def get_connection(self, url, proxies=None):
"""Returns a urllib3 connection for the given URL. This should not be
called from user code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param url: The URL to connect to.
:param proxies: (optional) A Requests-style dictionary of proxies used on this request.
:rtype: urllib3.ConnectionPool
"""
proxy = select_proxy(url, proxies)
if proxy:
proxy = prepend_scheme_if_needed(proxy, 'http')
proxy_url = parse_url(proxy)
if not proxy_url.host:
raise InvalidProxyURL("Please check proxy URL. It is malformed"
" and could be missing the host.")
proxy_manager = self.proxy_manager_for(proxy)
conn = proxy_manager.connection_from_url(url)
else:
# Only scheme should be lower case
parsed = urlparse(url)
url = parsed.geturl()
conn = self.poolmanager.connection_from_url(url)
return conn
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.
:rtype: str
"""
parsed = parse_url(url)
scheme, auth, host, port, path, query, fragment = parsed
# A defect in urlparse determines that there isn't a netloc present in some
# urls. We previously assumed parsing was overly cautious, and swapped the
# netloc and path. Due to a lack of tests on the original defect, this is
# maintained with parse_url for backwards compatibility.
netloc = parsed.netloc
if not netloc:
netloc, path = path, netloc
if auth:
# parse_url doesn't provide the netloc with auth
# so we'll add it ourselves.
netloc = '@'.join([auth, netloc])
if scheme is None:
scheme = new_scheme
if path is None:
path = ''
return urlunparse((scheme, netloc, path, '', query, fragment))
def get_connection(self, url, proxies=None):
"""Returns a urllib3 connection for the given URL. This should not be
called from user code, and is only exposed for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
:param url: The URL to connect to.
:param proxies: (optional) A Requests-style dictionary of proxies used on this request.
:rtype: urllib3.ConnectionPool
"""
proxy = select_proxy(url, proxies)
if proxy:
proxy = prepend_scheme_if_needed(proxy, 'http')
proxy_url = parse_url(proxy)
if not proxy_url.host:
raise InvalidProxyURL("Please check proxy URL. It is malformed"
" and could be missing the host.")
proxy_manager = self.proxy_manager_for(proxy)
conn = proxy_manager.connection_from_url(url)
else:
# Only scheme should be lower case
parsed = urlparse(url)
url = parsed.geturl()
conn = self.poolmanager.connection_from_url(url)
return conn
def prepare_url(self, url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/requests/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Remove leading whitespaces from url
url = url.lstrip()
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
self.url = url
return
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = parse_url(url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
error = (
"Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?"
)
error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# In general, we want to try IDNA encoding the hostname if the string contains
# non-ASCII characters. This allows users to automatically get the correct IDNA
# behaviour. For strings containing only ASCII characters, we need to also verify
# it doesn't start with a wildcard (*), before allowing the unencoded hostname.
if not unicode_is_ascii(host):
try:
host = self._get_idna_encoded_host(host)
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
elif host.startswith(u'*'):
raise InvalidURL('URL has an invalid label.')
# Carefully reconstruct the network location
netloc = auth or ''
if netloc:
netloc += '@'
netloc += host
if port:
netloc += ':' + str(port)
# Bare domains aren't valid URLs.
if not path:
path = '/'
if is_py2:
if isinstance(scheme, str):
scheme = scheme.encode('utf-8')
if isinstance(netloc, str):
netloc = netloc.encode('utf-8')
if isinstance(path, str):
path = path.encode('utf-8')
if isinstance(query, str):
query = query.encode('utf-8')
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = self._encode_params(params)
if enc_params:
if query:
query = '%s&%s' % (query, enc_params)
else:
query = enc_params
url = requote_uri(
urlunparse([scheme, netloc, path, None, query, fragment]))
self.url = url
def prepare_url(self, url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/requests/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Remove leading whitespaces from url
url = url.lstrip()
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
self.url = url
return
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = parse_url(url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
error = ("Invalid URL {0!r}: No schema supplied. Perhaps you meant http://{0}?")
error = error.format(to_native_string(url, 'utf8'))
raise MissingSchema(error)
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# In general, we want to try IDNA encoding the hostname if the string contains
# non-ASCII characters. This allows users to automatically get the correct IDNA
# behaviour. For strings containing only ASCII characters, we need to also verify
# it doesn't start with a wildcard (*), before allowing the unencoded hostname.
if not unicode_is_ascii(host):
try:
host = self._get_idna_encoded_host(host)
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
elif host.startswith(u'*'):
raise InvalidURL('URL has an invalid label.')
# Carefully reconstruct the network location
netloc = auth or ''
if netloc:
netloc += '@'
netloc += host
if port:
netloc += ':' + str(port)
# Bare domains aren't valid URLs.
if not path:
path = '/'
if is_py2:
if isinstance(scheme, str):
scheme = scheme.encode('utf-8')
if isinstance(netloc, str):
netloc = netloc.encode('utf-8')
if isinstance(path, str):
path = path.encode('utf-8')
if isinstance(query, str):
query = query.encode('utf-8')
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = self._encode_params(params)
if enc_params:
if query:
query = '%s&%s' % (query, enc_params)
else:
query = enc_params
url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
self.url = url
def prepare_url(self, url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindly call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/psf/requests/pull/2238
if isinstance(url, bytes):
url = url.decode("utf8")
else:
url = str(url)
# Remove leading whitespaces from url
url = url.lstrip()
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ":" in url and not url.lower().startswith("http"):
self.url = url
return
# Support for unicode domain names and paths.
try:
scheme, auth, host, port, path, query, fragment = parse_url(url)
except LocationParseError as e:
raise InvalidURL(*e.args)
if not scheme:
raise MissingSchema(
f"Invalid URL {url!r}: No scheme supplied. "
f"Perhaps you meant http://{url}?"
)
if not host:
raise InvalidURL(f"Invalid URL {url!r}: No host supplied")
# In general, we want to try IDNA encoding the hostname if the string contains
# non-ASCII characters. This allows users to automatically get the correct IDNA
# behaviour. For strings containing only ASCII characters, we need to also verify
# it doesn't start with a wildcard (*), before allowing the unencoded hostname.
if not unicode_is_ascii(host):
try:
host = self._get_idna_encoded_host(host)
except UnicodeError:
raise InvalidURL("URL has an invalid label.")
elif host.startswith(("*", ".")):
raise InvalidURL("URL has an invalid label.")
# Carefully reconstruct the network location
netloc = auth or ""
if netloc:
netloc += "@"
netloc += host
if port:
netloc += f":{port}"
# Bare domains aren't valid URLs.
if not path:
path = "/"
if isinstance(params, (str, bytes)):
params = to_native_string(params)
enc_params = self._encode_params(params)
if enc_params:
if query:
query = f"{query}&{enc_params}"
else:
query = enc_params
url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
self.url = url
