Edit File: parse.py
"""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 1995. RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M. McCahill, December 1994 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. """ import re import os import sys import collections __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', 'ws', 'wss'] uses_params = ['', 'ftp', 'hdl', 'prospero', 'http', 'imap', 'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips', 'mms', 'sftp', 'tel'] # 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', 'file', 'prospero'] # Characters valid in scheme names scheme_chars = ('abcdefghijklmnopqrstuvwxyz' 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' '0123456789' '+-.') # 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 MAX_CACHE_SIZE = 20 _parse_cache = {} def clear_cache(): """Clear the parse cache and the quoters cache.""" _parse_cache.clear() _safe_quoters.clear() # 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 _noop(obj): return obj 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) def _coerce_args(*args): # Invokes decode if necessary to create str args # and returns the coerced inputs along with # an appropriate result coercion function # - noop for str inputs # - encoding function otherwise str_input = isinstance(args[0], str) for arg in args[1:]: # 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") if str_input: return args + (_noop,) 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""" __slots__ = () 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""" __slots__ = () 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""" __slots__ = () @property def username(self): return self._userinfo[0] @property def password(self): return self._userinfo[1] @property def hostname(self): hostname = self._hostinfo[0] if not hostname: return None # 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 @property def port(self): port = self._hostinfo[1] if port is not None: port = int(port, 10) if not ( 0 <= port <= 65535): raise ValueError("Port out of range 0-65535") return port class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr): __slots__ = () @property def _userinfo(self): netloc = self.netloc userinfo, have_info, hostinfo = netloc.rpartition('@') if have_info: username, have_password, password = userinfo.partition(':') if not have_password: password = None else: username = password = None return username, password @property def _hostinfo(self): netloc = self.netloc _, _, hostinfo = netloc.rpartition('@') _, have_open_br, bracketed = hostinfo.partition('[') if have_open_br: hostname, _, port = bracketed.partition(']') _, _, port = port.partition(':') else: hostname, _, port = hostinfo.partition(':') if not port: port = None return hostname, port class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes): __slots__ = () @property def _userinfo(self): netloc = self.netloc userinfo, have_info, hostinfo = netloc.rpartition(b'@') if have_info: username, have_password, password = userinfo.partition(b':') if not have_password: password = None else: username = password = None return username, password @property def _hostinfo(self): netloc = self.netloc _, _, hostinfo = netloc.rpartition(b'@') _, have_open_br, bracketed = hostinfo.partition(b'[') if have_open_br: hostname, _, port = bracketed.partition(b']') _, _, port = port.partition(b':') else: hostname, _, port = hostinfo.partition(b':') if not port: port = None return hostname, port 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 information. """ _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 network location. """ _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): __slots__ = () def geturl(self): if self.fragment: return self.url + '#' + self.fragment else: return self.url class SplitResult(_SplitResultBase, _NetlocResultMixinStr): __slots__ = () def geturl(self): return urlunsplit(self) class ParseResult(_ParseResultBase, _NetlocResultMixinStr): __slots__ = () def geturl(self): return urlunparse(self) # Structured result objects for bytes data class DefragResultBytes(_DefragResultBase, _ResultMixinBytes): __slots__ = () def geturl(self): if self.fragment: return self.url + b'#' + self.fragment else: return self.url class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes): __slots__ = () def geturl(self): return urlunsplit(self) class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes): __slots__ = () def geturl(self): return urlunparse(self) # Set up the encode/decode result pairs def _fix_result_transcoding(): _result_pairs = ( (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) else: params = '' result = ParseResult(scheme, netloc, url, params, query, fragment) return _coerce_result(result) def _splitparams(url): if '/' in url: i = url.find(';', url.rfind('/')) if i < 0: return url, '' else: i = url.find(';') 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): return # looking for characters like \u2100 that expand to 'a/c' # IDNA uses NFKC equivalence, so normalize for this check import unicodedata n = netloc.replace('@', '') # ignore characters already included n = n.replace(':', '') # but not the surrounding text n = n.replace('#', '') n = n.replace('?', '') netloc2 = unicodedata.normalize('NFKC', n) if n == netloc2: return for c in '/?#@:': if c in netloc2: 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: url = url.replace(b, "") return url 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) if cached: return _coerce_result(cached) if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth clear_cache() netloc = query = fragment = '' i = url.find(':') if i > 0: if url[:i] == 'http': # optimize the common case scheme = url[:i].lower() url = url[i+1:] if url[:2] == '//': 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) if '?' in url: url, query = url.split('?', 1) _checknetloc(netloc) v = SplitResult(scheme, netloc, url, query, fragment) _parse_cache[key] = v return _coerce_result(v) for c in url[:i]: if c not in scheme_chars: break else: # make sure "url" is not actually a port number (in which case # "scheme" is really part of the path) rest = url[i+1:] if not rest or any(c not in '0123456789' for c in rest): # not a port number scheme, url = url[:i].lower(), rest if url[:2] == '//': 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) if '?' in url: url, query = url.split('?', 1) _checknetloc(netloc) v = SplitResult(scheme, netloc, url, query, fragment) _parse_cache[key] = v return _coerce_result(v) 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)) if params: url = "%s;%s" % (url, params) return _coerce_result(urlunsplit((scheme, netloc, url, query, fragment))) def urlunsplit(components): """Combine the elements of a tuple as returned by urlsplit() into a complete URL as a string. The data argument can be any five-item iterable. This may result in a slightly different, but equivalent URL, if the URL that was parsed originally had unnecessary delimiters (for example, a ? with an empty query; the RFC states that these are equivalent).""" scheme, netloc, url, query, fragment, _coerce_result = ( _coerce_args(*components)) if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'): if url and url[:1] != '/': url = '/' + url url = '//' + (netloc or '') + url if scheme: url = scheme + ':' + url if query: url = url + '?' + query if fragment: url = url + '#' + fragment return _coerce_result(url) def urljoin(base, url, allow_fragments=True): """Join a base URL and a possibly relative URL to form an absolute interpretation of the latter.""" if not base: return url if not url: return base base, url, _coerce_result = _coerce_args(base, url) bscheme, bnetloc, bpath, bparams, bquery, bfragment = \ urlparse(base, '', allow_fragments) scheme, netloc, path, params, query, fragment = \ urlparse(url, bscheme, allow_fragments) if scheme != bscheme or scheme not in uses_relative: return _coerce_result(url) if scheme in uses_netloc: if netloc: return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) netloc = bnetloc if not path and not params: path = bpath params = bparams if not query: query = bquery return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) base_parts = bpath.split('/') if base_parts[-1] != '': # the last item is not a directory, so will not be taken into account # in resolving the relative path del base_parts[-1] # for rfc3986, ignore all base path should the first character be root. if path[:1] == '/': segments = path.split('/') else: segments = base_parts + path.split('/') # filter out elements that would cause redundant slashes on re-joining # the resolved_path segments[1:-1] = filter(None, segments[1:-1]) resolved_path = [] for seg in segments: if seg == '..': try: resolved_path.pop() except IndexError: # ignore any .. segments that would otherwise cause an IndexError # when popped from resolved_path if resolving for rfc3986 pass elif seg == '.': continue else: resolved_path.append(seg) if segments[-1] in ('.', '..'): # do some post-processing here. if the last segment was a relative dir, # then we need to append the trailing '/' resolved_path.append('') return _coerce_result(urlunparse((scheme, netloc, '/'.join( resolved_path) or '/', params, query, fragment))) def urldefrag(url): """Removes any existing fragment from URL. Returns a tuple of the defragmented URL and the fragment. If the URL contained no fragments, the second element is the empty string. """ url, _coerce_result = _coerce_args(url) if '#' in url: s, n, p, a, q, frag = urlparse(url) defrag = urlunparse((s, n, p, a, q, '')) else: frag = '' defrag = url return _coerce_result(DefragResult(defrag, frag)) _hexdig = '0123456789ABCDEFabcdef' _hextobyte = None def unquote_to_bytes(string): """unquote_to_bytes('abc%20def') -> b'abc def'.""" # Note: strings are encoded as UTF-8. This is only an issue if it contains # unescaped non-ASCII characters, which URIs should not. if not string: # Is it a string-like object? string.split return b'' if isinstance(string, str): string = string.encode('utf-8') bits = string.split(b'%') if len(bits) == 1: return string res = [bits[0]] append = res.append # Delay the initialization of the table to not waste memory # if the function is never called global _hextobyte if _hextobyte is None: _hextobyte = {(a + b).encode(): bytes([int(a + b, 16)]) for a in _hexdig for b in _hexdig} for item in bits[1:]: try: append(_hextobyte[item[:2]]) append(item[2:]) except KeyError: append(b'%') append(item) return b''.join(res) _asciire = re.compile('([\x00-\x7f]+)') def unquote(string, encoding='utf-8', errors='replace'): """Replace %xx escapes by their single-character equivalent. The optional encoding and errors parameters specify how to decode percent-encoded sequences into Unicode characters, as accepted by the bytes.decode() method. By default, percent-encoded sequences are decoded with UTF-8, and invalid sequences are replaced by a placeholder character. unquote('abc%20def') -> 'abc def'. """ if '%' not in string: string.split return string if encoding is None: encoding = 'utf-8' if errors is None: errors = 'replace' bits = _asciire.split(string) res = [bits[0]] append = res.append for i in range(1, len(bits), 2): append(unquote_to_bytes(bits[i]).decode(encoding, errors)) append(bits[i + 1]) return ''.join(res) def parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator=None): """Parse a query given as a string argument. Arguments: qs: percent-encoded query string to be parsed keep_blank_values: flag indicating whether blank values in percent-encoded queries should be treated as blank strings. A true value indicates that blanks should be retained as blank strings. The default false value indicates that blank values are to be ignored and treated as if they were not included. strict_parsing: flag indicating what to do with parsing errors. If false (the default), errors are silently ignored. If true, errors raise a ValueError exception. encoding and errors: specify how to decode percent-encoded sequences into Unicode characters, as accepted by the bytes.decode() method. max_num_fields: int. If set, then throws a ValueError if there are more than n fields read by parse_qsl(). Returns a dictionary. """ parsed_result = {} pairs = parse_qsl(qs, keep_blank_values, strict_parsing, encoding=encoding, errors=errors, max_num_fields=max_num_fields, separator=separator) for name, value in pairs: if name in parsed_result: parsed_result[name].append(value) else: parsed_result[name] = [value] return parsed_result class _QueryStringSeparatorWarning(RuntimeWarning): """Warning for using default `separator` in parse_qs or parse_qsl""" # The default "separator" for parse_qsl can be specified in a config file. # It's cached after first read. _QS_SEPARATOR_CONFIG_FILENAME = '/etc/python/urllib.cfg' _default_qs_separator = None def parse_qsl(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace', max_num_fields=None, separator=None): """Parse a query given as a string argument. Arguments: qs: percent-encoded query string to be parsed keep_blank_values: flag indicating whether blank values in percent-encoded queries should be treated as blank strings. A true value indicates that blanks should be retained as blank strings. The default false value indicates that blank values are to be ignored and treated as if they were not included. strict_parsing: flag indicating what to do with parsing errors. If false (the default), errors are silently ignored. If true, errors raise a ValueError exception. encoding and errors: specify how to decode percent-encoded sequences into Unicode characters, as accepted by the bytes.decode() method. max_num_fields: int. If set, then throws a ValueError if there are more than n fields read by parse_qsl(). Returns a list, as G-d intended. """ qs, _coerce_result = _coerce_args(qs) if isinstance(separator, bytes): separator = separator.decode('ascii') if (not separator or (not isinstance(separator, (str, bytes)))) and separator is not None: raise ValueError("Separator must be of type string or bytes.") # Used when both "&" and ";" act as separators. (Need a non-string value.) _legacy = object() if separator is None: global _default_qs_separator separator = _default_qs_separator envvar_name = 'PYTHON_URLLIB_QS_SEPARATOR' if separator is None: # Set default separator from environment variable separator = os.environ.get(envvar_name) config_source = 'environment variable' if separator is None: # Set default separator from the configuration file try: file = open(_QS_SEPARATOR_CONFIG_FILENAME) except FileNotFoundError: pass else: with file: import configparser config = configparser.ConfigParser( interpolation=None, comment_prefixes=('#', ), ) config.read_file(file) separator = config.get('parse_qs', envvar_name, fallback=None) _default_qs_separator = separator config_source = _QS_SEPARATOR_CONFIG_FILENAME if separator is None: # The default is '&', but warn if not specified explicitly if ';' in qs: from warnings import warn warn("The default separator of urllib.parse.parse_qsl and " + "parse_qs was changed to '&' to avoid a web cache " + "poisoning issue (CVE-2021-23336). " + "By default, semicolons no longer act as query field " + "separators. " + "See https://access.redhat.com/articles/5860431 for " + "more details.", _QueryStringSeparatorWarning, stacklevel=2) separator = '&' elif separator == 'legacy': separator = _legacy elif len(separator) != 1: raise ValueError( f'{envvar_name} (from {config_source}) must contain ' + '1 character, or "legacy". See ' + 'https://access.redhat.com/articles/5860431 for more details.' ) # If max_num_fields is defined then check that the number of fields # is less than max_num_fields. This prevents a memory exhaustion DOS # attack via post bodies with many fields. if max_num_fields is not None: if separator is _legacy: num_fields = 1 + qs.count('&') + qs.count(';') else: num_fields = 1 + qs.count(separator) if max_num_fields < num_fields: raise ValueError('Max number of fields exceeded') if separator is _legacy: pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')] else: pairs = [s1 for s1 in qs.split(separator)] r = [] for name_value in pairs: if not name_value and not strict_parsing: continue nv = name_value.split('=', 1) if len(nv) != 2: if strict_parsing: raise ValueError("bad query field: %r" % (name_value,)) # Handle case of a control-name with no equal sign if keep_blank_values: nv.append('') else: continue if len(nv[1]) or keep_blank_values: name = nv[0].replace('+', ' ') name = unquote(name, encoding=encoding, errors=errors) name = _coerce_result(name) value = nv[1].replace('+', ' ') value = unquote(value, encoding=encoding, errors=errors) value = _coerce_result(value) r.append((name, value)) return r def unquote_plus(string, encoding='utf-8', errors='replace'): """Like unquote(), but also replace plus signs by spaces, as required for unquoting HTML form values. unquote_plus('%7e/abc+def') -> '~/abc def' """ string = string.replace('+', ' ') return unquote(string, encoding, errors) _ALWAYS_SAFE = frozenset(b'ABCDEFGHIJKLMNOPQRSTUVWXYZ' b'abcdefghijklmnopqrstuvwxyz' b'0123456789' b'_.-') _ALWAYS_SAFE_BYTES = bytes(_ALWAYS_SAFE) _safe_quoters = {} class Quoter(collections.defaultdict): """A mapping from bytes (in range(0,256)) to strings. String values are percent-encoded byte values, unless the key < 128, and in the "safe" set (either the specified safe set, or default set). """ # Keeps a cache internally, using defaultdict, for efficiency (lookups # of cached keys don't call Python code at all). def __init__(self, safe): """safe: bytes object.""" self.safe = _ALWAYS_SAFE.union(safe) def __repr__(self): # Without this, will just display as a defaultdict return "<%s %r>" % (self.__class__.__name__, dict(self)) def __missing__(self, b): # Handle a cache miss. Store quoted string in cache and return. res = chr(b) if b in self.safe else '%{:02X}'.format(b) self[b] = res return res def quote(string, safe='/', encoding=None, errors=None): """quote('abc def') -> 'abc%20def' Each part of a URL, e.g. the path info, the query, etc., has a different set of reserved characters that must be quoted. RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists the following reserved characters. reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | "$" | "," Each of these characters is reserved in some component of a URL, but not necessarily in all of them. By default, the quote function is intended for quoting the path section of a URL. Thus, it will not encode '/'. This character is reserved, but in typical usage the quote function is being called on a path where the existing slash characters are used as reserved characters. string and safe may be either str or bytes objects. encoding and errors must not be specified if string is a bytes object. The optional encoding and errors parameters specify how to deal with non-ASCII characters, as accepted by the str.encode method. By default, encoding='utf-8' (characters are encoded with UTF-8), and errors='strict' (unsupported characters raise a UnicodeEncodeError). """ if isinstance(string, str): if not string: return string if encoding is None: encoding = 'utf-8' if errors is None: errors = 'strict' string = string.encode(encoding, errors) else: if encoding is not None: raise TypeError("quote() doesn't support 'encoding' for bytes") if errors is not None: raise TypeError("quote() doesn't support 'errors' for bytes") return quote_from_bytes(string, safe) def quote_plus(string, safe='', encoding=None, errors=None): """Like quote(), but also replace ' ' with '+', as required for quoting HTML form values. Plus signs in the original string are escaped unless they are included in safe. It also does not have safe default to '/'. """ # Check if ' ' in string, where string may either be a str or bytes. If # there are no spaces, the regular quote will produce the right answer. if ((isinstance(string, str) and ' ' not in string) or (isinstance(string, bytes) and b' ' not in string)): return quote(string, safe, encoding, errors) if isinstance(safe, str): space = ' ' else: space = b' ' string = quote(string, safe + space, encoding, errors) return string.replace(' ', '+') def quote_from_bytes(bs, safe='/'): """Like quote(), but accepts a bytes object rather than a str, and does not perform string-to-bytes encoding. It always returns an ASCII string. quote_from_bytes(b'abc def\x3f') -> 'abc%20def%3f' """ if not isinstance(bs, (bytes, bytearray)): raise TypeError("quote_from_bytes() expected bytes") if not bs: return '' if isinstance(safe, str): # Normalize 'safe' by converting to bytes and removing non-ASCII chars safe = safe.encode('ascii', 'ignore') else: safe = bytes([c for c in safe if c < 128]) if not bs.rstrip(_ALWAYS_SAFE_BYTES + safe): return bs.decode() try: quoter = _safe_quoters[safe] except KeyError: _safe_quoters[safe] = quoter = Quoter(safe).__getitem__ return ''.join([quoter(char) for char in bs]) def urlencode(query, doseq=False, safe='', encoding=None, errors=None, quote_via=quote_plus): """Encode a dict or sequence of two-element tuples into a URL query string. If any values in the query arg are sequences and doseq is true, each sequence element is converted to a separate parameter. If the query arg is a sequence of two-element tuples, the order of the parameters in the output will match the order of parameters in the input. The components of a query arg may each be either a string or a bytes type. The safe, encoding, and errors parameters are passed down to the function specified by quote_via (encoding and errors only if a component is a str). """ if hasattr(query, "items"): query = query.items() else: # It's a bother at times that strings and string-like objects are # sequences. try: # non-sequence items should not work with len() # non-empty strings will fail this if len(query) and not isinstance(query[0], tuple): raise TypeError # Zero-length sequences of all types will get here and succeed, # but that's a minor nit. Since the original implementation # allowed empty dicts that type of behavior probably should be # preserved for consistency except TypeError: ty, va, tb = sys.exc_info() raise TypeError("not a valid non-string sequence " "or mapping object").with_traceback(tb) l = [] if not doseq: for k, v in query: if isinstance(k, bytes): k = quote_via(k, safe) else: k = quote_via(str(k), safe, encoding, errors) if isinstance(v, bytes): v = quote_via(v, safe) else: v = quote_via(str(v), safe, encoding, errors) l.append(k + '=' + v) else: for k, v in query: if isinstance(k, bytes): k = quote_via(k, safe) else: k = quote_via(str(k), safe, encoding, errors) if isinstance(v, bytes): v = quote_via(v, safe) l.append(k + '=' + v) elif isinstance(v, str): v = quote_via(v, safe, encoding, errors) l.append(k + '=' + v) else: try: # Is this a sufficient test for sequence-ness? x = len(v) except TypeError: # not a sequence v = quote_via(str(v), safe, encoding, errors) l.append(k + '=' + v) else: # loop over the sequence for elt in v: if isinstance(elt, bytes): elt = quote_via(elt, safe) else: elt = quote_via(str(elt), safe, encoding, errors) l.append(k + '=' + elt) return '&'.join(l) def to_bytes(url): """to_bytes(u"URL") --> 'URL'.""" # Most URL schemes require ASCII. If that changes, the conversion # can be relaxed. # XXX get rid of to_bytes() if isinstance(url, str): try: url = url.encode("ASCII").decode() except UnicodeError: raise UnicodeError("URL " + repr(url) + " contains non-ASCII characters") return url def unwrap(url): """unwrap('<URL:type://host/path>') --> 'type://host/path'.""" url = str(url).strip() if url[:1] == '<' and url[-1:] == '>': url = url[1:-1].strip() if url[:4] == 'URL:': url = url[4:].strip() return url _typeprog = None def splittype(url): """splittype('type:opaquestring') --> 'type', 'opaquestring'.""" global _typeprog if _typeprog is None: _typeprog = re.compile('([^/:]+):(.*)', re.DOTALL) match = _typeprog.match(url) if match: scheme, data = match.groups() return scheme.lower(), data return None, url _hostprog = None def splithost(url): """splithost('//host[:port]/path') --> 'host[:port]', '/path'.""" global _hostprog if _hostprog is None: _hostprog = re.compile('//([^/#?]*)(.*)', re.DOTALL) match = _hostprog.match(url) if match: host_port, path = match.groups() if path and path[0] != '/': path = '/' + path return host_port, path return None, url def splituser(host): """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.""" user, delim, host = host.rpartition('@') return (user if delim else None), host def splitpasswd(user): """splitpasswd('user:passwd') -> 'user', 'passwd'.""" user, delim, passwd = user.partition(':') return user, (passwd if delim else None) # splittag('/path#tag') --> '/path', 'tag' _portprog = None def splitport(host): """splitport('host:port') --> 'host', 'port'.""" global _portprog if _portprog is None: _portprog = re.compile('(.*):([0-9]*)$', re.DOTALL) match = _portprog.match(host) if match: host, port = match.groups() if port: return host, port return host, None def splitnport(host, defport=-1): """Split host and port, returning numeric port. Return given default port if no ':' found; defaults to -1. Return numerical port if a valid number are found after ':'. Return None if ':' but not a valid number.""" host, delim, port = host.rpartition(':') if not delim: host = port elif port: try: nport = int(port) except ValueError: nport = None return host, nport return host, defport def splitquery(url): """splitquery('/path?query') --> '/path', 'query'.""" path, delim, query = url.rpartition('?') if delim: return path, query return url, None def splittag(url): """splittag('/path#tag') --> '/path', 'tag'.""" path, delim, tag = url.rpartition('#') if delim: return path, tag return url, None def splitattr(url): """splitattr('/path;attr1=value1;attr2=value2;...') -> '/path', ['attr1=value1', 'attr2=value2', ...].""" words = url.split(';') return words[0], words[1:] def splitvalue(attr): """splitvalue('attr=value') --> 'attr', 'value'.""" attr, delim, value = attr.partition('=') return attr, (value if delim else None)