def resolve_proxies(request, proxies, trust_env=True):
"""This method takes proxy information from a request and configuration
input to resolve a mapping of target proxies. This will consider settings
such a NO_PROXY to strip proxy configurations.
:param request: Request or PreparedRequest
:param proxies: A dictionary of schemes or schemes and hosts to proxy URLs
:param trust_env: Boolean declaring whether to trust environment configs
:rtype: dict
"""
proxies = proxies if proxies is not None else {}
url = request.url
scheme = urlparse(url).scheme
no_proxy = proxies.get('no_proxy')
new_proxies = proxies.copy()
if trust_env and not should_bypass_proxies(url, no_proxy=no_proxy):
environ_proxies = get_environ_proxies(url, no_proxy=no_proxy)
proxy = environ_proxies.get(scheme, environ_proxies.get('all'))
if proxy:
new_proxies.setdefault(scheme, proxy)
return new_proxies
def should_bypass_proxies(url, no_proxy):
"""
Returns whether we should bypass proxies or not.
:rtype: bool
"""
# Prioritize lowercase environment variables over uppercase
# to keep a consistent behaviour with other http projects (curl, wget).
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_arg = no_proxy
if no_proxy is None:
no_proxy = get_proxy('no_proxy')
parsed = urlparse(url)
if parsed.hostname is None:
# URLs don't always have hostnames, e.g. file:/// urls.
return True
if no_proxy:
# We need to check whether we match here. We need to see if we match
# the end of the hostname, both with and without the port.
no_proxy = (host for host in no_proxy.replace(' ', '').split(',')
if host)
if is_ipv4_address(parsed.hostname):
for proxy_ip in no_proxy:
if is_valid_cidr(proxy_ip):
if address_in_network(parsed.hostname, proxy_ip):
return True
elif parsed.hostname == 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:
host_with_port = parsed.hostname
if parsed.port:
host_with_port += ':{}'.format(parsed.port)
for host in no_proxy:
if parsed.hostname.endswith(host) or host_with_port.endswith(
host):
# The URL does match something in no_proxy, so we don't want
# to apply the proxies on this URL.
return True
with set_environ('no_proxy', no_proxy_arg):
# parsed.hostname can be `None` in cases such as a file URI.
try:
bypass = proxy_bypass(parsed.hostname)
except (TypeError, socket.gaierror):
bypass = False
if bypass:
return True
return False
def get_netrc_auth(url, raise_errors=False):
"""Returns the Requests tuple auth for a given url from netrc."""
netrc_file = os.environ.get('NETRC')
if netrc_file is not None:
netrc_locations = (netrc_file, )
else:
netrc_locations = ('~/{}'.format(f) for f in NETRC_FILES)
try:
from netrc import netrc, NetrcParseError
netrc_path = None
for f in netrc_locations:
try:
loc = os.path.expanduser(f)
except KeyError:
# os.path.expanduser can fail when $HOME is undefined and
# getpwuid fails. See https://bugs.python.org/issue20164 &
# https://github.com/psf/requests/issues/1846
return
if os.path.exists(loc):
netrc_path = loc
break
# Abort early if there isn't one.
if netrc_path is None:
return
ri = urlparse(url)
# Strip port numbers from netloc. This weird `if...encode`` dance is
# 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:
_netrc = netrc(netrc_path).authenticators(host)
if _netrc:
# Return with login / password
login_i = (0 if _netrc[0] else 1)
return (_netrc[login_i], _netrc[2])
except (NetrcParseError, IOError):
# If there was a parsing error or a permissions issue reading the file,
# we'll just skip netrc auth unless explicitly asked to raise errors.
if raise_errors:
raise
# App Engine hackiness.
except (ImportError, AttributeError):
pass
def get_auth_from_url(url):
"""Given a url with authentication components, extract them into a tuple of
username,password.
:rtype: (str,str)
"""
parsed = urlparse(url)
try:
auth = (unquote(parsed.username), unquote(parsed.password))
except (AttributeError, TypeError):
auth = ('', '')
return auth
def urldefragauth(url):
"""
Given a url remove the fragment and the authentication part.
:rtype: str
"""
scheme, netloc, path, params, query, fragment = urlparse(url)
# see func:`prepend_scheme_if_needed`
if not netloc:
netloc, path = path, netloc
netloc = netloc.rsplit('@', 1)[-1]
return urlunparse((scheme, netloc, path, params, query, ''))
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:
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