Update requests to 2.18.4

This commit is contained in:
JonnyWong16 2017-12-26 15:26:09 -08:00
parent 52eac2b437
commit b1a3dd1a46
92 changed files with 1068 additions and 19854 deletions

View file

@ -6,36 +6,87 @@ requests.utils
This module provides utility functions that are used within Requests
that are also useful for external consumption.
"""
import cgi
import codecs
import collections
import contextlib
import io
import os
import platform
import re
import socket
import struct
import warnings
from . import __version__
from .__version__ import __version__
from . import certs
# to_native_string is unused here, but imported here for backwards compatibility
from ._internal_utils import to_native_string
from .compat import parse_http_list as _parse_list_header
from .compat import (quote, urlparse, bytes, str, OrderedDict, unquote, is_py2,
builtin_str, getproxies, proxy_bypass, urlunparse,
basestring)
from .cookies import RequestsCookieJar, cookiejar_from_dict
from .compat import (
quote, urlparse, bytes, str, OrderedDict, unquote, getproxies,
proxy_bypass, urlunparse, basestring, integer_types, is_py3,
proxy_bypass_environment, getproxies_environment)
from .cookies import cookiejar_from_dict
from .structures import CaseInsensitiveDict
from .exceptions import InvalidURL, FileModeWarning
_hush_pyflakes = (RequestsCookieJar,)
from .exceptions import (
InvalidURL, InvalidHeader, FileModeWarning, UnrewindableBodyError)
NETRC_FILES = ('.netrc', '_netrc')
DEFAULT_CA_BUNDLE_PATH = certs.where()
if platform.system() == 'Windows':
# provide a proxy_bypass version on Windows without DNS lookups
def proxy_bypass_registry(host):
if is_py3:
import winreg
else:
import _winreg as winreg
try:
internetSettings = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
r'Software\Microsoft\Windows\CurrentVersion\Internet Settings')
proxyEnable = winreg.QueryValueEx(internetSettings,
'ProxyEnable')[0]
proxyOverride = winreg.QueryValueEx(internetSettings,
'ProxyOverride')[0]
except OSError:
return False
if not proxyEnable or not proxyOverride:
return False
# make a check value list from the registry entry: replace the
# '<local>' string by the localhost entry and the corresponding
# canonical entry.
proxyOverride = proxyOverride.split(';')
# now check if we match one of the registry values.
for test in proxyOverride:
if test == '<local>':
if '.' not in host:
return True
test = test.replace(".", r"\.") # mask dots
test = test.replace("*", r".*") # change glob sequence
test = test.replace("?", r".") # change glob char
if re.match(test, host, re.I):
return True
return False
def proxy_bypass(host): # noqa
"""Return True, if the host should be bypassed.
Checks proxy settings gathered from the environment, if specified,
or the registry.
"""
if getproxies_environment():
return proxy_bypass_environment(host)
else:
return proxy_bypass_registry(host)
def dict_to_sequence(d):
"""Returns an internal sequence dictionary update."""
@ -46,7 +97,7 @@ def dict_to_sequence(d):
def super_len(o):
total_length = 0
total_length = None
current_position = 0
if hasattr(o, '__len__'):
@ -55,10 +106,6 @@ def super_len(o):
elif hasattr(o, 'len'):
total_length = o.len
elif hasattr(o, 'getvalue'):
# e.g. BytesIO, cStringIO.StringIO
total_length = len(o.getvalue())
elif hasattr(o, 'fileno'):
try:
fileno = o.fileno()
@ -88,7 +135,24 @@ def super_len(o):
# 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
if total_length is not None:
current_position = total_length
else:
if hasattr(o, 'seek') and total_length is None:
# StringIO and BytesIO have seek but no useable fileno
try:
# seek to end of file
o.seek(0, 2)
total_length = o.tell()
# seek back to current position to support
# partially read file-like objects
o.seek(current_position or 0)
except (OSError, IOError):
total_length = 0
if total_length is None:
total_length = 0
return max(0, total_length - current_position)
@ -107,7 +171,7 @@ def get_netrc_auth(url, raise_errors=False):
except KeyError:
# os.path.expanduser can fail when $HOME is undefined and
# getpwuid fails. See http://bugs.python.org/issue20164 &
# https://github.com/kennethreitz/requests/issues/1846
# https://github.com/requests/requests/issues/1846
return
if os.path.exists(loc):
@ -165,6 +229,8 @@ def from_key_val_list(value):
ValueError: need more than 1 value to unpack
>>> from_key_val_list({'key': 'val'})
OrderedDict([('key', 'val')])
:rtype: OrderedDict
"""
if value is None:
return None
@ -187,6 +253,8 @@ def to_key_val_list(value):
[('key', 'val')]
>>> to_key_val_list('string')
ValueError: cannot encode objects that are not 2-tuples.
:rtype: list
"""
if value is None:
return None
@ -222,6 +290,7 @@ def parse_list_header(value):
:param value: a string with a list header.
:return: :class:`list`
:rtype: list
"""
result = []
for item in _parse_list_header(value):
@ -252,6 +321,7 @@ def parse_dict_header(value):
:param value: a string with a dict header.
:return: :class:`dict`
:rtype: dict
"""
result = {}
for item in _parse_list_header(value):
@ -272,6 +342,7 @@ def unquote_header_value(value, is_filename=False):
using for quoting.
:param value: the header value to unquote.
:rtype: str
"""
if value and value[0] == value[-1] == '"':
# this is not the real unquoting, but fixing this so that the
@ -294,6 +365,7 @@ def dict_from_cookiejar(cj):
"""Returns a key/value dictionary from a CookieJar.
:param cj: CookieJar object to extract cookies from.
:rtype: dict
"""
cookie_dict = {}
@ -309,11 +381,10 @@ def add_dict_to_cookiejar(cj, cookie_dict):
:param cj: CookieJar to insert cookies into.
:param cookie_dict: Dict of key/values to insert into CookieJar.
:rtype: CookieJar
"""
cj2 = cookiejar_from_dict(cookie_dict)
cj.update(cj2)
return cj
return cookiejar_from_dict(cookie_dict, cj)
def get_encodings_from_content(content):
@ -340,6 +411,7 @@ def get_encoding_from_headers(headers):
"""Returns encodings from given HTTP Header Dict.
:param headers: dictionary to extract encoding from.
:rtype: str
"""
content_type = headers.get('content-type')
@ -377,6 +449,8 @@ def stream_decode_response_unicode(iterator, r):
def iter_slices(string, slice_length):
"""Iterate over slices of a string."""
pos = 0
if slice_length is None or slice_length <= 0:
slice_length = len(string)
while pos < len(string):
yield string[pos:pos + slice_length]
pos += slice_length
@ -392,6 +466,7 @@ def get_unicode_from_response(r):
1. charset from content-type
2. fall back and replace all unicode characters
:rtype: str
"""
warnings.warn((
'In requests 3.0, get_unicode_from_response will be removed. For '
@ -419,13 +494,14 @@ def get_unicode_from_response(r):
# The unreserved URI characters (RFC 3986)
UNRESERVED_SET = frozenset(
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz"
+ "0123456789-._~")
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" + "0123456789-._~")
def unquote_unreserved(uri):
"""Un-escape any percent-escape sequences in a URI that are unreserved
characters. This leaves all reserved, illegal and non-ASCII bytes encoded.
:rtype: str
"""
parts = uri.split('%')
for i in range(1, len(parts)):
@ -450,6 +526,8 @@ def requote_uri(uri):
This function passes the given URI through an unquote/quote cycle to
ensure that it is fully and consistently quoted.
:rtype: str
"""
safe_with_percent = "!#$%&'()*+,/:;=?@[]~"
safe_without_percent = "!#$&'()*+,/:;=?@[]~"
@ -466,10 +544,12 @@ def requote_uri(uri):
def address_in_network(ip, net):
"""
This function allows you to check if on IP belongs to a network subnet
"""This function allows you to check if an IP belongs to a network subnet
Example: returns True if ip = 192.168.1.1 and net = 192.168.1.0/24
returns False if ip = 192.168.1.1 and net = 192.168.100.0/24
:rtype: bool
"""
ipaddr = struct.unpack('=L', socket.inet_aton(ip))[0]
netaddr, bits = net.split('/')
@ -479,15 +559,20 @@ def address_in_network(ip, net):
def dotted_netmask(mask):
"""
Converts mask from /xx format to xxx.xxx.xxx.xxx
"""Converts mask from /xx format to xxx.xxx.xxx.xxx
Example: if mask is 24 function returns 255.255.255.0
:rtype: str
"""
bits = 0xffffffff ^ (1 << 32 - mask) - 1
return socket.inet_ntoa(struct.pack('>I', bits))
def is_ipv4_address(string_ip):
"""
:rtype: bool
"""
try:
socket.inet_aton(string_ip)
except socket.error:
@ -496,7 +581,11 @@ def is_ipv4_address(string_ip):
def is_valid_cidr(string_network):
"""Very simple check of the cidr format in no_proxy variable"""
"""
Very simple check of the cidr format in no_proxy variable.
:rtype: bool
"""
if string_network.count('/') == 1:
try:
mask = int(string_network.split('/')[1])
@ -515,15 +604,41 @@ def is_valid_cidr(string_network):
return True
def should_bypass_proxies(url):
@contextlib.contextmanager
def set_environ(env_name, value):
"""Set the environment variable 'env_name' to 'value'
Save previous value, yield, and then restore the previous value stored in
the environment variable 'env_name'.
If 'value' is None, do nothing"""
value_changed = value is not None
if value_changed:
old_value = os.environ.get(env_name)
os.environ[env_name] = value
try:
yield
finally:
if value_changed:
if old_value is None:
del os.environ[env_name]
else:
os.environ[env_name] = old_value
def should_bypass_proxies(url, no_proxy):
"""
Returns whether we should bypass proxies or not.
:rtype: bool
"""
get_proxy = lambda k: os.environ.get(k) or os.environ.get(k.upper())
# First check whether no_proxy is defined. If it is, check that the URL
# we're getting isn't in the no_proxy list.
no_proxy = get_proxy('no_proxy')
no_proxy_arg = no_proxy
if no_proxy is None:
no_proxy = get_proxy('no_proxy')
netloc = urlparse(url).netloc
if no_proxy:
@ -539,6 +654,10 @@ def should_bypass_proxies(url):
if is_valid_cidr(proxy_ip):
if address_in_network(ip, proxy_ip):
return True
elif ip == proxy_ip:
# If no_proxy ip was defined in plain IP notation instead of cidr notation &
# matches the IP of the index
return True
else:
for host in no_proxy:
if netloc.endswith(host) or netloc.split(':')[0].endswith(host):
@ -552,10 +671,11 @@ def should_bypass_proxies(url):
# of Python 2.6, so allow this call to fail. Only catch the specific
# exceptions we've seen, though: this call failing in other ways can reveal
# legitimate problems.
try:
bypass = proxy_bypass(netloc)
except (TypeError, socket.gaierror):
bypass = False
with set_environ('no_proxy', no_proxy_arg):
try:
bypass = proxy_bypass(netloc)
except (TypeError, socket.gaierror):
bypass = False
if bypass:
return True
@ -563,9 +683,13 @@ def should_bypass_proxies(url):
return False
def get_environ_proxies(url):
"""Return a dict of environment proxies."""
if should_bypass_proxies(url):
def get_environ_proxies(url, no_proxy=None):
"""
Return a dict of environment proxies.
:rtype: dict
"""
if should_bypass_proxies(url, no_proxy=no_proxy):
return {}
else:
return getproxies()
@ -580,20 +704,36 @@ def select_proxy(url, proxies):
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 proxies.get(urlparts.scheme, proxies.get('all'))
proxy_keys = [
urlparts.scheme + '://' + urlparts.hostname,
urlparts.scheme,
'all://' + urlparts.hostname,
'all',
]
proxy = None
for proxy_key in proxy_keys:
if proxy_key in proxies:
proxy = proxies[proxy_key]
break
return proxy
def default_user_agent(name="python-requests"):
"""Return a string representing the default user agent."""
"""
Return a string representing the default user agent.
:rtype: str
"""
return '%s/%s' % (name, __version__)
def default_headers():
"""
:rtype: requests.structures.CaseInsensitiveDict
"""
return CaseInsensitiveDict({
'User-Agent': default_user_agent(),
'Accept-Encoding': ', '.join(('gzip', 'deflate')),
@ -607,6 +747,7 @@ def parse_header_links(value):
i.e. Link: <http:/.../front.jpeg>; rel=front; type="image/jpeg",<http://.../back.jpeg>; rel=back;type="image/jpeg"
:rtype: list
"""
links = []
@ -641,11 +782,14 @@ _null3 = _null * 3
def guess_json_utf(data):
"""
:rtype: str
"""
# JSON always starts with two ASCII characters, so detection is as
# easy as counting the nulls and from their location and count
# determine the encoding. Also detect a BOM, if present.
sample = data[:4]
if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
if sample in (codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
return 'utf-32' # BOM included
if sample[:3] == codecs.BOM_UTF8:
return 'utf-8-sig' # BOM included, MS style (discouraged)
@ -671,7 +815,10 @@ def guess_json_utf(data):
def prepend_scheme_if_needed(url, new_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.
:rtype: str
"""
scheme, netloc, path, params, query, fragment = urlparse(url, new_scheme)
# urlparse is a finicky beast, and sometimes decides that there isn't a
@ -685,7 +832,10 @@ def prepend_scheme_if_needed(url, new_scheme):
def get_auth_from_url(url):
"""Given a url with authentication components, extract them into a tuple of
username,password."""
username,password.
:rtype: (str,str)
"""
parsed = urlparse(url)
try:
@ -696,26 +846,37 @@ def get_auth_from_url(url):
return auth
def to_native_string(string, encoding='ascii'):
"""
Given a string object, regardless of type, returns a representation of that
string in the native string type, encoding and decoding where necessary.
This assumes ASCII unless told otherwise.
"""
if isinstance(string, builtin_str):
out = string
else:
if is_py2:
out = string.encode(encoding)
else:
out = string.decode(encoding)
# Moved outside of function to avoid recompile every call
_CLEAN_HEADER_REGEX_BYTE = re.compile(b'^\\S[^\\r\\n]*$|^$')
_CLEAN_HEADER_REGEX_STR = re.compile(r'^\S[^\r\n]*$|^$')
return out
def check_header_validity(header):
"""Verifies that header value is a string which doesn't contain
leading whitespace or return characters. This prevents unintended
header injection.
:param header: tuple, in the format (name, value).
"""
name, value = header
if isinstance(value, bytes):
pat = _CLEAN_HEADER_REGEX_BYTE
else:
pat = _CLEAN_HEADER_REGEX_STR
try:
if not pat.match(value):
raise InvalidHeader("Invalid return character or leading space in header: %s" % name)
except TypeError:
raise InvalidHeader("Value for header {%s: %s} must be of type str or "
"bytes, not %s" % (name, value, type(value)))
def urldefragauth(url):
"""
Given a url remove the fragment and the authentication part
Given a url remove the fragment and the authentication part.
:rtype: str
"""
scheme, netloc, path, params, query, fragment = urlparse(url)
@ -726,3 +887,18 @@ def urldefragauth(url):
netloc = netloc.rsplit('@', 1)[-1]
return urlunparse((scheme, netloc, path, params, query, ''))
def rewind_body(prepared_request):
"""Move file pointer back to its recorded starting position
so it can be read again on redirect.
"""
body_seek = getattr(prepared_request.body, 'seek', None)
if body_seek is not None and isinstance(prepared_request._body_position, integer_types):
try:
body_seek(prepared_request._body_position)
except (IOError, OSError):
raise UnrewindableBodyError("An error occurred when rewinding request "
"body for redirect.")
else:
raise UnrewindableBodyError("Unable to rewind request body for redirect.")