '' http_error_msg = ''
if 400 <= self.status_code < 500: if 400 <= self.status_code < 500:
http_error_msg = '%s Client Error: %s' % (self.status_code, self.reason) http_error_msg = '%s Client Error: %s for url: %s' % (self.status_code, self.reason, self.url)
elif 500 <= self.status_code < 600: elif 500 <= self.status_code < 600:
http_error_msg = '%s Server Error: %s' % (self.status_code, self.reason) http_error_msg = '%s Server Error: %s for url: %s' % (self.status_code, self.reason, self.url)
if http_error_msg: if http_error_msg:
raise HTTPError(http_error_msg, response=self) raise HTTPError(http_error_msg, response=self)
@ -836,4 +849,7 @@ class Response(object):
*Note: Should not normally need to be called explicitly.* *Note: Should not normally need to be called explicitly.*
""" """
if not self._content_consumed:
return self.raw.close()
return self.raw.release_conn() return self.raw.release_conn()

View file

@ -0,0 +1,11 @@
If you are planning to submit a pull request to requests with any changes in
this library do not go any further. These are independent libraries which we
vendor into requests. Any changes necessary to these libraries must be made in
them and submitted as separate pull requests to those libraries.
urllib3 pull requests go here: https://github.com/shazow/urllib3
chardet pull requests go here: https://github.com/chardet/chardet
See https://github.com/kennethreitz/requests/pull/1812#issuecomment-30854316
for the reasoning behind this.

View file

@ -1,3 +1,36 @@
from __future__ import absolute_import '''
Debian and other distributions "unbundle" requests' vendored dependencies, and
rewrite all imports to use the global versions of ``urllib3`` and ``chardet``.
The problem with this is that not only requests itself imports those
dependencies, but third-party code outside of the distros' control too.
from . import urllib3 In reaction to these problems, the distro maintainers replaced
``requests.packages`` with a magical "stub module" that imports the correct
modules. The implementations were varying in quality and all had severe
problems. For example, a symlink (or hardlink) that links the correct modules
into place introduces problems regarding object identity, since you now have
two modules in `sys.modules` with the same API, but different identities::
requests.packages.urllib3 is not urllib3
With version ``2.5.2``, requests started to maintain its own stub, so that
distro-specific breakage would be reduced to a minimum, even though the whole
issue is not requests' fault in the first place. See
https://github.com/kennethreitz/requests/pull/2375 for the corresponding pull
request.
'''
from __future__ import absolute_import
import sys
try:
from . import urllib3
except ImportError:
import urllib3
sys.modules['%s.urllib3' % __name__] = urllib3
try:
from . import chardet
except ImportError:
import chardet
sys.modules['%s.chardet' % __name__] = chardet

View file

@ -2,10 +2,8 @@
urllib3 - Thread-safe connection pooling and re-using. urllib3 - Thread-safe connection pooling and re-using.
""" """
__author__ = 'Andrey Petrov (andrey.petrov@shazow.net)' from __future__ import absolute_import
__license__ = 'MIT' import warnings
__version__ = 'dev'
from .connectionpool import ( from .connectionpool import (
HTTPConnectionPool, HTTPConnectionPool,
@ -32,8 +30,30 @@ except ImportError:
def emit(self, record): def emit(self, record):
pass pass
__author__ = 'Andrey Petrov (andrey.petrov@shazow.net)'
__license__ = 'MIT'
__version__ = '1.15.1'
__all__ = (
'HTTPConnectionPool',
'HTTPSConnectionPool',
'PoolManager',
'ProxyManager',
'HTTPResponse',
'Retry',
'Timeout',
'add_stderr_logger',
'connection_from_url',
'disable_warnings',
'encode_multipart_formdata',
'get_host',
'make_headers',
'proxy_from_url',
)
logging.getLogger(__name__).addHandler(NullHandler()) logging.getLogger(__name__).addHandler(NullHandler())
def add_stderr_logger(level=logging.DEBUG): def add_stderr_logger(level=logging.DEBUG):
""" """
Helper for quickly adding a StreamHandler to the logger. Useful for Helper for quickly adding a StreamHandler to the logger. Useful for
@ -48,16 +68,26 @@ def add_stderr_logger(level=logging.DEBUG):
handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s')) handler.setFormatter(logging.Formatter('%(asctime)s %(levelname)s %(message)s'))
logger.addHandler(handler) logger.addHandler(handler)
logger.setLevel(level) logger.setLevel(level)
logger.debug('Added a stderr logging handler to logger: %s' % __name__) logger.debug('Added a stderr logging handler to logger: %s', __name__)
return handler return handler
# ... Clean up. # ... Clean up.
del NullHandler del NullHandler
# Set security warning to only go off once by default. # All warning filters *must* be appended unless you're really certain that they
import warnings # shouldn't be: otherwise, it's very hard for users to use most Python
warnings.simplefilter('always', exceptions.SecurityWarning) # mechanisms to silence them.
# SecurityWarning's always go off by default.
warnings.simplefilter('always', exceptions.SecurityWarning, append=True)
# SubjectAltNameWarning's should go off once per host
warnings.simplefilter('default', exceptions.SubjectAltNameWarning, append=True)
# InsecurePlatformWarning's don't vary between requests, so we keep it default.
warnings.simplefilter('default', exceptions.InsecurePlatformWarning,
append=True)
# SNIMissingWarnings should go off only once.
warnings.simplefilter('default', exceptions.SNIMissingWarning, append=True)
def disable_warnings(category=exceptions.HTTPWarning): def disable_warnings(category=exceptions.HTTPWarning):
""" """

View file

@ -1,7 +1,8 @@
from __future__ import absolute_import
from collections import Mapping, MutableMapping from collections import Mapping, MutableMapping
try: try:
from threading import RLock from threading import RLock
except ImportError: # Platform-specific: No threads available except ImportError: # Platform-specific: No threads available
class RLock: class RLock:
def __enter__(self): def __enter__(self):
pass pass
@ -10,11 +11,11 @@ except ImportError: # Platform-specific: No threads available
pass pass
try: # Python 2.7+ try: # Python 2.7+
from collections import OrderedDict from collections import OrderedDict
except ImportError: except ImportError:
from .packages.ordered_dict import OrderedDict from .packages.ordered_dict import OrderedDict
from .packages.six import iterkeys, itervalues from .packages.six import iterkeys, itervalues, PY3
__all__ = ['RecentlyUsedContainer', 'HTTPHeaderDict'] __all__ = ['RecentlyUsedContainer', 'HTTPHeaderDict']
@ -129,25 +130,82 @@ class HTTPHeaderDict(MutableMapping):
'foo=bar, baz=quxx' 'foo=bar, baz=quxx'
>>> headers['Content-Length'] >>> headers['Content-Length']
'7' '7'
If you want to access the raw headers with their original casing
for debugging purposes you can access the private ``._data`` attribute
which is a normal python ``dict`` that maps the case-insensitive key to a
list of tuples stored as (case-sensitive-original-name, value). Using the
structure from above as our example:
>>> headers._data
{'set-cookie': [('Set-Cookie', 'foo=bar'), ('set-cookie', 'baz=quxx')],
'content-length': [('content-length', '7')]}
""" """
def __init__(self, headers=None, **kwargs): def __init__(self, headers=None, **kwargs):
self._data = {} super(HTTPHeaderDict, self).__init__()
if headers is None: self._container = OrderedDict()
headers = {} if headers is not None:
self.update(headers, **kwargs) if isinstance(headers, HTTPHeaderDict):
self._copy_from(headers)
else:
self.extend(headers)
if kwargs:
self.extend(kwargs)
def add(self, key, value): def __setitem__(self, key, val):
self._container[key.lower()] = (key, val)
return self._container[key.lower()]
def __getitem__(self, key):
val = self._container[key.lower()]
return ', '.join(val[1:])
def __delitem__(self, key):
del self._container[key.lower()]
def __contains__(self, key):
return key.lower() in self._container
def __eq__(self, other):
if not isinstance(other, Mapping) and not hasattr(other, 'keys'):
return False
if not isinstance(other, type(self)):
other = type(self)(other)
return (dict((k.lower(), v) for k, v in self.itermerged()) ==
dict((k.lower(), v) for k, v in other.itermerged()))
def __ne__(self, other):
return not self.__eq__(other)
if not PY3: # Python 2
iterkeys = MutableMapping.iterkeys
itervalues = MutableMapping.itervalues
__marker = object()
def __len__(self):
return len(self._container)
def __iter__(self):
# Only provide the originally cased names
for vals in self._container.values():
yield vals[0]
def pop(self, key, default=__marker):
'''D.pop(k[,d]) -> v, remove specified key and return the corresponding value.
If key is not found, d is returned if given, otherwise KeyError is raised.
'''
# Using the MutableMapping function directly fails due to the private marker.
# Using ordinary dict.pop would expose the internal structures.
# So let's reinvent the wheel.
try:
value = self[key]
except KeyError:
if default is self.__marker:
raise
return default
else:
del self[key]
return value
def discard(self, key):
try:
del self[key]
except KeyError:
pass
def add(self, key, val):
"""Adds a (name, value) pair, doesn't overwrite the value if it already """Adds a (name, value) pair, doesn't overwrite the value if it already
exists. exists.
@ -156,43 +214,111 @@ class HTTPHeaderDict(MutableMapping):
>>> headers['foo'] >>> headers['foo']
'bar, baz' 'bar, baz'
""" """
self._data.setdefault(key.lower(), []).append((key, value)) key_lower = key.lower()
new_vals = key, val
# Keep the common case aka no item present as fast as possible
vals = self._container.setdefault(key_lower, new_vals)
if new_vals is not vals:
# new_vals was not inserted, as there was a previous one
if isinstance(vals, list):
# If already several items got inserted, we have a list
vals.append(val)
else:
# vals should be a tuple then, i.e. only one item so far
# Need to convert the tuple to list for further extension
self._container[key_lower] = [vals[0], vals[1], val]
def extend(self, *args, **kwargs):
"""Generic import function for any type of header-like object.
Adapted version of MutableMapping.update in order to insert items
with self.add instead of self.__setitem__
"""
if len(args) > 1:
raise TypeError("extend() takes at most 1 positional "
"arguments ({0} given)".format(len(args)))
other = args[0] if len(args) >= 1 else ()
if isinstance(other, HTTPHeaderDict):
for key, val in other.iteritems():
self.add(key, val)
elif isinstance(other, Mapping):
for key in other:
self.add(key, other[key])
elif hasattr(other, "keys"):
for key in other.keys():
self.add(key, other[key])
else:
for key, value in other:
self.add(key, value)
for key, value in kwargs.items():
self.add(key, value)
def getlist(self, key): def getlist(self, key):
"""Returns a list of all the values for the named field. Returns an """Returns a list of all the values for the named field. Returns an
empty list if the key doesn't exist.""" empty list if the key doesn't exist."""
return self[key].split(', ') if key in self else [] try:
vals = self._container[key.lower()]
except KeyError:
return []
else:
if isinstance(vals, tuple):
return [vals[1]]
else:
return vals[1:]
def copy(self): # Backwards compatibility for httplib
h = HTTPHeaderDict() getheaders = getlist
for key in self._data: getallmatchingheaders = getlist
for rawkey, value in self._data[key]: iget = getlist
h.add(rawkey, value)
return h
def __eq__(self, other):
if not isinstance(other, Mapping):
return False
other = HTTPHeaderDict(other)
return dict((k1, self[k1]) for k1 in self._data) == \
dict((k2, other[k2]) for k2 in other._data)
def __getitem__(self, key):
values = self._data[key.lower()]
return ', '.join(value[1] for value in values)
def __setitem__(self, key, value):
self._data[key.lower()] = [(key, value)]
def __delitem__(self, key):
del self._data[key.lower()]
def __len__(self):
return len(self._data)
def __iter__(self):
for headers in itervalues(self._data):
yield headers[0][0]
def __repr__(self): def __repr__(self):
return '%s(%r)' % (self.__class__.__name__, dict(self.items())) return "%s(%s)" % (type(self).__name__, dict(self.itermerged()))
def _copy_from(self, other):
for key in other:
val = other.getlist(key)
if isinstance(val, list):
# Don't need to convert tuples
val = list(val)
self._container[key.lower()] = [key] + val
def copy(self):
clone = type(self)()
clone._copy_from(self)
return clone
def iteritems(self):
"""Iterate over all header lines, including duplicate ones."""
for key in self:
vals = self._container[key.lower()]
for val in vals[1:]:
yield vals[0], val
def itermerged(self):
"""Iterate over all headers, merging duplicate ones together."""
for key in self:
val = self._container[key.lower()]
yield val[0], ', '.join(val[1:])
def items(self):
return list(self.iteritems())
@classmethod
def from_httplib(cls, message): # Python 2
"""Read headers from a Python 2 httplib message object."""
# python2.7 does not expose a proper API for exporting multiheaders
# efficiently. This function re-reads raw lines from the message
# object and extracts the multiheaders properly.
headers = []
for line in message.headers:
if line.startswith((' ', '\t')):
key, value = headers[-1]
headers[-1] = (key, value + '\r\n' + line.rstrip())
continue
key, value = line.split(':', 1)
headers.append((key, value.strip()))
return cls(headers)

View file

@ -1,23 +1,21 @@
from __future__ import absolute_import
import datetime import datetime
import logging
import os
import sys import sys
import socket import socket
from socket import timeout as SocketTimeout from socket import error as SocketError, timeout as SocketTimeout
import warnings import warnings
from .packages import six from .packages import six
try: # Python 3 try: # Python 3
from http.client import HTTPConnection as _HTTPConnection, HTTPException from http.client import HTTPConnection as _HTTPConnection
from http.client import HTTPException # noqa: unused in this module
except ImportError: except ImportError:
from httplib import HTTPConnection as _HTTPConnection, HTTPException from httplib import HTTPConnection as _HTTPConnection
from httplib import HTTPException # noqa: unused in this module
class DummyConnection(object):
"Used to detect a failed ConnectionCls import."
pass
try: # Compiled with SSL? try: # Compiled with SSL?
HTTPSConnection = DummyConnection
import ssl import ssl
BaseSSLError = ssl.SSLError BaseSSLError = ssl.SSLError
except (ImportError, AttributeError): # Platform-specific: No SSL. except (ImportError, AttributeError): # Platform-specific: No SSL.
@ -36,11 +34,12 @@ except NameError: # Python 2:
from .exceptions import ( from .exceptions import (
NewConnectionError,
ConnectTimeoutError, ConnectTimeoutError,
SubjectAltNameWarning,
SystemTimeWarning, SystemTimeWarning,
SecurityWarning,
) )
from .packages.ssl_match_hostname import match_hostname from .packages.ssl_match_hostname import match_hostname, CertificateError
from .util.ssl_ import ( from .util.ssl_ import (
resolve_cert_reqs, resolve_cert_reqs,
@ -52,6 +51,10 @@ from .util.ssl_ import (
from .util import connection from .util import connection
from ._collections import HTTPHeaderDict
log = logging.getLogger(__name__)
port_by_scheme = { port_by_scheme = {
'http': 80, 'http': 80,
'https': 443, 'https': 443,
@ -60,6 +63,11 @@ port_by_scheme = {
RECENT_DATE = datetime.date(2014, 1, 1) RECENT_DATE = datetime.date(2014, 1, 1)
class DummyConnection(object):
"""Used to detect a failed ConnectionCls import."""
pass
class HTTPConnection(_HTTPConnection, object): class HTTPConnection(_HTTPConnection, object):
""" """
Based on httplib.HTTPConnection but provides an extra constructor Based on httplib.HTTPConnection but provides an extra constructor
@ -133,11 +141,15 @@ class HTTPConnection(_HTTPConnection, object):
conn = connection.create_connection( conn = connection.create_connection(
(self.host, self.port), self.timeout, **extra_kw) (self.host, self.port), self.timeout, **extra_kw)
except SocketTimeout: except SocketTimeout as e:
raise ConnectTimeoutError( raise ConnectTimeoutError(
self, "Connection to %s timed out. (connect timeout=%s)" % self, "Connection to %s timed out. (connect timeout=%s)" %
(self.host, self.timeout)) (self.host, self.timeout))
except SocketError as e:
raise NewConnectionError(
self, "Failed to establish a new connection: %s" % e)
return conn return conn
def _prepare_conn(self, conn): def _prepare_conn(self, conn):
@ -155,6 +167,38 @@ class HTTPConnection(_HTTPConnection, object):
conn = self._new_conn() conn = self._new_conn()
self._prepare_conn(conn) self._prepare_conn(conn)
def request_chunked(self, method, url, body=None, headers=None):
"""
Alternative to the common request method, which sends the
body with chunked encoding and not as one block
"""
headers = HTTPHeaderDict(headers if headers is not None else {})
skip_accept_encoding = 'accept-encoding' in headers
self.putrequest(method, url, skip_accept_encoding=skip_accept_encoding)
for header, value in headers.items():
self.putheader(header, value)
if 'transfer-encoding' not in headers:
self.putheader('Transfer-Encoding', 'chunked')
self.endheaders()
if body is not None:
stringish_types = six.string_types + (six.binary_type,)
if isinstance(body, stringish_types):
body = (body,)
for chunk in body:
if not chunk:
continue
if not isinstance(chunk, six.binary_type):
chunk = chunk.encode('utf8')
len_str = hex(len(chunk))[2:]
self.send(len_str.encode('utf-8'))
self.send(b'\r\n')
self.send(chunk)
self.send(b'\r\n')
# After the if clause, to always have a closed body
self.send(b'0\r\n\r\n')
class HTTPSConnection(HTTPConnection): class HTTPSConnection(HTTPConnection):
default_port = port_by_scheme['https'] default_port = port_by_scheme['https']
@ -185,19 +229,25 @@ class VerifiedHTTPSConnection(HTTPSConnection):
""" """
cert_reqs = None cert_reqs = None
ca_certs = None ca_certs = None
ca_cert_dir = None
ssl_version = None ssl_version = None
assert_fingerprint = None assert_fingerprint = None
def set_cert(self, key_file=None, cert_file=None, def set_cert(self, key_file=None, cert_file=None,
cert_reqs=None, ca_certs=None, cert_reqs=None, ca_certs=None,
assert_hostname=None, assert_fingerprint=None): assert_hostname=None, assert_fingerprint=None,
ca_cert_dir=None):
if (ca_certs or ca_cert_dir) and cert_reqs is None:
cert_reqs = 'CERT_REQUIRED'
self.key_file = key_file self.key_file = key_file
self.cert_file = cert_file self.cert_file = cert_file
self.cert_reqs = cert_reqs self.cert_reqs = cert_reqs
self.ca_certs = ca_certs
self.assert_hostname = assert_hostname self.assert_hostname = assert_hostname
self.assert_fingerprint = assert_fingerprint self.assert_fingerprint = assert_fingerprint
self.ca_certs = ca_certs and os.path.expanduser(ca_certs)
self.ca_cert_dir = ca_cert_dir and os.path.expanduser(ca_cert_dir)
def connect(self): def connect(self):
# Add certificate verification # Add certificate verification
@ -234,6 +284,7 @@ class VerifiedHTTPSConnection(HTTPSConnection):
self.sock = ssl_wrap_socket(conn, self.key_file, self.cert_file, self.sock = ssl_wrap_socket(conn, self.key_file, self.cert_file,
cert_reqs=resolved_cert_reqs, cert_reqs=resolved_cert_reqs,
ca_certs=self.ca_certs, ca_certs=self.ca_certs,
ca_cert_dir=self.ca_cert_dir,
server_hostname=hostname, server_hostname=hostname,
ssl_version=resolved_ssl_version) ssl_version=resolved_ssl_version)
@ -245,18 +296,35 @@ class VerifiedHTTPSConnection(HTTPSConnection):
cert = self.sock.getpeercert() cert = self.sock.getpeercert()
if not cert.get('subjectAltName', ()): if not cert.get('subjectAltName', ()):
warnings.warn(( warnings.warn((
'Certificate has no `subjectAltName`, falling back to check for a `commonName` for now. ' 'Certificate for {0} has no `subjectAltName`, falling back to check for a '
'This feature is being removed by major browsers and deprecated by RFC 2818. ' '`commonName` for now. This feature is being removed by major browsers and '
'(See https://github.com/shazow/urllib3/issues/497 for details.)'), 'deprecated by RFC 2818. (See https://github.com/shazow/urllib3/issues/497 '
SecurityWarning 'for details.)'.format(hostname)),
SubjectAltNameWarning
) )
match_hostname(cert, self.assert_hostname or hostname) _match_hostname(cert, self.assert_hostname or hostname)
self.is_verified = (resolved_cert_reqs == ssl.CERT_REQUIRED self.is_verified = (resolved_cert_reqs == ssl.CERT_REQUIRED or
or self.assert_fingerprint is not None) self.assert_fingerprint is not None)
def _match_hostname(cert, asserted_hostname):
try:
match_hostname(cert, asserted_hostname)
except CertificateError as e:
log.error(
'Certificate did not match expected hostname: %s. '
'Certificate: %s', asserted_hostname, cert
)
# Add cert to exception and reraise so client code can inspect
# the cert when catching the exception, if they want to
e._peer_cert = cert
raise
if ssl: if ssl:
# Make a copy for testing. # Make a copy for testing.
UnverifiedHTTPSConnection = HTTPSConnection UnverifiedHTTPSConnection = HTTPSConnection
HTTPSConnection = VerifiedHTTPSConnection HTTPSConnection = VerifiedHTTPSConnection
else:
HTTPSConnection = DummyConnection

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import errno import errno
import logging import logging
import sys import sys
@ -10,13 +11,15 @@ try: # Python 3
from queue import LifoQueue, Empty, Full from queue import LifoQueue, Empty, Full
except ImportError: except ImportError:
from Queue import LifoQueue, Empty, Full from Queue import LifoQueue, Empty, Full
import Queue as _ # Platform-specific: Windows # Queue is imported for side effects on MS Windows
import Queue as _unused_module_Queue # noqa: unused
from .exceptions import ( from .exceptions import (
ClosedPoolError, ClosedPoolError,
ProtocolError, ProtocolError,
EmptyPoolError, EmptyPoolError,
HeaderParsingError,
HostChangedError, HostChangedError,
LocationValueError, LocationValueError,
MaxRetryError, MaxRetryError,
@ -25,6 +28,7 @@ from .exceptions import (
SSLError, SSLError,
TimeoutError, TimeoutError,
InsecureRequestWarning, InsecureRequestWarning,
NewConnectionError,
) )
from .packages.ssl_match_hostname import CertificateError from .packages.ssl_match_hostname import CertificateError
from .packages import six from .packages import six
@ -32,15 +36,16 @@ from .connection import (
port_by_scheme, port_by_scheme,
DummyConnection, DummyConnection,
HTTPConnection, HTTPSConnection, VerifiedHTTPSConnection, HTTPConnection, HTTPSConnection, VerifiedHTTPSConnection,
HTTPException, BaseSSLError, ConnectionError HTTPException, BaseSSLError,
) )
from .request import RequestMethods from .request import RequestMethods
from .response import HTTPResponse from .response import HTTPResponse
from .util.connection import is_connection_dropped from .util.connection import is_connection_dropped
from .util.response import assert_header_parsing
from .util.retry import Retry from .util.retry import Retry
from .util.timeout import Timeout from .util.timeout import Timeout
from .util.url import get_host from .util.url import get_host, Url
xrange = six.moves.xrange xrange = six.moves.xrange
@ -50,7 +55,7 @@ log = logging.getLogger(__name__)
_Default = object() _Default = object()
## Pool objects # Pool objects
class ConnectionPool(object): class ConnectionPool(object):
""" """
Base class for all connection pools, such as Base class for all connection pools, such as
@ -65,6 +70,11 @@ class ConnectionPool(object):
raise LocationValueError("No host specified.") raise LocationValueError("No host specified.")
# httplib doesn't like it when we include brackets in ipv6 addresses # 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.
self.host = host.strip('[]') self.host = host.strip('[]')
self.port = port self.port = port
@ -72,6 +82,21 @@ class ConnectionPool(object):
return '%s(host=%r, port=%r)' % (type(self).__name__, return '%s(host=%r, port=%r)' % (type(self).__name__,
self.host, self.port) self.host, self.port)
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.close()
# Return False to re-raise any potential exceptions
return False
def close():
"""
Close all pooled connections and disable the pool.
"""
pass
# This is taken from http://hg.python.org/cpython/file/7aaba721ebc0/Lib/socket.py#l252 # This is taken from http://hg.python.org/cpython/file/7aaba721ebc0/Lib/socket.py#l252
_blocking_errnos = set([errno.EAGAIN, errno.EWOULDBLOCK]) _blocking_errnos = set([errno.EAGAIN, errno.EWOULDBLOCK])
@ -105,7 +130,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
:param maxsize: :param maxsize:
Number of connections to save that can be reused. More than 1 is useful Number of connections to save that can be reused. More than 1 is useful
in multithreaded situations. If ``block`` is set to false, more in multithreaded situations. If ``block`` is set to False, more
connections will be created but they will not be saved once they've connections will be created but they will not be saved once they've
been used. been used.
@ -184,8 +209,8 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
Return a fresh :class:`HTTPConnection`. Return a fresh :class:`HTTPConnection`.
""" """
self.num_connections += 1 self.num_connections += 1
log.info("Starting new HTTP connection (%d): %s" % log.info("Starting new HTTP connection (%d): %s",
(self.num_connections, self.host)) self.num_connections, self.host)
conn = self.ConnectionCls(host=self.host, port=self.port, conn = self.ConnectionCls(host=self.host, port=self.port,
timeout=self.timeout.connect_timeout, timeout=self.timeout.connect_timeout,
@ -220,7 +245,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# If this is a persistent connection, check if it got disconnected # If this is a persistent connection, check if it got disconnected
if conn and is_connection_dropped(conn): if conn and is_connection_dropped(conn):
log.info("Resetting dropped connection: %s" % self.host) log.info("Resetting dropped connection: %s", self.host)
conn.close() 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 # This is a proxied connection that has been mutated by
@ -253,7 +278,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
except Full: except Full:
# This should never happen if self.block == True # This should never happen if self.block == True
log.warning( log.warning(
"Connection pool is full, discarding connection: %s" % "Connection pool is full, discarding connection: %s",
self.host) self.host)
# Connection never got put back into the pool, close it. # Connection never got put back into the pool, close it.
@ -266,6 +291,10 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
""" """
pass pass
def _prepare_proxy(self, conn):
# Nothing to do for HTTP connections.
pass
def _get_timeout(self, timeout): 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: if timeout is _Default:
@ -295,7 +324,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
if 'timed out' in str(err) or 'did not complete (read)' in str(err): # Python 2.6 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) raise ReadTimeoutError(self, url, "Read timed out. (read timeout=%s)" % timeout_value)
def _make_request(self, conn, method, url, timeout=_Default, def _make_request(self, conn, method, url, timeout=_Default, chunked=False,
**httplib_request_kw): **httplib_request_kw):
""" """
Perform a request on a given urllib connection object taken from our Perform a request on a given urllib connection object taken from our
@ -327,7 +356,10 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# conn.request() calls httplib.*.request, not the method in # conn.request() calls httplib.*.request, not the method in
# urllib3.request. It also calls makefile (recv) on the socket. # urllib3.request. It also calls makefile (recv) on the socket.
conn.request(method, url, **httplib_request_kw) if chunked:
conn.request_chunked(method, url, **httplib_request_kw)
else:
conn.request(method, url, **httplib_request_kw)
# Reset the timeout for the recv() on the socket # Reset the timeout for the recv() on the socket
read_timeout = timeout_obj.read_timeout read_timeout = timeout_obj.read_timeout
@ -349,7 +381,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# Receive the response from the server # Receive the response from the server
try: 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) httplib_response = conn.getresponse(buffering=True)
except TypeError: # Python 2.6 and older except TypeError: # Python 2.6 and older
httplib_response = conn.getresponse() httplib_response = conn.getresponse()
@ -359,11 +391,21 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# AppEngine doesn't have a version attr. # AppEngine doesn't have a version attr.
http_version = getattr(conn, '_http_vsn_str', 'HTTP/?') http_version = getattr(conn, '_http_vsn_str', 'HTTP/?')
log.debug("\"%s %s %s\" %s %s" % (method, url, http_version, log.debug("\"%s %s %s\" %s %s", method, url, http_version,
httplib_response.status, httplib_response.status, httplib_response.length)
httplib_response.length))
try:
assert_header_parsing(httplib_response.msg)
except HeaderParsingError as hpe: # Platform-specific: Python 3
log.warning(
'Failed to parse headers (url=%s): %s',
self._absolute_url(url), hpe, exc_info=True)
return httplib_response return httplib_response
def _absolute_url(self, path):
return Url(scheme=self.scheme, host=self.host, port=self.port, path=path).url
def close(self): def close(self):
""" """
Close all pooled connections and disable the pool. Close all pooled connections and disable the pool.
@ -401,7 +443,8 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
def urlopen(self, method, url, body=None, headers=None, retries=None, def urlopen(self, method, url, body=None, headers=None, retries=None,
redirect=True, assert_same_host=True, timeout=_Default, redirect=True, assert_same_host=True, timeout=_Default,
pool_timeout=None, release_conn=None, **response_kw): pool_timeout=None, release_conn=None, chunked=False,
**response_kw):
""" """
Get a connection from the pool and perform an HTTP request. This is the 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 lowest level call for making a request, so you'll need to specify all
@ -478,6 +521,11 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
back into the pool. If None, it takes the value of back into the pool. If None, it takes the value of
``response_kw.get('preload_content', True)``. ``response_kw.get('preload_content', True)``.
:param chunked:
If True, urllib3 will send the body using chunked transfer
encoding. Otherwise, urllib3 will send the body using the standard
content-length form. Defaults to False.
:param \**response_kw: :param \**response_kw:
Additional parameters are passed to Additional parameters are passed to
:meth:`urllib3.response.HTTPResponse.from_httplib` :meth:`urllib3.response.HTTPResponse.from_httplib`
@ -508,20 +556,32 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# complains about UnboundLocalError. # complains about UnboundLocalError.
err = None err = None
# Keep track of whether we cleanly exited the except block. This
# ensures we do proper cleanup in finally.
clean_exit = False
try: try:
# Request a connection from the queue. # Request a connection from the queue.
timeout_obj = self._get_timeout(timeout)
conn = self._get_conn(timeout=pool_timeout) conn = self._get_conn(timeout=pool_timeout)
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:
self._prepare_proxy(conn)
# Make the request on the httplib connection object. # Make the request on the httplib connection object.
httplib_response = self._make_request(conn, method, url, httplib_response = self._make_request(conn, method, url,
timeout=timeout, timeout=timeout_obj,
body=body, headers=headers) body=body, headers=headers,
chunked=chunked)
# If we're going to release the connection in ``finally:``, then # If we're going to release the connection in ``finally:``, then
# the request doesn't need to know about the connection. Otherwise # the response doesn't need to know about the connection. Otherwise
# it will also try to release it and we'll have a double-release # it will also try to release it and we'll have a double-release
# mess. # mess.
response_conn = not release_conn and conn response_conn = conn if not release_conn else None
# Import httplib's response into our own wrapper object # Import httplib's response into our own wrapper object
response = HTTPResponse.from_httplib(httplib_response, response = HTTPResponse.from_httplib(httplib_response,
@ -529,10 +589,8 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
connection=response_conn, connection=response_conn,
**response_kw) **response_kw)
# else: # Everything went great!
# The connection will be put back into the pool when clean_exit = True
# ``response.release_conn()`` is called (implicitly by
# ``response.read()``)
except Empty: except Empty:
# Timed out by queue. # Timed out by queue.
@ -542,32 +600,41 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
# Close the connection. If a connection is reused on which there # Close the connection. If a connection is reused on which there
# was a Certificate error, the next request will certainly raise # was a Certificate error, the next request will certainly raise
# another Certificate error. # another Certificate error.
if conn: clean_exit = False
conn.close()
conn = None
raise SSLError(e) raise SSLError(e)
except (TimeoutError, HTTPException, SocketError, ConnectionError) as e: except SSLError:
if conn: # Treat SSLError separately from BaseSSLError to preserve
# Discard the connection for these exceptions. It will be # traceback.
# be replaced during the next _get_conn() call. clean_exit = False
conn.close() raise
conn = None
stacktrace = sys.exc_info()[2] except (TimeoutError, HTTPException, SocketError, ProtocolError) as e:
if isinstance(e, SocketError) and self.proxy: # Discard the connection for these exceptions. It will be
# be replaced during the next _get_conn() call.
clean_exit = False
if 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)): elif isinstance(e, (SocketError, HTTPException)):
e = ProtocolError('Connection aborted.', e) e = ProtocolError('Connection aborted.', e)
retries = retries.increment(method, url, error=e, retries = retries.increment(method, url, error=e, _pool=self,
_pool=self, _stacktrace=stacktrace) _stacktrace=sys.exc_info()[2])
retries.sleep() retries.sleep()
# Keep track of the error for the retry warning. # Keep track of the error for the retry warning.
err = e err = e
finally: finally:
if not clean_exit:
# We hit some kind of exception, handled or otherwise. We need
# to throw the connection away unless explicitly told not to.
# Close the connection, set the variable to None, and make sure
# we put the None back in the pool to avoid leaking it.
conn = conn and conn.close()
release_conn = True
if release_conn: if release_conn:
# Put the connection back to be reused. If the connection is # Put the connection back to be reused. If the connection is
# expired then it will be None, which will get replaced with a # expired then it will be None, which will get replaced with a
@ -577,7 +644,7 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
if not conn: if not conn:
# Try again # Try again
log.warning("Retrying (%r) after connection " log.warning("Retrying (%r) after connection "
"broken by '%r': %s" % (retries, err, url)) "broken by '%r': %s", retries, err, url)
return self.urlopen(method, url, body, headers, retries, return self.urlopen(method, url, body, headers, retries,
redirect, assert_same_host, redirect, assert_same_host,
timeout=timeout, pool_timeout=pool_timeout, timeout=timeout, pool_timeout=pool_timeout,
@ -593,26 +660,39 @@ class HTTPConnectionPool(ConnectionPool, RequestMethods):
retries = retries.increment(method, url, response=response, _pool=self) retries = retries.increment(method, url, response=response, _pool=self)
except MaxRetryError: except MaxRetryError:
if retries.raise_on_redirect: if retries.raise_on_redirect:
# Release the connection for this response, since we're not
# returning it to be released manually.
response.release_conn()
raise raise
return response return response
log.info("Redirecting %s -> %s" % (url, redirect_location)) log.info("Redirecting %s -> %s", url, redirect_location)
return self.urlopen(method, redirect_location, body, headers, return self.urlopen(
retries=retries, redirect=redirect, method, redirect_location, body, headers,
assert_same_host=assert_same_host, retries=retries, redirect=redirect,
timeout=timeout, pool_timeout=pool_timeout, assert_same_host=assert_same_host,
release_conn=release_conn, **response_kw) timeout=timeout, pool_timeout=pool_timeout,
release_conn=release_conn, **response_kw)
# Check if we should retry the HTTP response. # Check if we should retry the HTTP response.
if retries.is_forced_retry(method, status_code=response.status): if retries.is_forced_retry(method, status_code=response.status):
retries = retries.increment(method, url, response=response, _pool=self) try:
retries = retries.increment(method, url, response=response, _pool=self)
except MaxRetryError:
if retries.raise_on_status:
# Release the connection for this response, since we're not
# returning it to be released manually.
response.release_conn()
raise
return response
retries.sleep() retries.sleep()
log.info("Forced retry: %s" % url) log.info("Forced retry: %s", url)
return self.urlopen(method, url, body, headers, return self.urlopen(
retries=retries, redirect=redirect, method, url, body, headers,
assert_same_host=assert_same_host, retries=retries, redirect=redirect,
timeout=timeout, pool_timeout=pool_timeout, assert_same_host=assert_same_host,
release_conn=release_conn, **response_kw) timeout=timeout, pool_timeout=pool_timeout,
release_conn=release_conn, **response_kw)
return response return response
@ -629,10 +709,10 @@ class HTTPSConnectionPool(HTTPConnectionPool):
``assert_hostname`` and ``host`` in this order to verify connections. ``assert_hostname`` and ``host`` in this order to verify connections.
If ``assert_hostname`` is False, no verification is done. If ``assert_hostname`` is False, no verification is done.
The ``key_file``, ``cert_file``, ``cert_reqs``, ``ca_certs`` and The ``key_file``, ``cert_file``, ``cert_reqs``, ``ca_certs``,
``ssl_version`` are only used if :mod:`ssl` is available and are fed into ``ca_cert_dir``, and ``ssl_version`` are only used if :mod:`ssl` is
:meth:`urllib3.util.ssl_wrap_socket` to upgrade the connection socket available and are fed into :meth:`urllib3.util.ssl_wrap_socket` to upgrade
into an SSL socket. the connection socket into an SSL socket.
""" """
scheme = 'https' scheme = 'https'
@ -645,15 +725,20 @@ class HTTPSConnectionPool(HTTPConnectionPool):
key_file=None, cert_file=None, cert_reqs=None, key_file=None, cert_file=None, cert_reqs=None,
ca_certs=None, ssl_version=None, ca_certs=None, ssl_version=None,
assert_hostname=None, assert_fingerprint=None, assert_hostname=None, assert_fingerprint=None,
**conn_kw): ca_cert_dir=None, **conn_kw):
HTTPConnectionPool.__init__(self, host, port, strict, timeout, maxsize, HTTPConnectionPool.__init__(self, host, port, strict, timeout, maxsize,
block, headers, retries, _proxy, _proxy_headers, block, headers, retries, _proxy, _proxy_headers,
**conn_kw) **conn_kw)
if ca_certs and cert_reqs is None:
cert_reqs = 'CERT_REQUIRED'
self.key_file = key_file self.key_file = key_file
self.cert_file = cert_file self.cert_file = cert_file
self.cert_reqs = cert_reqs self.cert_reqs = cert_reqs
self.ca_certs = ca_certs self.ca_certs = ca_certs
self.ca_cert_dir = ca_cert_dir
self.ssl_version = ssl_version self.ssl_version = ssl_version
self.assert_hostname = assert_hostname self.assert_hostname = assert_hostname
self.assert_fingerprint = assert_fingerprint self.assert_fingerprint = assert_fingerprint
@ -669,38 +754,40 @@ class HTTPSConnectionPool(HTTPConnectionPool):
cert_file=self.cert_file, cert_file=self.cert_file,
cert_reqs=self.cert_reqs, cert_reqs=self.cert_reqs,
ca_certs=self.ca_certs, ca_certs=self.ca_certs,
ca_cert_dir=self.ca_cert_dir,
assert_hostname=self.assert_hostname, assert_hostname=self.assert_hostname,
assert_fingerprint=self.assert_fingerprint) assert_fingerprint=self.assert_fingerprint)
conn.ssl_version = self.ssl_version conn.ssl_version = self.ssl_version
if self.proxy is not None:
# Python 2.7+
try:
set_tunnel = conn.set_tunnel
except AttributeError: # Platform-specific: Python 2.6
set_tunnel = conn._set_tunnel
if sys.version_info <= (2, 6, 4) and not self.proxy_headers: # Python 2.6.4 and older
set_tunnel(self.host, self.port)
else:
set_tunnel(self.host, self.port, self.proxy_headers)
# Establish tunnel connection early, because otherwise httplib
# would improperly set Host: header to proxy's IP:port.
conn.connect()
return conn 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
if sys.version_info <= (2, 6, 4) and not self.proxy_headers: # Python 2.6.4 and older
set_tunnel(self.host, self.port)
else:
set_tunnel(self.host, self.port, self.proxy_headers)
conn.connect()
def _new_conn(self): def _new_conn(self):
""" """
Return a fresh :class:`httplib.HTTPSConnection`. Return a fresh :class:`httplib.HTTPSConnection`.
""" """
self.num_connections += 1 self.num_connections += 1
log.info("Starting new HTTPS connection (%d): %s" log.info("Starting new HTTPS connection (%d): %s",
% (self.num_connections, self.host)) self.num_connections, self.host)
if not self.ConnectionCls or self.ConnectionCls is DummyConnection: if not self.ConnectionCls or self.ConnectionCls is DummyConnection:
# Platform-specific: Python without ssl
raise SSLError("Can't connect to HTTPS URL because the SSL " raise SSLError("Can't connect to HTTPS URL because the SSL "
"module is not available.") "module is not available.")
@ -755,6 +842,7 @@ def connection_from_url(url, **kw):
>>> r = conn.request('GET', '/') >>> r = conn.request('GET', '/')
""" """
scheme, host, port = get_host(url) 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) return HTTPSConnectionPool(host, port=port, **kw)
else: else:

View file

@ -0,0 +1,231 @@
from __future__ import absolute_import
import logging
import os
import warnings
from ..exceptions import (
HTTPError,
HTTPWarning,
MaxRetryError,
ProtocolError,
TimeoutError,
SSLError
)
from ..packages.six import BytesIO
from ..request import RequestMethods
from ..response import HTTPResponse
from ..util.timeout import Timeout
from ..util.retry import Retry
try:
from google.appengine.api import urlfetch
except ImportError:
urlfetch = None
log = logging.getLogger(__name__)
class AppEnginePlatformWarning(HTTPWarning):
pass
class AppEnginePlatformError(HTTPError):
pass
class AppEngineManager(RequestMethods):
"""
Connection manager for Google App Engine sandbox applications.
This manager uses the URLFetch service directly instead of using the
emulated httplib, and is subject to URLFetch limitations as described in
the App Engine documentation here:
https://cloud.google.com/appengine/docs/python/urlfetch
Notably it will raise an AppEnginePlatformError if:
* URLFetch is not available.
* If you attempt to use this on GAEv2 (Managed VMs), as full socket
support is available.
* If a request size is more than 10 megabytes.
* If a response size is more than 32 megabtyes.
* If you use an unsupported request method such as OPTIONS.
Beyond those cases, it will raise normal urllib3 errors.
"""
def __init__(self, headers=None, retries=None, validate_certificate=True):
if not urlfetch:
raise AppEnginePlatformError(
"URLFetch is not available in this environment.")
if is_prod_appengine_mvms():
raise AppEnginePlatformError(
"Use normal urllib3.PoolManager instead of AppEngineManager"
"on Managed VMs, as using URLFetch is not necessary in "
"this environment.")
warnings.warn(
"urllib3 is using URLFetch on Google App Engine sandbox instead "
"of sockets. To use sockets directly instead of URLFetch see "
"https://urllib3.readthedocs.org/en/latest/contrib.html.",
AppEnginePlatformWarning)
RequestMethods.__init__(self, headers)
self.validate_certificate = validate_certificate
self.retries = retries or Retry.DEFAULT
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
# Return False to re-raise any potential exceptions
return False
def urlopen(self, method, url, body=None, headers=None,
retries=None, redirect=True, timeout=Timeout.DEFAULT_TIMEOUT,
**response_kw):
retries = self._get_retries(retries, redirect)
try:
response = urlfetch.fetch(
url,
payload=body,
method=method,
headers=headers or {},
allow_truncated=False,
follow_redirects=(
redirect and
retries.redirect != 0 and
retries.total),
deadline=self._get_absolute_timeout(timeout),
validate_certificate=self.validate_certificate,
)
except urlfetch.DeadlineExceededError as e:
raise TimeoutError(self, e)
except urlfetch.InvalidURLError as e:
if 'too large' in str(e):
raise AppEnginePlatformError(
"URLFetch request too large, URLFetch only "
"supports requests up to 10mb in size.", e)
raise ProtocolError(e)
except urlfetch.DownloadError as e:
if 'Too many redirects' in str(e):
raise MaxRetryError(self, url, reason=e)
raise ProtocolError(e)
except urlfetch.ResponseTooLargeError as e:
raise AppEnginePlatformError(
"URLFetch response too large, URLFetch only supports"
"responses up to 32mb in size.", e)
except urlfetch.SSLCertificateError as e:
raise SSLError(e)
except urlfetch.InvalidMethodError as e:
raise AppEnginePlatformError(
"URLFetch does not support method: %s" % method, e)
http_response = self._urlfetch_response_to_http_response(
response, **response_kw)
# Check for redirect response
if (http_response.get_redirect_location() and
retries.raise_on_redirect and redirect):
raise MaxRetryError(self, url, "too many redirects")
# Check if we should retry the HTTP response.
if retries.is_forced_retry(method, status_code=http_response.status):
retries = retries.increment(
method, url, response=http_response, _pool=self)
log.info("Forced retry: %s", url)
retries.sleep()
return self.urlopen(
method, url,
body=body, headers=headers,
retries=retries, redirect=redirect,
timeout=timeout, **response_kw)
return http_response
def _urlfetch_response_to_http_response(self, urlfetch_resp, **response_kw):
if is_prod_appengine():
# Production GAE handles deflate encoding automatically, but does
# not remove the encoding header.
content_encoding = urlfetch_resp.headers.get('content-encoding')
if content_encoding == 'deflate':
del urlfetch_resp.headers['content-encoding']
transfer_encoding = urlfetch_resp.headers.get('transfer-encoding')
# We have a full response's content,
# so let's make sure we don't report ourselves as chunked data.
if transfer_encoding == 'chunked':
encodings = transfer_encoding.split(",")
encodings.remove('chunked')
urlfetch_resp.headers['transfer-encoding'] = ','.join(encodings)
return HTTPResponse(
# In order for decoding to work, we must present the content as
# a file-like object.
body=BytesIO(urlfetch_resp.content),
headers=urlfetch_resp.headers,
status=urlfetch_resp.status_code,
**response_kw
)
def _get_absolute_timeout(self, timeout):
if timeout is Timeout.DEFAULT_TIMEOUT:
return 5 # 5s is the default timeout for URLFetch.
if isinstance(timeout, Timeout):
if timeout._read is not timeout._connect:
warnings.warn(
"URLFetch does not support granular timeout settings, "
"reverting to total timeout.", AppEnginePlatformWarning)
return timeout.total
return timeout
def _get_retries(self, retries, redirect):
if not isinstance(retries, Retry):
retries = Retry.from_int(
retries, redirect=redirect, default=self.retries)
if retries.connect or retries.read or retries.redirect:
warnings.warn(
"URLFetch only supports total retries and does not "
"recognize connect, read, or redirect retry parameters.",
AppEnginePlatformWarning)
return retries
def is_appengine():
return (is_local_appengine() or
is_prod_appengine() or
is_prod_appengine_mvms())
def is_appengine_sandbox():
return is_appengine() and not is_prod_appengine_mvms()
def is_local_appengine():
return ('APPENGINE_RUNTIME' in os.environ and
'Development/' in os.environ['SERVER_SOFTWARE'])
def is_prod_appengine():
return ('APPENGINE_RUNTIME' in os.environ and
'Google App Engine/' in os.environ['SERVER_SOFTWARE'] and
not is_prod_appengine_mvms())
def is_prod_appengine_mvms():
return os.environ.get('GAE_VM', False) == 'true'

View file

@ -3,6 +3,7 @@ NTLM authenticating pool, contributed by erikcederstran
Issue #10, see: http://code.google.com/p/urllib3/issues/detail?id=10 Issue #10, see: http://code.google.com/p/urllib3/issues/detail?id=10
""" """
from __future__ import absolute_import
try: try:
from http.client import HTTPSConnection from http.client import HTTPSConnection
@ -42,8 +43,8 @@ class NTLMConnectionPool(HTTPSConnectionPool):
# Performs the NTLM handshake that secures the connection. The socket # Performs the NTLM handshake that secures the connection. The socket
# must be kept open while requests are performed. # must be kept open while requests are performed.
self.num_connections += 1 self.num_connections += 1
log.debug('Starting NTLM HTTPS connection no. %d: https://%s%s' % log.debug('Starting NTLM HTTPS connection no. %d: https://%s%s',
(self.num_connections, self.host, self.authurl)) self.num_connections, self.host, self.authurl)
headers = {} headers = {}
headers['Connection'] = 'Keep-Alive' headers['Connection'] = 'Keep-Alive'
@ -55,13 +56,13 @@ class NTLMConnectionPool(HTTPSConnectionPool):
# Send negotiation message # Send negotiation message
headers[req_header] = ( headers[req_header] = (
'NTLM %s' % ntlm.create_NTLM_NEGOTIATE_MESSAGE(self.rawuser)) 'NTLM %s' % ntlm.create_NTLM_NEGOTIATE_MESSAGE(self.rawuser))
log.debug('Request headers: %s' % headers) log.debug('Request headers: %s', headers)
conn.request('GET', self.authurl, None, headers) conn.request('GET', self.authurl, None, headers)
res = conn.getresponse() res = conn.getresponse()
reshdr = dict(res.getheaders()) reshdr = dict(res.getheaders())
log.debug('Response status: %s %s' % (res.status, res.reason)) log.debug('Response status: %s %s', res.status, res.reason)
log.debug('Response headers: %s' % reshdr) log.debug('Response headers: %s', reshdr)
log.debug('Response data: %s [...]' % res.read(100)) log.debug('Response data: %s [...]', res.read(100))
# Remove the reference to the socket, so that it can not be closed by # Remove the reference to the socket, so that it can not be closed by
# the response object (we want to keep the socket open) # the response object (we want to keep the socket open)
@ -86,12 +87,12 @@ class NTLMConnectionPool(HTTPSConnectionPool):
self.pw, self.pw,
NegotiateFlags) NegotiateFlags)
headers[req_header] = 'NTLM %s' % auth_msg headers[req_header] = 'NTLM %s' % auth_msg
log.debug('Request headers: %s' % headers) log.debug('Request headers: %s', headers)
conn.request('GET', self.authurl, None, headers) conn.request('GET', self.authurl, None, headers)
res = conn.getresponse() res = conn.getresponse()
log.debug('Response status: %s %s' % (res.status, res.reason)) log.debug('Response status: %s %s', res.status, res.reason)
log.debug('Response headers: %s' % dict(res.getheaders())) log.debug('Response headers: %s', dict(res.getheaders()))
log.debug('Response data: %s [...]' % res.read()[:100]) log.debug('Response data: %s [...]', res.read()[:100])
if res.status != 200: if res.status != 200:
if res.status == 401: if res.status == 401:
raise Exception('Server rejected request: wrong ' raise Exception('Server rejected request: wrong '

View file

@ -38,13 +38,12 @@ Module Variables
---------------- ----------------
:var DEFAULT_SSL_CIPHER_LIST: The list of supported SSL/TLS cipher suites. :var DEFAULT_SSL_CIPHER_LIST: The list of supported SSL/TLS cipher suites.
Default: ``ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:
ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+3DES:!aNULL:!MD5:!DSS``
.. _sni: https://en.wikipedia.org/wiki/Server_Name_Indication .. _sni: https://en.wikipedia.org/wiki/Server_Name_Indication
.. _crime attack: https://en.wikipedia.org/wiki/CRIME_(security_exploit) .. _crime attack: https://en.wikipedia.org/wiki/CRIME_(security_exploit)
''' '''
from __future__ import absolute_import
try: try:
from ndg.httpsclient.ssl_peer_verification import SUBJ_ALT_NAME_SUPPORT from ndg.httpsclient.ssl_peer_verification import SUBJ_ALT_NAME_SUPPORT
@ -55,9 +54,17 @@ except SyntaxError as e:
import OpenSSL.SSL import OpenSSL.SSL
from pyasn1.codec.der import decoder as der_decoder from pyasn1.codec.der import decoder as der_decoder
from pyasn1.type import univ, constraint from pyasn1.type import univ, constraint
from socket import _fileobject, timeout from socket import timeout, error as SocketError
try: # Platform-specific: Python 2
from socket import _fileobject
except ImportError: # Platform-specific: Python 3
_fileobject = None
from urllib3.packages.backports.makefile import backport_makefile
import ssl import ssl
import select import select
import six
from .. import connection from .. import connection
from .. import util from .. import util
@ -73,6 +80,12 @@ _openssl_versions = {
ssl.PROTOCOL_TLSv1: OpenSSL.SSL.TLSv1_METHOD, ssl.PROTOCOL_TLSv1: OpenSSL.SSL.TLSv1_METHOD,
} }
if hasattr(ssl, 'PROTOCOL_TLSv1_1') and hasattr(OpenSSL.SSL, 'TLSv1_1_METHOD'):
_openssl_versions[ssl.PROTOCOL_TLSv1_1] = OpenSSL.SSL.TLSv1_1_METHOD
if hasattr(ssl, 'PROTOCOL_TLSv1_2') and hasattr(OpenSSL.SSL, 'TLSv1_2_METHOD'):
_openssl_versions[ssl.PROTOCOL_TLSv1_2] = OpenSSL.SSL.TLSv1_2_METHOD
try: try:
_openssl_versions.update({ssl.PROTOCOL_SSLv3: OpenSSL.SSL.SSLv3_METHOD}) _openssl_versions.update({ssl.PROTOCOL_SSLv3: OpenSSL.SSL.SSLv3_METHOD})
except AttributeError: except AttributeError:
@ -81,27 +94,14 @@ except AttributeError:
_openssl_verify = { _openssl_verify = {
ssl.CERT_NONE: OpenSSL.SSL.VERIFY_NONE, ssl.CERT_NONE: OpenSSL.SSL.VERIFY_NONE,
ssl.CERT_OPTIONAL: OpenSSL.SSL.VERIFY_PEER, ssl.CERT_OPTIONAL: OpenSSL.SSL.VERIFY_PEER,
ssl.CERT_REQUIRED: OpenSSL.SSL.VERIFY_PEER ssl.CERT_REQUIRED:
+ OpenSSL.SSL.VERIFY_FAIL_IF_NO_PEER_CERT, OpenSSL.SSL.VERIFY_PEER + OpenSSL.SSL.VERIFY_FAIL_IF_NO_PEER_CERT,
} }
# A secure default. DEFAULT_SSL_CIPHER_LIST = util.ssl_.DEFAULT_CIPHERS.encode('ascii')
# Sources for more information on TLS ciphers:
#
# - https://wiki.mozilla.org/Security/Server_Side_TLS
# - https://www.ssllabs.com/projects/best-practices/index.html
# - https://hynek.me/articles/hardening-your-web-servers-ssl-ciphers/
#
# The general intent is:
# - Prefer cipher suites that offer perfect forward secrecy (DHE/ECDHE),
# - prefer ECDHE over DHE for better performance,
# - prefer any AES-GCM over any AES-CBC for better performance and security,
# - use 3DES as fallback which is secure but slow,
# - disable NULL authentication, MD5 MACs and DSS for security reasons.
DEFAULT_SSL_CIPHER_LIST = "ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:" + \
"ECDH+AES128:DH+AES:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+3DES:" + \
"!aNULL:!MD5:!DSS"
# OpenSSL will only write 16K at a time
SSL_WRITE_BLOCKSIZE = 16384
orig_util_HAS_SNI = util.HAS_SNI orig_util_HAS_SNI = util.HAS_SNI
orig_connection_ssl_wrap_socket = connection.ssl_wrap_socket orig_connection_ssl_wrap_socket = connection.ssl_wrap_socket
@ -112,6 +112,7 @@ def inject_into_urllib3():
connection.ssl_wrap_socket = ssl_wrap_socket connection.ssl_wrap_socket = ssl_wrap_socket
util.HAS_SNI = HAS_SNI util.HAS_SNI = HAS_SNI
util.IS_PYOPENSSL = True
def extract_from_urllib3(): def extract_from_urllib3():
@ -119,9 +120,10 @@ def extract_from_urllib3():
connection.ssl_wrap_socket = orig_connection_ssl_wrap_socket connection.ssl_wrap_socket = orig_connection_ssl_wrap_socket
util.HAS_SNI = orig_util_HAS_SNI util.HAS_SNI = orig_util_HAS_SNI
util.IS_PYOPENSSL = False
### Note: This is a slightly bug-fixed version of same from ndg-httpsclient. # Note: This is a slightly bug-fixed version of same from ndg-httpsclient.
class SubjectAltName(BaseSubjectAltName): class SubjectAltName(BaseSubjectAltName):
'''ASN.1 implementation for subjectAltNames support''' '''ASN.1 implementation for subjectAltNames support'''
@ -132,7 +134,7 @@ class SubjectAltName(BaseSubjectAltName):
constraint.ValueSizeConstraint(1, 1024) constraint.ValueSizeConstraint(1, 1024)
### Note: This is a slightly bug-fixed version of same from ndg-httpsclient. # Note: This is a slightly bug-fixed version of same from ndg-httpsclient.
def get_subj_alt_name(peer_cert): def get_subj_alt_name(peer_cert):
# Search through extensions # Search through extensions
dns_name = [] dns_name = []
@ -143,7 +145,7 @@ def get_subj_alt_name(peer_cert):
for i in range(peer_cert.get_extension_count()): for i in range(peer_cert.get_extension_count()):
ext = peer_cert.get_extension(i) ext = peer_cert.get_extension(i)
ext_name = ext.get_short_name() ext_name = ext.get_short_name()
if ext_name != 'subjectAltName': if ext_name != b'subjectAltName':
continue continue
# PyOpenSSL returns extension data in ASN.1 encoded form # PyOpenSSL returns extension data in ASN.1 encoded form
@ -175,13 +177,17 @@ class WrappedSocket(object):
self.socket = socket self.socket = socket
self.suppress_ragged_eofs = suppress_ragged_eofs self.suppress_ragged_eofs = suppress_ragged_eofs
self._makefile_refs = 0 self._makefile_refs = 0
self._closed = False
def fileno(self): def fileno(self):
return self.socket.fileno() return self.socket.fileno()
def makefile(self, mode, bufsize=-1): # Copy-pasted from Python 3.5 source code
self._makefile_refs += 1 def _decref_socketios(self):
return _fileobject(self, mode, bufsize, close=True) if self._makefile_refs > 0:
self._makefile_refs -= 1
if self._closed:
self.close()
def recv(self, *args, **kwargs): def recv(self, *args, **kwargs):
try: try:
@ -189,6 +195,11 @@ class WrappedSocket(object):
except OpenSSL.SSL.SysCallError as e: except OpenSSL.SSL.SysCallError as e:
if self.suppress_ragged_eofs and e.args == (-1, 'Unexpected EOF'): if self.suppress_ragged_eofs and e.args == (-1, 'Unexpected EOF'):
return b'' return b''
else:
raise SocketError(str(e))
except OpenSSL.SSL.ZeroReturnError as e:
if self.connection.get_shutdown() == OpenSSL.SSL.RECEIVED_SHUTDOWN:
return b''
else: else:
raise raise
except OpenSSL.SSL.WantReadError: except OpenSSL.SSL.WantReadError:
@ -201,6 +212,27 @@ class WrappedSocket(object):
else: else:
return data return data
def recv_into(self, *args, **kwargs):
try:
return self.connection.recv_into(*args, **kwargs)
except OpenSSL.SSL.SysCallError as e:
if self.suppress_ragged_eofs and e.args == (-1, 'Unexpected EOF'):
return 0
else:
raise SocketError(str(e))
except OpenSSL.SSL.ZeroReturnError as e:
if self.connection.get_shutdown() == OpenSSL.SSL.RECEIVED_SHUTDOWN:
return 0
else:
raise
except OpenSSL.SSL.WantReadError:
rd, wd, ed = select.select(
[self.socket], [], [], self.socket.gettimeout())
if not rd:
raise timeout('The read operation timed out')
else:
return self.recv_into(*args, **kwargs)
def settimeout(self, timeout): def settimeout(self, timeout):
return self.socket.settimeout(timeout) return self.socket.settimeout(timeout)
@ -216,13 +248,22 @@ class WrappedSocket(object):
continue continue
def sendall(self, data): def sendall(self, data):
while len(data): total_sent = 0
sent = self._send_until_done(data) while total_sent < len(data):
data = data[sent:] sent = self._send_until_done(data[total_sent:total_sent + SSL_WRITE_BLOCKSIZE])
total_sent += sent
def shutdown(self):
# FIXME rethrow compatible exceptions should we ever use this
self.connection.shutdown()
def close(self): def close(self):
if self._makefile_refs < 1: if self._makefile_refs < 1:
return self.connection.shutdown() try:
self._closed = True
return self.connection.close()
except OpenSSL.SSL.Error:
return
else: else:
self._makefile_refs -= 1 self._makefile_refs -= 1
@ -257,13 +298,23 @@ class WrappedSocket(object):
self._makefile_refs -= 1 self._makefile_refs -= 1
if _fileobject: # Platform-specific: Python 2
def makefile(self, mode, bufsize=-1):
self._makefile_refs += 1
return _fileobject(self, mode, bufsize, close=True)
else: # Platform-specific: Python 3
makefile = backport_makefile
WrappedSocket.makefile = makefile
def _verify_callback(cnx, x509, err_no, err_depth, return_code): def _verify_callback(cnx, x509, err_no, err_depth, return_code):
return err_no == 0 return err_no == 0
def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None, def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
ca_certs=None, server_hostname=None, ca_certs=None, server_hostname=None,
ssl_version=None): ssl_version=None, ca_cert_dir=None):
ctx = OpenSSL.SSL.Context(_openssl_versions[ssl_version]) ctx = OpenSSL.SSL.Context(_openssl_versions[ssl_version])
if certfile: if certfile:
keyfile = keyfile or certfile # Match behaviour of the normal python ssl library keyfile = keyfile or certfile # Match behaviour of the normal python ssl library
@ -272,15 +323,15 @@ def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
ctx.use_privatekey_file(keyfile) ctx.use_privatekey_file(keyfile)
if cert_reqs != ssl.CERT_NONE: if cert_reqs != ssl.CERT_NONE:
ctx.set_verify(_openssl_verify[cert_reqs], _verify_callback) ctx.set_verify(_openssl_verify[cert_reqs], _verify_callback)
if ca_certs: if ca_certs or ca_cert_dir:
try: try:
ctx.load_verify_locations(ca_certs, None) ctx.load_verify_locations(ca_certs, ca_cert_dir)
except OpenSSL.SSL.Error as e: except OpenSSL.SSL.Error as e:
raise ssl.SSLError('bad ca_certs: %r' % ca_certs, e) raise ssl.SSLError('bad ca_certs: %r' % ca_certs, e)
else: else:
ctx.set_default_verify_paths() ctx.set_default_verify_paths()
# Disable TLS compression to migitate CRIME attack (issue #309) # Disable TLS compression to mitigate CRIME attack (issue #309)
OP_NO_COMPRESSION = 0x20000 OP_NO_COMPRESSION = 0x20000
ctx.set_options(OP_NO_COMPRESSION) ctx.set_options(OP_NO_COMPRESSION)
@ -288,16 +339,20 @@ def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
ctx.set_cipher_list(DEFAULT_SSL_CIPHER_LIST) ctx.set_cipher_list(DEFAULT_SSL_CIPHER_LIST)
cnx = OpenSSL.SSL.Connection(ctx, sock) cnx = OpenSSL.SSL.Connection(ctx, sock)
if isinstance(server_hostname, six.text_type): # Platform-specific: Python 3
server_hostname = server_hostname.encode('utf-8')
cnx.set_tlsext_host_name(server_hostname) cnx.set_tlsext_host_name(server_hostname)
cnx.set_connect_state() cnx.set_connect_state()
while True: while True:
try: try:
cnx.do_handshake() cnx.do_handshake()
except OpenSSL.SSL.WantReadError: except OpenSSL.SSL.WantReadError:
select.select([sock], [], []) rd, _, _ = select.select([sock], [], [], sock.gettimeout())
if not rd:
raise timeout('select timed out')
continue continue
except OpenSSL.SSL.Error as e: except OpenSSL.SSL.Error as e:
raise ssl.SSLError('bad handshake', e) raise ssl.SSLError('bad handshake: %r' % e)
break break
return WrappedSocket(cnx, sock) return WrappedSocket(cnx, sock)

View file

@ -0,0 +1,172 @@
# -*- coding: utf-8 -*-
"""
SOCKS support for urllib3
~~~~~~~~~~~~~~~~~~~~~~~~~
This contrib module contains provisional support for SOCKS proxies from within
urllib3. This module supports SOCKS4 (specifically the SOCKS4A variant) and
SOCKS5. To enable its functionality, either install PySocks or install this
module with the ``socks`` extra.
Known Limitations:
- Currently PySocks does not support contacting remote websites via literal
IPv6 addresses. Any such connection attempt will fail.
- Currently PySocks does not support IPv6 connections to the SOCKS proxy. Any
such connection attempt will fail.
"""
from __future__ import absolute_import
try:
import socks
except ImportError:
import warnings
from ..exceptions import DependencyWarning
warnings.warn((
'SOCKS support in urllib3 requires the installation of optional '
'dependencies: specifically, PySocks. For more information, see '
'https://urllib3.readthedocs.org/en/latest/contrib.html#socks-proxies'
),
DependencyWarning
)
raise
from socket import error as SocketError, timeout as SocketTimeout
from ..connection import (
HTTPConnection, HTTPSConnection
)
from ..connectionpool import (
HTTPConnectionPool, HTTPSConnectionPool
)
from ..exceptions import ConnectTimeoutError, NewConnectionError
from ..poolmanager import PoolManager
from ..util.url import parse_url
try:
import ssl
except ImportError:
ssl = None
class SOCKSConnection(HTTPConnection):
"""
A plain-text HTTP connection that connects via a SOCKS proxy.
"""
def __init__(self, *args, **kwargs):
self._socks_options = kwargs.pop('_socks_options')
super(SOCKSConnection, self).__init__(*args, **kwargs)
def _new_conn(self):
"""
Establish a new connection via the SOCKS proxy.
"""
extra_kw = {}
if self.source_address:
extra_kw['source_address'] = self.source_address
if self.socket_options:
extra_kw['socket_options'] = self.socket_options
try:
conn = socks.create_connection(
(self.host, self.port),
proxy_type=self._socks_options['socks_version'],
proxy_addr=self._socks_options['proxy_host'],
proxy_port=self._socks_options['proxy_port'],
proxy_username=self._socks_options['username'],
proxy_password=self._socks_options['password'],
timeout=self.timeout,
**extra_kw
)
except SocketTimeout as e:
raise ConnectTimeoutError(
self, "Connection to %s timed out. (connect timeout=%s)" %
(self.host, self.timeout))
except socks.ProxyError as e:
# This is fragile as hell, but it seems to be the only way to raise
# useful errors here.
if e.socket_err:
error = e.socket_err
if isinstance(error, SocketTimeout):
raise ConnectTimeoutError(
self,
"Connection to %s timed out. (connect timeout=%s)" %
(self.host, self.timeout)
)
else:
raise NewConnectionError(
self,
"Failed to establish a new connection: %s" % error
)
else:
raise NewConnectionError(
self,
"Failed to establish a new connection: %s" % e
)
except SocketError as e: # Defensive: PySocks should catch all these.
raise NewConnectionError(
self, "Failed to establish a new connection: %s" % e)
return conn
# We don't need to duplicate the Verified/Unverified distinction from
# urllib3/connection.py here because the HTTPSConnection will already have been
# correctly set to either the Verified or Unverified form by that module. This
# means the SOCKSHTTPSConnection will automatically be the correct type.
class SOCKSHTTPSConnection(SOCKSConnection, HTTPSConnection):
pass
class SOCKSHTTPConnectionPool(HTTPConnectionPool):
ConnectionCls = SOCKSConnection
class SOCKSHTTPSConnectionPool(HTTPSConnectionPool):
ConnectionCls = SOCKSHTTPSConnection
class SOCKSProxyManager(PoolManager):
"""
A version of the urllib3 ProxyManager that routes connections via the
defined SOCKS proxy.
"""
pool_classes_by_scheme = {
'http': SOCKSHTTPConnectionPool,
'https': SOCKSHTTPSConnectionPool,
}
def __init__(self, proxy_url, username=None, password=None,
num_pools=10, headers=None, **connection_pool_kw):
parsed = parse_url(proxy_url)
if parsed.scheme == 'socks5':
socks_version = socks.PROXY_TYPE_SOCKS5
elif parsed.scheme == 'socks4':
socks_version = socks.PROXY_TYPE_SOCKS4
else:
raise ValueError(
"Unable to determine SOCKS version from %s" % proxy_url
)
self.proxy_url = proxy_url
socks_options = {
'socks_version': socks_version,
'proxy_host': parsed.host,
'proxy_port': parsed.port,
'username': username,
'password': password,
}
connection_pool_kw['_socks_options'] = socks_options
super(SOCKSProxyManager, self).__init__(
num_pools, headers, **connection_pool_kw
)
self.pool_classes_by_scheme = SOCKSProxyManager.pool_classes_by_scheme

View file

@ -1,16 +1,17 @@
from __future__ import absolute_import
# Base Exceptions
## Base Exceptions
class HTTPError(Exception): class HTTPError(Exception):
"Base exception used by this module." "Base exception used by this module."
pass pass
class HTTPWarning(Warning): class HTTPWarning(Warning):
"Base warning used by this module." "Base warning used by this module."
pass pass
class PoolError(HTTPError): class PoolError(HTTPError):
"Base exception for errors caused within a pool." "Base exception for errors caused within a pool."
def __init__(self, pool, message): def __init__(self, pool, message):
@ -57,7 +58,7 @@ class ProtocolError(HTTPError):
ConnectionError = ProtocolError ConnectionError = ProtocolError
## Leaf Exceptions # Leaf Exceptions
class MaxRetryError(RequestError): class MaxRetryError(RequestError):
"""Raised when the maximum number of retries is exceeded. """Raised when the maximum number of retries is exceeded.
@ -113,6 +114,11 @@ class ConnectTimeoutError(TimeoutError):
pass pass
class NewConnectionError(ConnectTimeoutError, PoolError):
"Raised when we fail to establish a new connection. Usually ECONNREFUSED."
pass
class EmptyPoolError(PoolError): class EmptyPoolError(PoolError):
"Raised when a pool runs out of connections and no more are allowed." "Raised when a pool runs out of connections and no more are allowed."
pass pass
@ -149,6 +155,11 @@ class SecurityWarning(HTTPWarning):
pass pass
class SubjectAltNameWarning(SecurityWarning):
"Warned when connecting to a host with a certificate missing a SAN."
pass
class InsecureRequestWarning(SecurityWarning): class InsecureRequestWarning(SecurityWarning):
"Warned when making an unverified HTTPS request." "Warned when making an unverified HTTPS request."
pass pass
@ -157,3 +168,42 @@ class InsecureRequestWarning(SecurityWarning):
class SystemTimeWarning(SecurityWarning): class SystemTimeWarning(SecurityWarning):
"Warned when system time is suspected to be wrong" "Warned when system time is suspected to be wrong"
pass pass
class InsecurePlatformWarning(SecurityWarning):
"Warned when certain SSL configuration is not available on a platform."
pass
class SNIMissingWarning(HTTPWarning):
"Warned when making a HTTPS request without SNI available."
pass
class DependencyWarning(HTTPWarning):
"""
Warned when an attempt is made to import a module with missing optional
dependencies.
"""
pass
class ResponseNotChunked(ProtocolError, ValueError):
"Response needs to be chunked in order to read it as chunks."
pass
class ProxySchemeUnknown(AssertionError, ValueError):
"ProxyManager does not support the supplied scheme"
# TODO(t-8ch): Stop inheriting from AssertionError in v2.0.
def __init__(self, scheme):
message = "Not supported proxy scheme %s" % scheme
super(ProxySchemeUnknown, self).__init__(message)
class HeaderParsingError(HTTPError):
"Raised by assert_header_parsing, but we convert it to a log.warning statement."
def __init__(self, defects, unparsed_data):
message = '%s, unparsed data: %r' % (defects or 'Unknown', unparsed_data)
super(HeaderParsingError, self).__init__(message)

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import email.utils import email.utils
import mimetypes import mimetypes
@ -35,11 +36,11 @@ def format_header_param(name, value):
result = '%s="%s"' % (name, value) result = '%s="%s"' % (name, value)
try: try:
result.encode('ascii') result.encode('ascii')
except UnicodeEncodeError: except (UnicodeEncodeError, UnicodeDecodeError):
pass pass
else: else:
return result return result
if not six.PY3: # Python 2: if not six.PY3 and isinstance(value, six.text_type): # Python 2:
value = value.encode('utf-8') value = value.encode('utf-8')
value = email.utils.encode_rfc2231(value, 'utf-8') value = email.utils.encode_rfc2231(value, 'utf-8')
value = '%s*=%s' % (name, value) value = '%s*=%s' % (name, value)

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import codecs import codecs
from uuid import uuid4 from uuid import uuid4

View file

@ -2,3 +2,4 @@ from __future__ import absolute_import
from . import ssl_match_hostname from . import ssl_match_hostname
__all__ = ('ssl_match_hostname', )

View file

@ -0,0 +1,53 @@
# -*- coding: utf-8 -*-
"""
backports.makefile
~~~~~~~~~~~~~~~~~~
Backports the Python 3 ``socket.makefile`` method for use with anything that
wants to create a "fake" socket object.
"""
import io
from socket import SocketIO
def backport_makefile(self, mode="r", buffering=None, encoding=None,
errors=None, newline=None):
"""
Backport of ``socket.makefile`` from Python 3.5.
"""
if not set(mode) <= set(["r", "w", "b"]):
raise ValueError(
"invalid mode %r (only r, w, b allowed)" % (mode,)
)
writing = "w" in mode
reading = "r" in mode or not writing
assert reading or writing
binary = "b" in mode
rawmode = ""
if reading:
rawmode += "r"
if writing:
rawmode += "w"
raw = SocketIO(self, rawmode)
self._makefile_refs += 1
if buffering is None:
buffering = -1
if buffering < 0:
buffering = io.DEFAULT_BUFFER_SIZE
if buffering == 0:
if not binary:
raise ValueError("unbuffered streams must be binary")
return raw
if reading and writing:
buffer = io.BufferedRWPair(raw, raw, buffering)
elif reading:
buffer = io.BufferedReader(raw, buffering)
else:
assert writing
buffer = io.BufferedWriter(raw, buffering)
if binary:
return buffer
text = io.TextIOWrapper(buffer, encoding, errors, newline)
text.mode = mode
return text

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import logging import logging
try: # Python 3 try: # Python 3
@ -8,7 +9,7 @@ except ImportError:
from ._collections import RecentlyUsedContainer from ._collections import RecentlyUsedContainer
from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool
from .connectionpool import port_by_scheme from .connectionpool import port_by_scheme
from .exceptions import LocationValueError from .exceptions import LocationValueError, MaxRetryError, ProxySchemeUnknown
from .request import RequestMethods from .request import RequestMethods
from .util.url import parse_url from .util.url import parse_url
from .util.retry import Retry from .util.retry import Retry
@ -17,16 +18,16 @@ from .util.retry import Retry
__all__ = ['PoolManager', 'ProxyManager', 'proxy_from_url'] __all__ = ['PoolManager', 'ProxyManager', 'proxy_from_url']
log = logging.getLogger(__name__)
SSL_KEYWORDS = ('key_file', 'cert_file', 'cert_reqs', 'ca_certs',
'ssl_version', 'ca_cert_dir')
pool_classes_by_scheme = { pool_classes_by_scheme = {
'http': HTTPConnectionPool, 'http': HTTPConnectionPool,
'https': HTTPSConnectionPool, 'https': HTTPSConnectionPool,
} }
log = logging.getLogger(__name__)
SSL_KEYWORDS = ('key_file', 'cert_file', 'cert_reqs', 'ca_certs',
'ssl_version')
class PoolManager(RequestMethods): class PoolManager(RequestMethods):
""" """
@ -64,6 +65,17 @@ class PoolManager(RequestMethods):
self.pools = RecentlyUsedContainer(num_pools, self.pools = RecentlyUsedContainer(num_pools,
dispose_func=lambda p: p.close()) dispose_func=lambda p: p.close())
# Locally set the pool classes so other PoolManagers can override them.
self.pool_classes_by_scheme = pool_classes_by_scheme
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
self.clear()
# Return False to re-raise any potential exceptions
return False
def _new_pool(self, scheme, host, port): def _new_pool(self, scheme, host, port):
""" """
Create a new :class:`ConnectionPool` based on host, port and scheme. Create a new :class:`ConnectionPool` based on host, port and scheme.
@ -72,7 +84,7 @@ class PoolManager(RequestMethods):
by :meth:`connection_from_url` and companion methods. It is intended by :meth:`connection_from_url` and companion methods. It is intended
to be overridden for customization. to be overridden for customization.
""" """
pool_cls = pool_classes_by_scheme[scheme] pool_cls = self.pool_classes_by_scheme[scheme]
kwargs = self.connection_pool_kw kwargs = self.connection_pool_kw
if scheme == 'http': if scheme == 'http':
kwargs = self.connection_pool_kw.copy() kwargs = self.connection_pool_kw.copy()
@ -167,10 +179,17 @@ class PoolManager(RequestMethods):
if not isinstance(retries, Retry): if not isinstance(retries, Retry):
retries = Retry.from_int(retries, redirect=redirect) retries = Retry.from_int(retries, redirect=redirect)
kw['retries'] = retries.increment(method, redirect_location) try:
retries = retries.increment(method, url, response=response, _pool=conn)
except MaxRetryError:
if retries.raise_on_redirect:
raise
return response
kw['retries'] = retries
kw['redirect'] = redirect kw['redirect'] = redirect
log.info("Redirecting %s -> %s" % (url, redirect_location)) log.info("Redirecting %s -> %s", url, redirect_location)
return self.urlopen(method, redirect_location, **kw) return self.urlopen(method, redirect_location, **kw)
@ -212,8 +231,8 @@ class ProxyManager(PoolManager):
port = port_by_scheme.get(proxy.scheme, 80) port = port_by_scheme.get(proxy.scheme, 80)
proxy = proxy._replace(port=port) proxy = proxy._replace(port=port)
assert proxy.scheme in ("http", "https"), \ if proxy.scheme not in ("http", "https"):
'Not supported proxy scheme %s' % proxy.scheme raise ProxySchemeUnknown(proxy.scheme)
self.proxy = proxy self.proxy = proxy
self.proxy_headers = proxy_headers or {} self.proxy_headers = proxy_headers or {}

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
try: try:
from urllib.parse import urlencode from urllib.parse import urlencode
except ImportError: except ImportError:
@ -71,14 +72,22 @@ class RequestMethods(object):
headers=headers, headers=headers,
**urlopen_kw) **urlopen_kw)
def request_encode_url(self, method, url, fields=None, **urlopen_kw): def request_encode_url(self, method, url, fields=None, headers=None,
**urlopen_kw):
""" """
Make a request using :meth:`urlopen` with the ``fields`` encoded in Make a request using :meth:`urlopen` with the ``fields`` encoded in
the url. This is useful for request methods like GET, HEAD, DELETE, etc. the url. This is useful for request methods like GET, HEAD, DELETE, etc.
""" """
if headers is None:
headers = self.headers
extra_kw = {'headers': headers}
extra_kw.update(urlopen_kw)
if fields: if fields:
url += '?' + urlencode(fields) url += '?' + urlencode(fields)
return self.urlopen(method, url, **urlopen_kw)
return self.urlopen(method, url, **extra_kw)
def request_encode_body(self, method, url, fields=None, headers=None, def request_encode_body(self, method, url, fields=None, headers=None,
encode_multipart=True, multipart_boundary=None, encode_multipart=True, multipart_boundary=None,
@ -125,7 +134,8 @@ class RequestMethods(object):
if fields: if fields:
if 'body' in urlopen_kw: if 'body' in urlopen_kw:
raise TypeError('request got values for both \'fields\' and \'body\', can only specify one.') raise TypeError(
"request got values for both 'fields' and 'body', can only specify one.")
if encode_multipart: if encode_multipart:
body, content_type = encode_multipart_formdata(fields, boundary=multipart_boundary) body, content_type = encode_multipart_formdata(fields, boundary=multipart_boundary)

View file

@ -1,13 +1,18 @@
from __future__ import absolute_import
from contextlib import contextmanager
import zlib import zlib
import io import io
from socket import timeout as SocketTimeout from socket import timeout as SocketTimeout
from socket import error as SocketError
from ._collections import HTTPHeaderDict from ._collections import HTTPHeaderDict
from .exceptions import ProtocolError, DecodeError, ReadTimeoutError from .exceptions import (
from .packages.six import string_types as basestring, binary_type ProtocolError, DecodeError, ReadTimeoutError, ResponseNotChunked
)
from .packages.six import string_types as basestring, binary_type, PY3
from .packages.six.moves import http_client as httplib
from .connection import HTTPException, BaseSSLError from .connection import HTTPException, BaseSSLError
from .util.response import is_fp_closed from .util.response import is_fp_closed, is_response_to_head
class DeflateDecoder(object): class DeflateDecoder(object):
@ -21,6 +26,9 @@ class DeflateDecoder(object):
return getattr(self._obj, name) return getattr(self._obj, name)
def decompress(self, data): def decompress(self, data):
if not data:
return data
if not self._first_try: if not self._first_try:
return self._obj.decompress(data) return self._obj.decompress(data)
@ -36,9 +44,23 @@ class DeflateDecoder(object):
self._data = None self._data = None
class GzipDecoder(object):
def __init__(self):
self._obj = zlib.decompressobj(16 + zlib.MAX_WBITS)
def __getattr__(self, name):
return getattr(self._obj, name)
def decompress(self, data):
if not data:
return data
return self._obj.decompress(data)
def _get_decoder(mode): def _get_decoder(mode):
if mode == 'gzip': if mode == 'gzip':
return zlib.decompressobj(16 + zlib.MAX_WBITS) return GzipDecoder()
return DeflateDecoder() return DeflateDecoder()
@ -76,9 +98,10 @@ class HTTPResponse(io.IOBase):
strict=0, preload_content=True, decode_content=True, strict=0, preload_content=True, decode_content=True,
original_response=None, pool=None, connection=None): original_response=None, pool=None, connection=None):
self.headers = HTTPHeaderDict() if isinstance(headers, HTTPHeaderDict):
if headers: self.headers = headers
self.headers.update(headers) else:
self.headers = HTTPHeaderDict(headers)
self.status = status self.status = status
self.version = version self.version = version
self.reason = reason self.reason = reason
@ -100,6 +123,16 @@ class HTTPResponse(io.IOBase):
if hasattr(body, 'read'): if hasattr(body, 'read'):
self._fp = body self._fp = body
# Are we using the chunked-style of transfer encoding?
self.chunked = False
self.chunk_left = None
tr_enc = self.headers.get('transfer-encoding', '').lower()
# Don't incur the penalty of creating a list and then discarding it
encodings = (enc.strip() for enc in tr_enc.split(","))
if "chunked" in encodings:
self.chunked = True
# If requested, preload the body.
if preload_content and not self._body: if preload_content and not self._body:
self._body = self.read(decode_content=decode_content) self._body = self.read(decode_content=decode_content)
@ -140,6 +173,102 @@ class HTTPResponse(io.IOBase):
""" """
return self._fp_bytes_read return self._fp_bytes_read
def _init_decoder(self):
"""
Set-up the _decoder attribute if necessar.
"""
# Note: content-encoding value should be case-insensitive, per RFC 7230
# Section 3.2
content_encoding = self.headers.get('content-encoding', '').lower()
if self._decoder is None and content_encoding in self.CONTENT_DECODERS:
self._decoder = _get_decoder(content_encoding)
def _decode(self, data, decode_content, flush_decoder):
"""
Decode the data passed in and potentially flush the decoder.
"""
try:
if decode_content and self._decoder:
data = self._decoder.decompress(data)
except (IOError, zlib.error) as e:
content_encoding = self.headers.get('content-encoding', '').lower()
raise DecodeError(
"Received response with content-encoding: %s, but "
"failed to decode it." % content_encoding, e)
if flush_decoder and decode_content:
data += self._flush_decoder()
return data
def _flush_decoder(self):
"""
Flushes the decoder. Should only be called if the decoder is actually
being used.
"""
if self._decoder:
buf = self._decoder.decompress(b'')
return buf + self._decoder.flush()
return b''
@contextmanager
def _error_catcher(self):
"""
Catch low-level python exceptions, instead re-raising urllib3
variants, so that low-level exceptions are not leaked in the
high-level api.
On exit, release the connection back to the pool.
"""
clean_exit = False
try:
try:
yield
except SocketTimeout:
# FIXME: Ideally we'd like to include the url in the ReadTimeoutError but
# there is yet no clean way to get at it from this context.
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except BaseSSLError as e:
# FIXME: Is there a better way to differentiate between SSLErrors?
if 'read operation timed out' not in str(e): # Defensive:
# This shouldn't happen but just in case we're missing an edge
# case, let's avoid swallowing SSL errors.
raise
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except (HTTPException, SocketError) as e:
# This includes IncompleteRead.
raise ProtocolError('Connection broken: %r' % e, e)
# If no exception is thrown, we should avoid cleaning up
# unnecessarily.
clean_exit = True
finally:
# If we didn't terminate cleanly, we need to throw away our
# connection.
if not clean_exit:
# The response may not be closed but we're not going to use it
# anymore so close it now to ensure that the connection is
# released back to the pool.
if self._original_response:
self._original_response.close()
# Closing the response may not actually be sufficient to close
# everything, so if we have a hold of the connection close that
# too.
if self._connection:
self._connection.close()
# If we hold the original response but it's closed now, we should
# return the connection back to the pool.
if self._original_response and self._original_response.isclosed():
self.release_conn()
def read(self, amt=None, decode_content=None, cache_content=False): def read(self, amt=None, decode_content=None, cache_content=False):
""" """
Similar to :meth:`httplib.HTTPResponse.read`, but with two additional Similar to :meth:`httplib.HTTPResponse.read`, but with two additional
@ -161,12 +290,7 @@ class HTTPResponse(io.IOBase):
after having ``.read()`` the file object. (Overridden if ``amt`` is after having ``.read()`` the file object. (Overridden if ``amt`` is
set.) set.)
""" """
# Note: content-encoding value should be case-insensitive, per RFC 7230 self._init_decoder()
# Section 3.2
content_encoding = self.headers.get('content-encoding', '').lower()
if self._decoder is None:
if content_encoding in self.CONTENT_DECODERS:
self._decoder = _get_decoder(content_encoding)
if decode_content is None: if decode_content is None:
decode_content = self.decode_content decode_content = self.decode_content
@ -174,67 +298,36 @@ class HTTPResponse(io.IOBase):
return return
flush_decoder = False flush_decoder = False
data = None
try: with self._error_catcher():
try: if amt is None:
if amt is None: # cStringIO doesn't like amt=None
# cStringIO doesn't like amt=None data = self._fp.read()
data = self._fp.read() flush_decoder = True
else:
cache_content = False
data = self._fp.read(amt)
if amt != 0 and not data: # Platform-specific: Buggy versions of Python.
# Close the connection when no data is returned
#
# This is redundant to what httplib/http.client _should_
# already do. However, versions of python released before
# December 15, 2012 (http://bugs.python.org/issue16298) do
# not properly close the connection in all cases. There is
# no harm in redundantly calling close.
self._fp.close()
flush_decoder = True flush_decoder = True
else:
cache_content = False
data = self._fp.read(amt)
if amt != 0 and not data: # Platform-specific: Buggy versions of Python.
# Close the connection when no data is returned
#
# This is redundant to what httplib/http.client _should_
# already do. However, versions of python released before
# December 15, 2012 (http://bugs.python.org/issue16298) do
# not properly close the connection in all cases. There is
# no harm in redundantly calling close.
self._fp.close()
flush_decoder = True
except SocketTimeout:
# FIXME: Ideally we'd like to include the url in the ReadTimeoutError but
# there is yet no clean way to get at it from this context.
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except BaseSSLError as e:
# FIXME: Is there a better way to differentiate between SSLErrors?
if not 'read operation timed out' in str(e): # Defensive:
# This shouldn't happen but just in case we're missing an edge
# case, let's avoid swallowing SSL errors.
raise
raise ReadTimeoutError(self._pool, None, 'Read timed out.')
except HTTPException as e:
# This includes IncompleteRead.
raise ProtocolError('Connection broken: %r' % e, e)
if data:
self._fp_bytes_read += len(data) self._fp_bytes_read += len(data)
try: data = self._decode(data, decode_content, flush_decoder)
if decode_content and self._decoder:
data = self._decoder.decompress(data)
except (IOError, zlib.error) as e:
raise DecodeError(
"Received response with content-encoding: %s, but "
"failed to decode it." % content_encoding, e)
if flush_decoder and decode_content and self._decoder:
buf = self._decoder.decompress(binary_type())
data += buf + self._decoder.flush()
if cache_content: if cache_content:
self._body = data self._body = data
return data return data
finally:
if self._original_response and self._original_response.isclosed():
self.release_conn()
def stream(self, amt=2**16, decode_content=None): def stream(self, amt=2**16, decode_content=None):
""" """
@ -252,11 +345,15 @@ class HTTPResponse(io.IOBase):
If True, will attempt to decode the body based on the If True, will attempt to decode the body based on the
'content-encoding' header. 'content-encoding' header.
""" """
while not is_fp_closed(self._fp): if self.chunked:
data = self.read(amt=amt, decode_content=decode_content) for line in self.read_chunked(amt, decode_content=decode_content):
yield line
else:
while not is_fp_closed(self._fp):
data = self.read(amt=amt, decode_content=decode_content)
if data: if data:
yield data yield data
@classmethod @classmethod
def from_httplib(ResponseCls, r, **response_kw): def from_httplib(ResponseCls, r, **response_kw):
@ -267,14 +364,17 @@ class HTTPResponse(io.IOBase):
Remaining parameters are passed to the HTTPResponse constructor, along Remaining parameters are passed to the HTTPResponse constructor, along
with ``original_response=r``. with ``original_response=r``.
""" """
headers = r.msg
headers = HTTPHeaderDict() if not isinstance(headers, HTTPHeaderDict):
for k, v in r.getheaders(): if PY3: # Python 3
headers.add(k, v) headers = HTTPHeaderDict(headers.items())
else: # Python 2
headers = HTTPHeaderDict.from_httplib(headers)
# HTTPResponse objects in Python 3 don't have a .strict attribute # HTTPResponse objects in Python 3 don't have a .strict attribute
strict = getattr(r, 'strict', 0) strict = getattr(r, 'strict', 0)
return ResponseCls(body=r, resp = ResponseCls(body=r,
headers=headers, headers=headers,
status=r.status, status=r.status,
version=r.version, version=r.version,
@ -282,6 +382,7 @@ class HTTPResponse(io.IOBase):
strict=strict, strict=strict,
original_response=r, original_response=r,
**response_kw) **response_kw)
return resp
# Backwards-compatibility methods for httplib.HTTPResponse # Backwards-compatibility methods for httplib.HTTPResponse
def getheaders(self): def getheaders(self):
@ -295,6 +396,9 @@ class HTTPResponse(io.IOBase):
if not self.closed: if not self.closed:
self._fp.close() self._fp.close()
if self._connection:
self._connection.close()
@property @property
def closed(self): def closed(self):
if self._fp is None: if self._fp is None:
@ -331,3 +435,92 @@ class HTTPResponse(io.IOBase):
else: else:
b[:len(temp)] = temp b[:len(temp)] = temp
return len(temp) return len(temp)
def _update_chunk_length(self):
# First, we'll figure out length of a chunk and then
# we'll try to read it from socket.
if self.chunk_left is not None:
return
line = self._fp.fp.readline()
line = line.split(b';', 1)[0]
try:
self.chunk_left = int(line, 16)
except ValueError:
# Invalid chunked protocol response, abort.
self.close()
raise httplib.IncompleteRead(line)
def _handle_chunk(self, amt):
returned_chunk = None
if amt is None:
chunk = self._fp._safe_read(self.chunk_left)
returned_chunk = chunk
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
elif amt < self.chunk_left:
value = self._fp._safe_read(amt)
self.chunk_left = self.chunk_left - amt
returned_chunk = value
elif amt == self.chunk_left:
value = self._fp._safe_read(amt)
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
returned_chunk = value
else: # amt > self.chunk_left
returned_chunk = self._fp._safe_read(self.chunk_left)
self._fp._safe_read(2) # Toss the CRLF at the end of the chunk.
self.chunk_left = None
return returned_chunk
def read_chunked(self, amt=None, decode_content=None):
"""
Similar to :meth:`HTTPResponse.read`, but with an additional
parameter: ``decode_content``.
:param decode_content:
If True, will attempt to decode the body based on the
'content-encoding' header.
"""
self._init_decoder()
# FIXME: Rewrite this method and make it a class with a better structured logic.
if not self.chunked:
raise ResponseNotChunked(
"Response is not chunked. "
"Header 'transfer-encoding: chunked' is missing.")
# Don't bother reading the body of a HEAD request.
if self._original_response and is_response_to_head(self._original_response):
self._original_response.close()
return
with self._error_catcher():
while True:
self._update_chunk_length()
if self.chunk_left == 0:
break
chunk = self._handle_chunk(amt)
decoded = self._decode(chunk, decode_content=decode_content,
flush_decoder=False)
if decoded:
yield decoded
if decode_content:
# On CPython and PyPy, we should never need to flush the
# decoder. However, on Jython we *might* need to, so
# lets defensively do it anyway.
decoded = self._flush_decoder()
if decoded: # Platform-specific: Jython.
yield decoded
# Chunk content ends with \r\n: discard it.
while True:
line = self._fp.fp.readline()
if not line:
# Some sites may not end with '\r\n'.
break
if line == b'\r\n':
break
# We read everything; close the "file".
if self._original_response:
self._original_response.close()

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
# For backwards compatibility, provide imports that used to be here. # For backwards compatibility, provide imports that used to be here.
from .connection import is_connection_dropped from .connection import is_connection_dropped
from .request import make_headers from .request import make_headers
@ -5,6 +6,7 @@ from .response import is_fp_closed
from .ssl_ import ( from .ssl_ import (
SSLContext, SSLContext,
HAS_SNI, HAS_SNI,
IS_PYOPENSSL,
assert_fingerprint, assert_fingerprint,
resolve_cert_reqs, resolve_cert_reqs,
resolve_ssl_version, resolve_ssl_version,
@ -22,3 +24,23 @@ from .url import (
split_first, split_first,
Url, Url,
) )
__all__ = (
'HAS_SNI',
'IS_PYOPENSSL',
'SSLContext',
'Retry',
'Timeout',
'Url',
'assert_fingerprint',
'current_time',
'is_connection_dropped',
'is_fp_closed',
'get_host',
'parse_url',
'make_headers',
'resolve_cert_reqs',
'resolve_ssl_version',
'split_first',
'ssl_wrap_socket',
)

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import socket import socket
try: try:
from select import poll, POLLIN from select import poll, POLLIN
@ -60,6 +61,8 @@ def create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
""" """
host, port = address host, port = address
if host.startswith('['):
host = host.strip('[]')
err = None err = None
for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM): for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res af, socktype, proto, canonname, sa = res
@ -78,15 +81,16 @@ def create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
sock.connect(sa) sock.connect(sa)
return sock return sock
except socket.error as _: except socket.error as e:
err = _ err = e
if sock is not None: if sock is not None:
sock.close() sock.close()
sock = None
if err is not None: if err is not None:
raise err raise err
else:
raise socket.error("getaddrinfo returns an empty list") raise socket.error("getaddrinfo returns an empty list")
def _set_socket_options(sock, options): def _set_socket_options(sock, options):

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
from base64 import b64encode from base64 import b64encode
from ..packages.six import b from ..packages.six import b

View file

@ -1,3 +1,9 @@
from __future__ import absolute_import
from ..packages.six.moves import http_client as httplib
from ..exceptions import HeaderParsingError
def is_fp_closed(obj): def is_fp_closed(obj):
""" """
Checks whether a given file-like object is closed. Checks whether a given file-like object is closed.
@ -20,3 +26,49 @@ def is_fp_closed(obj):
pass pass
raise ValueError("Unable to determine whether fp is closed.") raise ValueError("Unable to determine whether fp is closed.")
def assert_header_parsing(headers):
"""
Asserts whether all headers have been successfully parsed.
Extracts encountered errors from the result of parsing headers.
Only works on Python 3.
:param headers: Headers to verify.
:type headers: `httplib.HTTPMessage`.
:raises urllib3.exceptions.HeaderParsingError:
If parsing errors are found.
"""
# This will fail silently if we pass in the wrong kind of parameter.
# To make debugging easier add an explicit check.
if not isinstance(headers, httplib.HTTPMessage):
raise TypeError('expected httplib.Message, got {0}.'.format(
type(headers)))
defects = getattr(headers, 'defects', None)
get_payload = getattr(headers, 'get_payload', None)
unparsed_data = None
if get_payload: # Platform-specific: Python 3.
unparsed_data = get_payload()
if defects or unparsed_data:
raise HeaderParsingError(defects=defects, unparsed_data=unparsed_data)
def is_response_to_head(response):
"""
Checks whether the request of a response has been a HEAD-request.
Handles the quirks of AppEngine.
:param conn:
:type conn: :class:`httplib.HTTPResponse`
"""
# FIXME: Can we do this somehow without accessing private httplib _method?
method = response._method
if isinstance(method, int): # Platform-specific: Appengine
return method == 3
return method.upper() == 'HEAD'

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
import time import time
import logging import logging
@ -94,13 +95,18 @@ class Retry(object):
seconds. If the backoff_factor is 0.1, then :func:`.sleep` will sleep seconds. If the backoff_factor is 0.1, then :func:`.sleep` will sleep
for [0.1s, 0.2s, 0.4s, ...] between retries. It will never be longer for [0.1s, 0.2s, 0.4s, ...] between retries. It will never be longer
than :attr:`Retry.MAX_BACKOFF`. than :attr:`Retry.BACKOFF_MAX`.
By default, backoff is disabled (set to 0). By default, backoff is disabled (set to 0).
:param bool raise_on_redirect: Whether, if the number of redirects is :param bool raise_on_redirect: Whether, if the number of redirects is
exhausted, to raise a MaxRetryError, or to return a response with a exhausted, to raise a MaxRetryError, or to return a response with a
response code in the 3xx range. response code in the 3xx range.
:param bool raise_on_status: Similar meaning to ``raise_on_redirect``:
whether we should raise an exception, or return a response,
if status falls in ``status_forcelist`` range and retries have
been exhausted.
""" """
DEFAULT_METHOD_WHITELIST = frozenset([ DEFAULT_METHOD_WHITELIST = frozenset([
@ -111,7 +117,8 @@ class Retry(object):
def __init__(self, total=10, connect=None, read=None, redirect=None, def __init__(self, total=10, connect=None, read=None, redirect=None,
method_whitelist=DEFAULT_METHOD_WHITELIST, status_forcelist=None, method_whitelist=DEFAULT_METHOD_WHITELIST, status_forcelist=None,
backoff_factor=0, raise_on_redirect=True, _observed_errors=0): backoff_factor=0, raise_on_redirect=True, raise_on_status=True,
_observed_errors=0):
self.total = total self.total = total
self.connect = connect self.connect = connect
@ -126,7 +133,8 @@ class Retry(object):
self.method_whitelist = method_whitelist self.method_whitelist = method_whitelist
self.backoff_factor = backoff_factor self.backoff_factor = backoff_factor
self.raise_on_redirect = raise_on_redirect self.raise_on_redirect = raise_on_redirect
self._observed_errors = _observed_errors # TODO: use .history instead? self.raise_on_status = raise_on_status
self._observed_errors = _observed_errors # TODO: use .history instead?
def new(self, **kw): def new(self, **kw):
params = dict( params = dict(
@ -136,6 +144,7 @@ class Retry(object):
status_forcelist=self.status_forcelist, status_forcelist=self.status_forcelist,
backoff_factor=self.backoff_factor, backoff_factor=self.backoff_factor,
raise_on_redirect=self.raise_on_redirect, raise_on_redirect=self.raise_on_redirect,
raise_on_status=self.raise_on_status,
_observed_errors=self._observed_errors, _observed_errors=self._observed_errors,
) )
params.update(kw) params.update(kw)
@ -152,7 +161,7 @@ class Retry(object):
redirect = bool(redirect) and None redirect = bool(redirect) and None
new_retries = cls(retries, redirect=redirect) new_retries = cls(retries, redirect=redirect)
log.debug("Converted retries value: %r -> %r" % (retries, new_retries)) log.debug("Converted retries value: %r -> %r", retries, new_retries)
return new_retries return new_retries
def get_backoff_time(self): def get_backoff_time(self):
@ -190,7 +199,7 @@ class Retry(object):
return isinstance(err, (ReadTimeoutError, ProtocolError)) return isinstance(err, (ReadTimeoutError, ProtocolError))
def is_forced_retry(self, method, status_code): def is_forced_retry(self, method, status_code):
""" Is this method/response retryable? (Based on method/codes whitelists) """ Is this method/status code retryable? (Based on method/codes whitelists)
""" """
if self.method_whitelist and method.upper() not in self.method_whitelist: if self.method_whitelist and method.upper() not in self.method_whitelist:
return False return False
@ -206,7 +215,8 @@ class Retry(object):
return min(retry_counts) < 0 return min(retry_counts) < 0
def increment(self, method=None, url=None, response=None, error=None, _pool=None, _stacktrace=None): def increment(self, method=None, url=None, response=None, error=None,
_pool=None, _stacktrace=None):
""" Return a new Retry object with incremented retry counters. """ Return a new Retry object with incremented retry counters.
:param response: A response object, or None, if the server did not :param response: A response object, or None, if the server did not
@ -270,11 +280,10 @@ class Retry(object):
if new_retry.is_exhausted(): if new_retry.is_exhausted():
raise MaxRetryError(_pool, url, error or ResponseError(cause)) raise MaxRetryError(_pool, url, error or ResponseError(cause))
log.debug("Incremented Retry for (url='%s'): %r" % (url, new_retry)) log.debug("Incremented Retry for (url='%s'): %r", url, new_retry)
return new_retry return new_retry
def __repr__(self): def __repr__(self):
return ('{cls.__name__}(total={self.total}, connect={self.connect}, ' return ('{cls.__name__}(total={self.total}, connect={self.connect}, '
'read={self.read}, redirect={self.redirect})').format( 'read={self.read}, redirect={self.redirect})').format(

View file

@ -1,17 +1,46 @@
from binascii import hexlify, unhexlify from __future__ import absolute_import
from hashlib import md5, sha1 import errno
import warnings
import hmac
from ..exceptions import SSLError from binascii import hexlify, unhexlify
from hashlib import md5, sha1, sha256
from ..exceptions import SSLError, InsecurePlatformWarning, SNIMissingWarning
SSLContext = None SSLContext = None
HAS_SNI = False HAS_SNI = False
create_default_context = None create_default_context = None
IS_PYOPENSSL = False
# Maps the length of a digest to a possible hash function producing this digest
HASHFUNC_MAP = {
32: md5,
40: sha1,
64: sha256,
}
def _const_compare_digest_backport(a, b):
"""
Compare two digests of equal length in constant time.
The digests must be of type str/bytes.
Returns True if the digests match, and False otherwise.
"""
result = abs(len(a) - len(b))
for l, r in zip(bytearray(a), bytearray(b)):
result |= l ^ r
return result == 0
_const_compare_digest = getattr(hmac, 'compare_digest',
_const_compare_digest_backport)
import errno
import ssl
try: # Test for SSL features try: # Test for SSL features
import ssl
from ssl import wrap_socket, CERT_NONE, PROTOCOL_SSLv23 from ssl import wrap_socket, CERT_NONE, PROTOCOL_SSLv23
from ssl import HAS_SNI # Has SNI? from ssl import HAS_SNI # Has SNI?
except ImportError: except ImportError:
@ -24,14 +53,24 @@ except ImportError:
OP_NO_SSLv2, OP_NO_SSLv3 = 0x1000000, 0x2000000 OP_NO_SSLv2, OP_NO_SSLv3 = 0x1000000, 0x2000000
OP_NO_COMPRESSION = 0x20000 OP_NO_COMPRESSION = 0x20000
try: # A secure default.
from ssl import _DEFAULT_CIPHERS # Sources for more information on TLS ciphers:
except ImportError: #
_DEFAULT_CIPHERS = ( # - https://wiki.mozilla.org/Security/Server_Side_TLS
'ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:' # - https://www.ssllabs.com/projects/best-practices/index.html
'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES:ECDH+RC4:' # - https://hynek.me/articles/hardening-your-web-servers-ssl-ciphers/
'DH+RC4:RSA+RC4:!aNULL:!eNULL:!MD5' #
) # The general intent is:
# - Prefer cipher suites that offer perfect forward secrecy (DHE/ECDHE),
# - prefer ECDHE over DHE for better performance,
# - prefer any AES-GCM over any AES-CBC for better performance and security,
# - use 3DES as fallback which is secure but slow,
# - disable NULL authentication, MD5 MACs and DSS for security reasons.
DEFAULT_CIPHERS = (
'ECDH+AESGCM:DH+AESGCM:ECDH+AES256:DH+AES256:ECDH+AES128:DH+AES:ECDH+HIGH:'
'DH+HIGH:ECDH+3DES:DH+3DES:RSA+AESGCM:RSA+AES:RSA+HIGH:RSA+3DES:!aNULL:'
'!eNULL:!MD5'
)
try: try:
from ssl import SSLContext # Modern SSL? from ssl import SSLContext # Modern SSL?
@ -39,7 +78,8 @@ except ImportError:
import sys import sys
class SSLContext(object): # Platform-specific: Python 2 & 3.1 class SSLContext(object): # Platform-specific: Python 2 & 3.1
supports_set_ciphers = sys.version_info >= (2, 7) supports_set_ciphers = ((2, 7) <= sys.version_info < (3,) or
(3, 2) <= sys.version_info)
def __init__(self, protocol_version): def __init__(self, protocol_version):
self.protocol = protocol_version self.protocol = protocol_version
@ -56,8 +96,11 @@ except ImportError:
self.certfile = certfile self.certfile = certfile
self.keyfile = keyfile self.keyfile = keyfile
def load_verify_locations(self, location): def load_verify_locations(self, cafile=None, capath=None):
self.ca_certs = location self.ca_certs = cafile
if capath is not None:
raise SSLError("CA directories not supported in older Pythons")
def set_ciphers(self, cipher_suite): def set_ciphers(self, cipher_suite):
if not self.supports_set_ciphers: if not self.supports_set_ciphers:
@ -68,13 +111,23 @@ except ImportError:
) )
self.ciphers = cipher_suite self.ciphers = cipher_suite
def wrap_socket(self, socket, server_hostname=None): def wrap_socket(self, socket, server_hostname=None, server_side=False):
warnings.warn(
'A true SSLContext object is not available. This prevents '
'urllib3 from configuring SSL appropriately and may cause '
'certain SSL connections to fail. You can upgrade to a newer '
'version of Python to solve this. For more information, see '
'https://urllib3.readthedocs.org/en/latest/security.html'
'#insecureplatformwarning.',
InsecurePlatformWarning
)
kwargs = { kwargs = {
'keyfile': self.keyfile, 'keyfile': self.keyfile,
'certfile': self.certfile, 'certfile': self.certfile,
'ca_certs': self.ca_certs, 'ca_certs': self.ca_certs,
'cert_reqs': self.verify_mode, 'cert_reqs': self.verify_mode,
'ssl_version': self.protocol, 'ssl_version': self.protocol,
'server_side': server_side,
} }
if self.supports_set_ciphers: # Platform-specific: Python 2.7+ if self.supports_set_ciphers: # Platform-specific: Python 2.7+
return wrap_socket(socket, ciphers=self.ciphers, **kwargs) return wrap_socket(socket, ciphers=self.ciphers, **kwargs)
@ -92,30 +145,21 @@ def assert_fingerprint(cert, fingerprint):
Fingerprint as string of hexdigits, can be interspersed by colons. Fingerprint as string of hexdigits, can be interspersed by colons.
""" """
# Maps the length of a digest to a possible hash function producing
# this digest.
hashfunc_map = {
16: md5,
20: sha1
}
fingerprint = fingerprint.replace(':', '').lower() fingerprint = fingerprint.replace(':', '').lower()
digest_length, odd = divmod(len(fingerprint), 2) digest_length = len(fingerprint)
hashfunc = HASHFUNC_MAP.get(digest_length)
if odd or digest_length not in hashfunc_map: if not hashfunc:
raise SSLError('Fingerprint is of invalid length.') raise SSLError(
'Fingerprint of invalid length: {0}'.format(fingerprint))
# We need encode() here for py32; works on py2 and p33. # We need encode() here for py32; works on py2 and p33.
fingerprint_bytes = unhexlify(fingerprint.encode()) fingerprint_bytes = unhexlify(fingerprint.encode())
hashfunc = hashfunc_map[digest_length]
cert_digest = hashfunc(cert).digest() cert_digest = hashfunc(cert).digest()
if not cert_digest == fingerprint_bytes: if not _const_compare_digest(cert_digest, fingerprint_bytes):
raise SSLError('Fingerprints did not match. Expected "{0}", got "{1}".' raise SSLError('Fingerprints did not match. Expected "{0}", got "{1}".'
.format(hexlify(fingerprint_bytes), .format(fingerprint, hexlify(cert_digest)))
hexlify(cert_digest)))
def resolve_cert_reqs(candidate): def resolve_cert_reqs(candidate):
@ -157,7 +201,7 @@ def resolve_ssl_version(candidate):
return candidate return candidate
def create_urllib3_context(ssl_version=None, cert_reqs=ssl.CERT_REQUIRED, def create_urllib3_context(ssl_version=None, cert_reqs=None,
options=None, ciphers=None): options=None, ciphers=None):
"""All arguments have the same meaning as ``ssl_wrap_socket``. """All arguments have the same meaning as ``ssl_wrap_socket``.
@ -194,6 +238,9 @@ def create_urllib3_context(ssl_version=None, cert_reqs=ssl.CERT_REQUIRED,
""" """
context = SSLContext(ssl_version or ssl.PROTOCOL_SSLv23) context = SSLContext(ssl_version or ssl.PROTOCOL_SSLv23)
# Setting the default here, as we may have no ssl module on import
cert_reqs = ssl.CERT_REQUIRED if cert_reqs is None else cert_reqs
if options is None: if options is None:
options = 0 options = 0
# SSLv2 is easily broken and is considered harmful and dangerous # SSLv2 is easily broken and is considered harmful and dangerous
@ -207,20 +254,23 @@ def create_urllib3_context(ssl_version=None, cert_reqs=ssl.CERT_REQUIRED,
context.options |= options context.options |= options
if getattr(context, 'supports_set_ciphers', True): # Platform-specific: Python 2.6 if getattr(context, 'supports_set_ciphers', True): # Platform-specific: Python 2.6
context.set_ciphers(ciphers or _DEFAULT_CIPHERS) context.set_ciphers(ciphers or DEFAULT_CIPHERS)
context.verify_mode = cert_reqs context.verify_mode = cert_reqs
if getattr(context, 'check_hostname', None) is not None: # Platform-specific: Python 3.2 if getattr(context, 'check_hostname', None) is not None: # Platform-specific: Python 3.2
context.check_hostname = (context.verify_mode == ssl.CERT_REQUIRED) # We do our own verification, including fingerprints and alternative
# hostnames. So disable it here
context.check_hostname = False
return context return context
def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None, def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
ca_certs=None, server_hostname=None, ca_certs=None, server_hostname=None,
ssl_version=None, ciphers=None, ssl_context=None): ssl_version=None, ciphers=None, ssl_context=None,
ca_cert_dir=None):
""" """
All arguments except for server_hostname and ssl_context have the same All arguments except for server_hostname, ssl_context, and ca_cert_dir have
meaning as they do when using :func:`ssl.wrap_socket`. the same meaning as they do when using :func:`ssl.wrap_socket`.
:param server_hostname: :param server_hostname:
When SNI is supported, the expected hostname of the certificate When SNI is supported, the expected hostname of the certificate
@ -230,15 +280,19 @@ def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
:param ciphers: :param ciphers:
A string of ciphers we wish the client to support. This is not A string of ciphers we wish the client to support. This is not
supported on Python 2.6 as the ssl module does not support it. supported on Python 2.6 as the ssl module does not support it.
:param ca_cert_dir:
A directory containing CA certificates in multiple separate files, as
supported by OpenSSL's -CApath flag or the capath argument to
SSLContext.load_verify_locations().
""" """
context = ssl_context context = ssl_context
if context is None: if context is None:
context = create_urllib3_context(ssl_version, cert_reqs, context = create_urllib3_context(ssl_version, cert_reqs,
ciphers=ciphers) ciphers=ciphers)
if ca_certs: if ca_certs or ca_cert_dir:
try: try:
context.load_verify_locations(ca_certs) context.load_verify_locations(ca_certs, ca_cert_dir)
except IOError as e: # Platform-specific: Python 2.6, 2.7, 3.2 except IOError as e: # Platform-specific: Python 2.6, 2.7, 3.2
raise SSLError(e) raise SSLError(e)
# Py33 raises FileNotFoundError which subclasses OSError # Py33 raises FileNotFoundError which subclasses OSError
@ -247,8 +301,20 @@ def ssl_wrap_socket(sock, keyfile=None, certfile=None, cert_reqs=None,
if e.errno == errno.ENOENT: if e.errno == errno.ENOENT:
raise SSLError(e) raise SSLError(e)
raise raise
if certfile: if certfile:
context.load_cert_chain(certfile, keyfile) context.load_cert_chain(certfile, keyfile)
if HAS_SNI: # Platform-specific: OpenSSL with enabled SNI if HAS_SNI: # Platform-specific: OpenSSL with enabled SNI
return context.wrap_socket(sock, server_hostname=server_hostname) return context.wrap_socket(sock, server_hostname=server_hostname)
warnings.warn(
'An HTTPS request has been made, but the SNI (Subject Name '
'Indication) extension to TLS is not available on this platform. '
'This may cause the server to present an incorrect TLS '
'certificate, which can cause validation failures. You can upgrade to '
'a newer version of Python to solve this. For more information, see '
'https://urllib3.readthedocs.org/en/latest/security.html'
'#snimissingwarning.',
SNIMissingWarning
)
return context.wrap_socket(sock) return context.wrap_socket(sock)

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
# The default socket timeout, used by httplib to indicate that no timeout was # The default socket timeout, used by httplib to indicate that no timeout was
# specified by the user # specified by the user
from socket import _GLOBAL_DEFAULT_TIMEOUT from socket import _GLOBAL_DEFAULT_TIMEOUT
@ -9,6 +10,7 @@ from ..exceptions import TimeoutStateError
# urllib3 # urllib3
_Default = object() _Default = object()
def current_time(): def current_time():
""" """
Retrieve the current time. This function is mocked out in unit testing. Retrieve the current time. This function is mocked out in unit testing.
@ -226,9 +228,9 @@ class Timeout(object):
has not yet been called on this object. has not yet been called on this object.
""" """
if (self.total is not None and if (self.total is not None and
self.total is not self.DEFAULT_TIMEOUT and self.total is not self.DEFAULT_TIMEOUT and
self._read is not None and self._read is not None and
self._read is not self.DEFAULT_TIMEOUT): self._read is not self.DEFAULT_TIMEOUT):
# In case the connect timeout has not yet been established. # In case the connect timeout has not yet been established.
if self._start_connect is None: if self._start_connect is None:
return self._read return self._read

View file

@ -1,3 +1,4 @@
from __future__ import absolute_import
from collections import namedtuple from collections import namedtuple
from ..exceptions import LocationParseError from ..exceptions import LocationParseError
@ -15,6 +16,8 @@ class Url(namedtuple('Url', url_attrs)):
def __new__(cls, scheme=None, auth=None, host=None, port=None, path=None, def __new__(cls, scheme=None, auth=None, host=None, port=None, path=None,
query=None, fragment=None): query=None, fragment=None):
if path and not path.startswith('/'):
path = '/' + path
return super(Url, cls).__new__(cls, scheme, auth, host, port, path, return super(Url, cls).__new__(cls, scheme, auth, host, port, path,
query, fragment) query, fragment)
@ -83,6 +86,7 @@ class Url(namedtuple('Url', url_attrs)):
def __str__(self): def __str__(self):
return self.url return self.url
def split_first(s, delims): def split_first(s, delims):
""" """
Given a string and an iterable of delimiters, split on the first found Given a string and an iterable of delimiters, split on the first found
@ -113,7 +117,7 @@ def split_first(s, delims):
if min_idx is None or min_idx < 0: if min_idx is None or min_idx < 0:
return s, '', None return s, '', None
return s[:min_idx], s[min_idx+1:], min_delim return s[:min_idx], s[min_idx + 1:], min_delim
def parse_url(url): def parse_url(url):
@ -204,6 +208,7 @@ def parse_url(url):
return Url(scheme, auth, host, port, path, query, fragment) return Url(scheme, auth, host, port, path, query, fragment)
def get_host(url): def get_host(url):
""" """
Deprecated. Use :func:`.parse_url` instead. Deprecated. Use :func:`.parse_url` instead.

View file

@ -62,12 +62,11 @@ def merge_setting(request_setting, session_setting, dict_class=OrderedDict):
merged_setting = dict_class(to_key_val_list(session_setting)) merged_setting = dict_class(to_key_val_list(session_setting))
merged_setting.update(to_key_val_list(request_setting)) merged_setting.update(to_key_val_list(request_setting))
# Remove keys that are set to None. # Remove keys that are set to None. Extract keys first to avoid altering
for (k, v) in request_setting.items(): # the dictionary during iteration.
if v is None: none_keys = [k for (k, v) in merged_setting.items() if v is None]
del merged_setting[k] for key in none_keys:
del merged_setting[key]
merged_setting = dict((k, v) for (k, v) in merged_setting.items() if v is not None)
return merged_setting return merged_setting
@ -90,7 +89,7 @@ def merge_hooks(request_hooks, session_hooks, dict_class=OrderedDict):
class SessionRedirectMixin(object): class SessionRedirectMixin(object):
def resolve_redirects(self, resp, req, stream=False, timeout=None, def resolve_redirects(self, resp, req, stream=False, timeout=None,
verify=True, cert=None, proxies=None): verify=True, cert=None, proxies=None, **adapter_kwargs):
"""Receives a Response. Returns a generator of Responses.""" """Receives a Response. Returns a generator of Responses."""
i = 0 i = 0
@ -111,13 +110,12 @@ class SessionRedirectMixin(object):
resp.raw.read(decode_content=False) resp.raw.read(decode_content=False)
if i >= self.max_redirects: if i >= self.max_redirects:
raise TooManyRedirects('Exceeded %s redirects.' % self.max_redirects) raise TooManyRedirects('Exceeded %s redirects.' % self.max_redirects, response=resp)
# Release the connection back into the pool. # Release the connection back into the pool.
resp.close() resp.close()
url = resp.headers['location'] url = resp.headers['location']
method = req.method
# Handle redirection without scheme (see: RFC 1808 Section 4) # Handle redirection without scheme (see: RFC 1808 Section 4)
if url.startswith('//'): if url.startswith('//'):
@ -141,22 +139,7 @@ class SessionRedirectMixin(object):
if resp.is_permanent_redirect and req.url != prepared_request.url: if resp.is_permanent_redirect and req.url != prepared_request.url:
self.redirect_cache[req.url] = prepared_request.url self.redirect_cache[req.url] = prepared_request.url
# http://tools.ietf.org/html/rfc7231#section-6.4.4 self.rebuild_method(prepared_request, resp)
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 # https://github.com/kennethreitz/requests/issues/1084
if resp.status_code not in (codes.temporary_redirect, codes.permanent_redirect): if resp.status_code not in (codes.temporary_redirect, codes.permanent_redirect):
@ -171,7 +154,10 @@ class SessionRedirectMixin(object):
except KeyError: except KeyError:
pass pass
extract_cookies_to_jar(prepared_request._cookies, prepared_request, resp.raw) # Extract any cookies sent on the response to the cookiejar
# in the new request. Because we've mutated our copied prepared
# request, use the old one that we haven't yet touched.
extract_cookies_to_jar(prepared_request._cookies, req, resp.raw)
prepared_request._cookies.update(self.cookies) prepared_request._cookies.update(self.cookies)
prepared_request.prepare_cookies(prepared_request._cookies) prepared_request.prepare_cookies(prepared_request._cookies)
@ -190,6 +176,7 @@ class SessionRedirectMixin(object):
cert=cert, cert=cert,
proxies=proxies, proxies=proxies,
allow_redirects=False, allow_redirects=False,
**adapter_kwargs
) )
extract_cookies_to_jar(self.cookies, prepared_request, resp.raw) extract_cookies_to_jar(self.cookies, prepared_request, resp.raw)
@ -259,6 +246,28 @@ class SessionRedirectMixin(object):
return new_proxies return new_proxies
def rebuild_method(self, prepared_request, response):
"""When being redirected we may want to change the method of the request
based on certain specs or browser behavior.
"""
method = prepared_request.method
# http://tools.ietf.org/html/rfc7231#section-6.4.4
if response.status_code == codes.see_other and method != 'HEAD':
method = 'GET'
# Do what the browsers do, despite standards...
# First, turn 302s into GETs.
if response.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 response.status_code == codes.moved and method == 'POST':
method = 'GET'
prepared_request.method = method
class Session(SessionRedirectMixin): class Session(SessionRedirectMixin):
"""A Requests session. """A Requests session.
@ -270,7 +279,13 @@ class Session(SessionRedirectMixin):
>>> import requests >>> import requests
>>> s = requests.Session() >>> s = requests.Session()
>>> s.get('http://httpbin.org/get') >>> s.get('http://httpbin.org/get')
200 <Response [200]>
Or as a context manager::
>>> with requests.Session() as s:
>>> s.get('http://httpbin.org/get')
<Response [200]>
""" """
__attrs__ = [ __attrs__ = [
@ -290,9 +305,9 @@ class Session(SessionRedirectMixin):
#: :class:`Request <Request>`. #: :class:`Request <Request>`.
self.auth = None self.auth = None
#: Dictionary mapping protocol to the URL of the proxy (e.g. #: Dictionary mapping protocol or protocol and host to the URL of the proxy
#: {'http': 'foo.bar:3128'}) to be used on each #: (e.g. {'http': 'foo.bar:3128', 'http://host.name': 'foo.bar:4012'}) to
#: :class:`Request <Request>`. #: be used on each :class:`Request <Request>`.
self.proxies = {} self.proxies = {}
#: Event-handling hooks. #: Event-handling hooks.
@ -316,7 +331,8 @@ class Session(SessionRedirectMixin):
#: limit, a :class:`TooManyRedirects` exception is raised. #: limit, a :class:`TooManyRedirects` exception is raised.
self.max_redirects = DEFAULT_REDIRECT_LIMIT self.max_redirects = DEFAULT_REDIRECT_LIMIT
#: Should we trust the environment? #: Trust environment settings for proxy configuration, default
#: authentication and similar.
self.trust_env = True self.trust_env = True
#: A CookieJar containing all currently outstanding cookies set on this #: A CookieJar containing all currently outstanding cookies set on this
@ -401,8 +417,8 @@ class Session(SessionRedirectMixin):
:param url: URL 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 :param params: (optional) Dictionary or bytes to be sent in the query
string for the :class:`Request`. string for the :class:`Request`.
:param data: (optional) Dictionary or bytes to send in the body of the :param data: (optional) Dictionary, bytes, or file-like object to send
:class:`Request`. in the body of the :class:`Request`.
:param json: (optional) json to send in the body of the :param json: (optional) json to send in the body of the
:class:`Request`. :class:`Request`.
:param headers: (optional) Dictionary of HTTP Headers to send with the :param headers: (optional) Dictionary of HTTP Headers to send with the
@ -414,23 +430,21 @@ class Session(SessionRedirectMixin):
:param auth: (optional) Auth tuple or callable to enable :param auth: (optional) Auth tuple or callable to enable
Basic/Digest/Custom HTTP Auth. Basic/Digest/Custom HTTP Auth.
:param timeout: (optional) How long to wait for the server to send :param timeout: (optional) How long to wait for the server to send
data before giving up, as a float, or a (`connect timeout, read data before giving up, as a float, or a :ref:`(connect timeout,
timeout <user/advanced.html#timeouts>`_) tuple. read timeout) <timeouts>` tuple.
:type timeout: float or tuple :type timeout: float or tuple
:param allow_redirects: (optional) Set to True by default. :param allow_redirects: (optional) Set to True by default.
:type allow_redirects: bool :type allow_redirects: bool
:param proxies: (optional) Dictionary mapping protocol to the URL of :param proxies: (optional) Dictionary mapping protocol or protocol and
the proxy. hostname to the URL of the proxy.
:param stream: (optional) whether to immediately download the response :param stream: (optional) whether to immediately download the response
content. Defaults to ``False``. content. Defaults to ``False``.
:param verify: (optional) if ``True``, the SSL cert will be verified. :param verify: (optional) whether the SSL cert will be verified.
A CA_BUNDLE path can also be provided. A CA_BUNDLE path can also be provided. Defaults to ``True``.
:param cert: (optional) if String, path to ssl client cert file (.pem). :param cert: (optional) if String, path to ssl client cert file (.pem).
If Tuple, ('cert', 'key') pair. If Tuple, ('cert', 'key') pair.
""" :rtype: requests.Response
"""
method = to_native_string(method)
# Create the Request. # Create the Request.
req = Request( req = Request(
method = method.upper(), method = method.upper(),
@ -543,26 +557,24 @@ class Session(SessionRedirectMixin):
# It's possible that users might accidentally send a Request object. # It's possible that users might accidentally send a Request object.
# Guard against that specific failure case. # Guard against that specific failure case.
if not isinstance(request, PreparedRequest): if isinstance(request, Request):
raise ValueError('You can only send PreparedRequests.') 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 # Set up variables needed for resolve_redirects and dispatching of hooks
allow_redirects = kwargs.pop('allow_redirects', True) allow_redirects = kwargs.pop('allow_redirects', True)
stream = kwargs.get('stream') stream = kwargs.get('stream')
timeout = kwargs.get('timeout')
verify = kwargs.get('verify')
cert = kwargs.get('cert')
proxies = kwargs.get('proxies')
hooks = request.hooks hooks = request.hooks
# Resolve URL in redirect cache, if available.
if allow_redirects:
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
# Get the appropriate adapter to use # Get the appropriate adapter to use
adapter = self.get_adapter(url=request.url) adapter = self.get_adapter(url=request.url)
@ -588,12 +600,7 @@ class Session(SessionRedirectMixin):
extract_cookies_to_jar(self.cookies, request, r.raw) extract_cookies_to_jar(self.cookies, request, r.raw)
# Redirect resolving generator. # Redirect resolving generator.
gen = self.resolve_redirects(r, request, gen = self.resolve_redirects(r, request, **kwargs)
stream=stream,
timeout=timeout,
verify=verify,
cert=cert,
proxies=proxies)
# Resolve redirects if allowed. # Resolve redirects if allowed.
history = [resp for resp in gen] if allow_redirects else [] history = [resp for resp in gen] if allow_redirects else []
@ -636,7 +643,7 @@ class Session(SessionRedirectMixin):
'cert': cert} 'cert': cert}
def get_adapter(self, url): def get_adapter(self, url):
"""Returns the appropriate connnection adapter for the given URL.""" """Returns the appropriate connection adapter for the given URL."""
for (prefix, adapter) in self.adapters.items(): for (prefix, adapter) in self.adapters.items():
if url.lower().startswith(prefix): if url.lower().startswith(prefix):

View file

@ -53,6 +53,7 @@ _codes = {
416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'), 416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'),
417: ('expectation_failed',), 417: ('expectation_failed',),
418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'), 418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'),
421: ('misdirected_request',),
422: ('unprocessable_entity', 'unprocessable'), 422: ('unprocessable_entity', 'unprocessable'),
423: ('locked',), 423: ('locked',),
424: ('failed_dependency', 'dependency'), 424: ('failed_dependency', 'dependency'),
@ -78,11 +79,12 @@ _codes = {
507: ('insufficient_storage',), 507: ('insufficient_storage',),
509: ('bandwidth_limit_exceeded', 'bandwidth'), 509: ('bandwidth_limit_exceeded', 'bandwidth'),
510: ('not_extended',), 510: ('not_extended',),
511: ('network_authentication_required', 'network_auth', 'network_authentication'),
} }
codes = LookupDict(name='status_codes') codes = LookupDict(name='status_codes')
for (code, titles) in list(_codes.items()): for code, titles in _codes.items():
for title in titles: for title in titles:
setattr(codes, title, code) setattr(codes, title, code)
if not title.startswith('\\'): if not title.startswith('\\'):

View file

@ -10,6 +10,8 @@ Data structures that power Requests.
import collections import collections
from .compat import OrderedDict
class CaseInsensitiveDict(collections.MutableMapping): class CaseInsensitiveDict(collections.MutableMapping):
""" """
@ -40,7 +42,7 @@ class CaseInsensitiveDict(collections.MutableMapping):
""" """
def __init__(self, data=None, **kwargs): def __init__(self, data=None, **kwargs):
self._store = dict() self._store = OrderedDict()
if data is None: if data is None:
data = {} data = {}
self.update(data, **kwargs) self.update(data, **kwargs)

View file

@ -14,9 +14,7 @@ import codecs
import collections import collections
import io import io
import os import os
import platform
import re import re
import sys
import socket import socket
import struct import struct
import warnings import warnings
@ -25,10 +23,11 @@ from . import __version__
from . import certs from . import certs
from .compat import parse_http_list as _parse_list_header from .compat import parse_http_list as _parse_list_header
from .compat import (quote, urlparse, bytes, str, OrderedDict, unquote, is_py2, from .compat import (quote, urlparse, bytes, str, OrderedDict, unquote, is_py2,
builtin_str, getproxies, proxy_bypass, urlunparse) builtin_str, getproxies, proxy_bypass, urlunparse,
basestring)
from .cookies import RequestsCookieJar, cookiejar_from_dict from .cookies import RequestsCookieJar, cookiejar_from_dict
from .structures import CaseInsensitiveDict from .structures import CaseInsensitiveDict
from .exceptions import InvalidURL from .exceptions import InvalidURL, FileModeWarning
_hush_pyflakes = (RequestsCookieJar,) _hush_pyflakes = (RequestsCookieJar,)
@ -47,26 +46,54 @@ def dict_to_sequence(d):
def super_len(o): def super_len(o):
total_length = 0
current_position = 0
if hasattr(o, '__len__'): if hasattr(o, '__len__'):
return len(o) total_length = len(o)
if hasattr(o, 'len'): elif hasattr(o, 'len'):
return o.len total_length = o.len
if hasattr(o, 'fileno'): elif hasattr(o, 'getvalue'):
# e.g. BytesIO, cStringIO.StringIO
total_length = len(o.getvalue())
elif hasattr(o, 'fileno'):
try: try:
fileno = o.fileno() fileno = o.fileno()
except io.UnsupportedOperation: except io.UnsupportedOperation:
pass pass
else: else:
return os.fstat(fileno).st_size total_length = os.fstat(fileno).st_size
if hasattr(o, 'getvalue'): # Having used fstat to determine the file length, we need to
# e.g. BytesIO, cStringIO.StringIO # confirm that this file was opened up in binary mode.
return len(o.getvalue()) if 'b' not in o.mode:
warnings.warn((
"Requests has determined the content-length for this "
"request using the binary size of the file: however, the "
"file has been opened in text mode (i.e. without the 'b' "
"flag in the mode). This may lead to an incorrect "
"content-length. In Requests 3.0, support will be removed "
"for files in text mode."),
FileModeWarning
)
if hasattr(o, 'tell'):
try:
current_position = o.tell()
except (OSError, IOError):
# This can happen in some weird situations, such as when the file
# is actually a special file descriptor like stdin. In this
# instance, we don't know what the length is, so set it to zero and
# let requests chunk it instead.
current_position = total_length
return max(0, total_length - current_position)
def get_netrc_auth(url): def get_netrc_auth(url, raise_errors=False):
"""Returns the Requests tuple auth for a given url from netrc.""" """Returns the Requests tuple auth for a given url from netrc."""
try: try:
@ -93,8 +120,12 @@ def get_netrc_auth(url):
ri = urlparse(url) ri = urlparse(url)
# Strip port numbers from netloc # Strip port numbers from netloc. This weird `if...encode`` dance is
host = ri.netloc.split(':')[0] # used for Python 3.2, which doesn't support unicode literals.
splitstr = b':'
if isinstance(url, str):
splitstr = splitstr.decode('ascii')
host = ri.netloc.split(splitstr)[0]
try: try:
_netrc = netrc(netrc_path).authenticators(host) _netrc = netrc(netrc_path).authenticators(host)
@ -104,8 +135,9 @@ def get_netrc_auth(url):
return (_netrc[login_i], _netrc[2]) return (_netrc[login_i], _netrc[2])
except (NetrcParseError, IOError): except (NetrcParseError, IOError):
# If there was a parsing error or a permissions issue reading the file, # If there was a parsing error or a permissions issue reading the file,
# we'll just skip netrc auth # we'll just skip netrc auth unless explicitly asked to raise errors.
pass if raise_errors:
raise
# AppEngine hackiness. # AppEngine hackiness.
except (ImportError, AttributeError): except (ImportError, AttributeError):
@ -115,7 +147,8 @@ def get_netrc_auth(url):
def guess_filename(obj): def guess_filename(obj):
"""Tries to guess the filename of the given object.""" """Tries to guess the filename of the given object."""
name = getattr(obj, 'name', None) name = getattr(obj, 'name', None)
if name and isinstance(name, builtin_str) and name[0] != '<' and name[-1] != '>': if (name and isinstance(name, basestring) and name[0] != '<' and
name[-1] != '>'):
return os.path.basename(name) return os.path.basename(name)
@ -418,10 +451,18 @@ def requote_uri(uri):
This function passes the given URI through an unquote/quote cycle to This function passes the given URI through an unquote/quote cycle to
ensure that it is fully and consistently quoted. ensure that it is fully and consistently quoted.
""" """
# Unquote only the unreserved characters safe_with_percent = "!#$%&'()*+,/:;=?@[]~"
# Then quote only illegal characters (do not quote reserved, unreserved, safe_without_percent = "!#$&'()*+,/:;=?@[]~"
# or '%') try:
return quote(unquote_unreserved(uri), safe="!#$%&'()*+,/:;=?@[]~") # Unquote only the unreserved characters
# Then quote only illegal characters (do not quote reserved,
# unreserved, or '%')
return quote(unquote_unreserved(uri), safe=safe_with_percent)
except InvalidURL:
# We couldn't unquote the given URI, so let's try quoting it, but
# there may be unquoted '%'s in the URI. We need to make sure they're
# properly quoted so they do not cause issues elsewhere.
return quote(uri, safe=safe_without_percent)
def address_in_network(ip, net): def address_in_network(ip, net):
@ -488,7 +529,9 @@ def should_bypass_proxies(url):
if no_proxy: if no_proxy:
# We need to check whether we match here. We need to see if we match # We need to check whether we match here. We need to see if we match
# the end of the netloc, both with and without the port. # the end of the netloc, both with and without the port.
no_proxy = no_proxy.replace(' ', '').split(',') no_proxy = (
host for host in no_proxy.replace(' ', '').split(',') if host
)
ip = netloc.split(':')[0] ip = netloc.split(':')[0]
if is_ipv4_address(ip): if is_ipv4_address(ip):
@ -519,6 +562,7 @@ def should_bypass_proxies(url):
return False return False
def get_environ_proxies(url): def get_environ_proxies(url):
"""Return a dict of environment proxies.""" """Return a dict of environment proxies."""
if should_bypass_proxies(url): if should_bypass_proxies(url):
@ -527,35 +571,26 @@ def get_environ_proxies(url):
return getproxies() return getproxies()
def select_proxy(url, proxies):
"""Select a proxy for the url, if applicable.
:param url: The url being for the request
:param proxies: A dictionary of schemes or schemes and hosts to proxy URLs
"""
proxies = proxies or {}
urlparts = urlparse(url)
if urlparts.hostname is None:
proxy = None
else:
proxy = proxies.get(urlparts.scheme+'://'+urlparts.hostname)
if proxy is None:
proxy = proxies.get(urlparts.scheme)
return proxy
def default_user_agent(name="python-requests"): def default_user_agent(name="python-requests"):
"""Return a string representing the default user agent.""" """Return a string representing the default user agent."""
_implementation = platform.python_implementation() return '%s/%s' % (name, __version__)
if _implementation == 'CPython':
_implementation_version = platform.python_version()
elif _implementation == 'PyPy':
_implementation_version = '%s.%s.%s' % (sys.pypy_version_info.major,
sys.pypy_version_info.minor,
sys.pypy_version_info.micro)
if sys.pypy_version_info.releaselevel != 'final':
_implementation_version = ''.join([_implementation_version, sys.pypy_version_info.releaselevel])
elif _implementation == 'Jython':
_implementation_version = platform.python_version() # Complete Guess
elif _implementation == 'IronPython':
_implementation_version = platform.python_version() # Complete Guess
else:
_implementation_version = 'Unknown'
try:
p_system = platform.system()
p_release = platform.release()
except IOError:
p_system = 'Unknown'
p_release = 'Unknown'
return " ".join(['%s/%s' % (name, __version__),
'%s/%s' % (_implementation, _implementation_version),
'%s/%s' % (p_system, p_release)])
def default_headers(): def default_headers():
@ -576,21 +611,19 @@ def parse_header_links(value):
links = [] links = []
replace_chars = " '\"" replace_chars = ' \'"'
for val in re.split(", *<", value): for val in re.split(', *<', value):
try: try:
url, params = val.split(";", 1) url, params = val.split(';', 1)
except ValueError: except ValueError:
url, params = val, '' url, params = val, ''
link = {} link = {'url': url.strip('<> \'"')}
link["url"] = url.strip("<> '\"") for param in params.split(';'):
for param in params.split(";"):
try: try:
key, value = param.split("=") key, value = param.split('=')
except ValueError: except ValueError:
break break
@ -637,8 +670,8 @@ def guess_json_utf(data):
def prepend_scheme_if_needed(url, new_scheme): def prepend_scheme_if_needed(url, new_scheme):
'''Given a URL that may or may not have a scheme, prepend the given scheme. """Given a URL that may or may not have a scheme, prepend the given scheme.
Does not replace a present scheme with the one provided as an argument.''' Does not replace a present scheme with the one provided as an argument."""
scheme, netloc, path, params, query, fragment = urlparse(url, new_scheme) scheme, netloc, path, params, query, fragment = urlparse(url, new_scheme)
# urlparse is a finicky beast, and sometimes decides that there isn't a # urlparse is a finicky beast, and sometimes decides that there isn't a
@ -669,8 +702,6 @@ def to_native_string(string, encoding='ascii'):
string in the native string type, encoding and decoding where necessary. string in the native string type, encoding and decoding where necessary.
This assumes ASCII unless told otherwise. This assumes ASCII unless told otherwise.
""" """
out = None
if isinstance(string, builtin_str): if isinstance(string, builtin_str):
out = string out = string
else: else: