"""Parse (absolute and relative) URLs.
urlparse module is based upon the following RFC specifications.
RFC 3986 (STD66): "Uniform Resource Identifiers" by T. Berners-Lee, R. Fielding
and L. Masinter, January 2005.
RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
and L.Masinter, December 1999.
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zawinski, July 1998.
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
RFC 3986 is considered the current standard and any future changes to
urlparse module should conform with it. The urlparse module is
currently not entirely compliant with this RFC due to defacto
scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
The WHATWG URL Parser spec should also be considered. We are not compliant with
it either due to existing user code API behavior expectations (Hyrum's Law).
It serves as a useful guide when making changes.
__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
"urlsplit", "urlunsplit", "urlencode", "parse_qs",
"parse_qsl", "quote", "quote_plus", "quote_from_bytes",
"unquote", "unquote_plus", "unquote_to_bytes",
"DefragResult", "ParseResult", "SplitResult",
"DefragResultBytes", "ParseResultBytes", "SplitResultBytes"]
# A classification of schemes.
# The empty string classifies URLs with no scheme specified,
# being the default value returned by “urlsplit” and “urlparse”.
uses_relative = ['', 'ftp', 'http', 'gopher', 'nntp', 'imap',
'wais', 'file', 'https', 'shttp', 'mms',
'prospero', 'rtsp', 'rtspu', 'sftp',
'svn', 'svn+ssh', 'ws', 'wss']
uses_netloc = ['', 'ftp', 'http', 'gopher', 'nntp', 'telnet',
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync',
'svn', 'svn+ssh', 'sftp', 'nfs', 'git', 'git+ssh',
uses_params = ['', 'ftp', 'hdl', 'prospero', 'http', 'imap',
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
# These are not actually used anymore, but should stay for backwards
# compatibility. (They are undocumented, but have a public-looking name.)
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
uses_query = ['', 'http', 'wais', 'imap', 'https', 'shttp', 'mms',
'gopher', 'rtsp', 'rtspu', 'sip', 'sips']
uses_fragment = ['', 'ftp', 'hdl', 'http', 'gopher', 'news',
'nntp', 'wais', 'https', 'shttp', 'snews',
# Characters valid in scheme names
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
# Leading and trailing C0 control and space to be stripped per WHATWG spec.
# == "".join([chr(i) for i in range(0, 0x20 + 1)])
_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '
# Unsafe bytes to be removed per WHATWG spec
_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']
# XXX: Consider replacing with functools.lru_cache
"""Clear the parse cache and the quoters cache."""
# Helpers for bytes handling
# For 3.2, we deliberately require applications that
# handle improperly quoted URLs to do their own
# decoding and encoding. If valid use cases are
# presented, we may relax this by using latin-1
# decoding internally for 3.3
_implicit_encoding = 'ascii'
_implicit_errors = 'strict'
def _encode_result(obj, encoding=_implicit_encoding,
errors=_implicit_errors):
return obj.encode(encoding, errors)
def _decode_args(args, encoding=_implicit_encoding,
errors=_implicit_errors):
return tuple(x.decode(encoding, errors) if x else '' for x in args)
# Invokes decode if necessary to create str args
# and returns the coerced inputs along with
# an appropriate result coercion function
# - encoding function otherwise
str_input = isinstance(args[0], str)
# We special-case the empty string to support the
# "scheme=''" default argument to some functions
if arg and isinstance(arg, str) != str_input:
raise TypeError("Cannot mix str and non-str arguments")
return _decode_args(args) + (_encode_result,)
# Result objects are more helpful than simple tuples
class _ResultMixinStr(object):
"""Standard approach to encoding parsed results from str to bytes"""
def encode(self, encoding='ascii', errors='strict'):
return self._encoded_counterpart(*(x.encode(encoding, errors) for x in self))
class _ResultMixinBytes(object):
"""Standard approach to decoding parsed results from bytes to str"""
def decode(self, encoding='ascii', errors='strict'):
return self._decoded_counterpart(*(x.decode(encoding, errors) for x in self))
class _NetlocResultMixinBase(object):
"""Shared methods for the parsed result objects containing a netloc element"""
hostname = self._hostinfo[0]
# Scoped IPv6 address may have zone info, which must not be lowercased
# like http://[fe80::822a:a8ff:fe49:470c%tESt]:1234/keys
separator = '%' if isinstance(hostname, str) else b'%'
hostname, percent, zone = hostname.partition(separator)
return hostname.lower() + percent + zone
if not ( 0 <= port <= 65535):
raise ValueError("Port out of range 0-65535")
class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):
userinfo, have_info, hostinfo = netloc.rpartition('@')
username, have_password, password = userinfo.partition(':')
username = password = None
return username, password
_, _, hostinfo = netloc.rpartition('@')
_, have_open_br, bracketed = hostinfo.partition('[')
hostname, _, port = bracketed.partition(']')
_, _, port = port.partition(':')
hostname, _, port = hostinfo.partition(':')
class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):
userinfo, have_info, hostinfo = netloc.rpartition(b'@')
username, have_password, password = userinfo.partition(b':')
username = password = None
return username, password
_, _, hostinfo = netloc.rpartition(b'@')
_, have_open_br, bracketed = hostinfo.partition(b'[')
hostname, _, port = bracketed.partition(b']')
_, _, port = port.partition(b':')
hostname, _, port = hostinfo.partition(b':')
from collections import namedtuple
_DefragResultBase = namedtuple('DefragResult', 'url fragment')
_SplitResultBase = namedtuple(
'SplitResult', 'scheme netloc path query fragment')
_ParseResultBase = namedtuple(
'ParseResult', 'scheme netloc path params query fragment')
_DefragResultBase.__doc__ = """
DefragResult(url, fragment)
A 2-tuple that contains the url without fragment identifier and the fragment
identifier as a separate argument.
_DefragResultBase.url.__doc__ = """The URL with no fragment identifier."""
_DefragResultBase.fragment.__doc__ = """
Fragment identifier separated from URL, that allows indirect identification of a
secondary resource by reference to a primary resource and additional identifying
_SplitResultBase.__doc__ = """
SplitResult(scheme, netloc, path, query, fragment)
A 5-tuple that contains the different components of a URL. Similar to
ParseResult, but does not split params.
_SplitResultBase.scheme.__doc__ = """Specifies URL scheme for the request."""
_SplitResultBase.netloc.__doc__ = """
Network location where the request is made to.
_SplitResultBase.path.__doc__ = """
The hierarchical path, such as the path to a file to download.
_SplitResultBase.query.__doc__ = """
The query component, that contains non-hierarchical data, that along with data
in path component, identifies a resource in the scope of URI's scheme and
_SplitResultBase.fragment.__doc__ = """
Fragment identifier, that allows indirect identification of a secondary resource
by reference to a primary resource and additional identifying information.
_ParseResultBase.__doc__ = """
ParseResult(scheme, netloc, path, params, query, fragment)
A 6-tuple that contains components of a parsed URL.
_ParseResultBase.scheme.__doc__ = _SplitResultBase.scheme.__doc__
_ParseResultBase.netloc.__doc__ = _SplitResultBase.netloc.__doc__
_ParseResultBase.path.__doc__ = _SplitResultBase.path.__doc__
_ParseResultBase.params.__doc__ = """
Parameters for last path element used to dereference the URI in order to provide
access to perform some operation on the resource.
_ParseResultBase.query.__doc__ = _SplitResultBase.query.__doc__
_ParseResultBase.fragment.__doc__ = _SplitResultBase.fragment.__doc__
# For backwards compatibility, alias _NetlocResultMixinStr
# ResultBase is no longer part of the documented API, but it is
# retained since deprecating it isn't worth the hassle
ResultBase = _NetlocResultMixinStr
# Structured result objects for string data
class DefragResult(_DefragResultBase, _ResultMixinStr):
return self.url + '#' + self.fragment
class SplitResult(_SplitResultBase, _NetlocResultMixinStr):
class ParseResult(_ParseResultBase, _NetlocResultMixinStr):
# Structured result objects for bytes data
class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):
return self.url + b'#' + self.fragment
class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):
class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):
# Set up the encode/decode result pairs
def _fix_result_transcoding():
(DefragResult, DefragResultBytes),
(SplitResult, SplitResultBytes),
(ParseResult, ParseResultBytes),
for _decoded, _encoded in _result_pairs:
_decoded._encoded_counterpart = _encoded
_encoded._decoded_counterpart = _decoded
_fix_result_transcoding()
del _fix_result_transcoding
def urlparse(url, scheme='', allow_fragments=True):
"""Parse a URL into 6 components:
<scheme>://<netloc>/<path>;<params>?<query>#<fragment>
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
splitresult = urlsplit(url, scheme, allow_fragments)
scheme, netloc, url, query, fragment = splitresult
if scheme in uses_params and ';' in url:
url, params = _splitparams(url)
result = ParseResult(scheme, netloc, url, params, query, fragment)
return _coerce_result(result)
i = url.find(';', url.rfind('/'))
return url[:i], url[i+1:]
def _splitnetloc(url, start=0):
delim = len(url) # position of end of domain part of url, default is end
for c in '/?#': # look for delimiters; the order is NOT important
wdelim = url.find(c, start) # find first of this delim
if wdelim >= 0: # if found
delim = min(delim, wdelim) # use earliest delim position
return url[start:delim], url[delim:] # return (domain, rest)
def _checknetloc(netloc):
if not netloc or not any(ord(c) > 127 for c in netloc):
# looking for characters like \u2100 that expand to 'a/c'
# IDNA uses NFKC equivalence, so normalize for this check
n = netloc.replace('@', '') # ignore characters already included
n = n.replace(':', '') # but not the surrounding text
netloc2 = unicodedata.normalize('NFKC', n)
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")
def _remove_unsafe_bytes_from_url(url):
for b in _UNSAFE_URL_BYTES_TO_REMOVE:
def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
url, scheme, _coerce_result = _coerce_args(url, scheme)
url = _remove_unsafe_bytes_from_url(url)
scheme = _remove_unsafe_bytes_from_url(scheme)
# Only lstrip url as some applications rely on preserving trailing space.
# (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both)
url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)
scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
return _coerce_result(cached)
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
netloc = query = fragment = ''
if url[:i] == 'http': # optimize the common case
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
if c not in scheme_chars:
# make sure "url" is not actually a port number (in which case
# "scheme" is really part of the path)
if not rest or any(c not in '0123456789' for c in rest):
scheme, url = url[:i].lower(), rest
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
def urlunparse(components):
"""Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent)."""
scheme, netloc, url, params, query, fragment, _coerce_result = (
_coerce_args(*components))
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
