2000-02-04 11:28:42 -04:00
|
|
|
"""Parse (absolute and relative) URLs.
|
|
|
|
|
2010-04-17 11:30:53 -03:00
|
|
|
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.
|
|
|
|
|
2010-04-29 21:49:09 -03:00
|
|
|
RFC 2396: "Uniform Resource Identifiers (URI)": Generic Syntax by T.
|
2010-04-17 11:30:53 -03:00
|
|
|
Berners-Lee, R. Fielding, and L. Masinter, August 1998.
|
|
|
|
|
2010-04-29 21:49:09 -03:00
|
|
|
RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zwinski, July 1998.
|
2010-04-17 11:30:53 -03:00
|
|
|
|
|
|
|
RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, UC Irvine, June
|
|
|
|
1995.
|
|
|
|
|
2010-04-29 21:49:09 -03:00
|
|
|
RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
|
2010-04-17 11:30:53 -03:00
|
|
|
McCahill, December 1994
|
|
|
|
|
2010-04-29 21:49:09 -03:00
|
|
|
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
|
2010-04-17 11:30:53 -03:00
|
|
|
test_urlparse.py provides a good indicator of parsing behavior.
|
|
|
|
|
2000-02-04 11:28:42 -04:00
|
|
|
"""
|
1994-09-12 07:36:35 -03:00
|
|
|
|
2002-10-16 18:21:39 -03:00
|
|
|
__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
|
2008-09-03 19:35:50 -03:00
|
|
|
"urlsplit", "urlunsplit", "parse_qs", "parse_qsl"]
|
2001-03-01 00:27:19 -04:00
|
|
|
|
1994-09-12 07:36:35 -03:00
|
|
|
# A classification of schemes ('' means apply by default)
|
2004-05-07 02:50:35 -03:00
|
|
|
uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap',
|
2006-01-20 13:24:23 -04:00
|
|
|
'wais', 'file', 'https', 'shttp', 'mms',
|
|
|
|
'prospero', 'rtsp', 'rtspu', '', 'sftp']
|
2004-05-07 02:50:35 -03:00
|
|
|
uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet',
|
2006-01-20 13:24:23 -04:00
|
|
|
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
|
|
|
|
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '',
|
2010-05-13 00:25:21 -03:00
|
|
|
'svn', 'svn+ssh', 'sftp','nfs','git', 'git+ssh']
|
2004-05-07 02:50:35 -03:00
|
|
|
non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
|
2006-04-01 02:11:07 -04:00
|
|
|
'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
|
2004-05-07 02:50:35 -03:00
|
|
|
uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap',
|
2006-04-01 02:11:07 -04:00
|
|
|
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
|
2006-01-20 13:24:23 -04:00
|
|
|
'mms', '', 'sftp']
|
2004-05-07 02:50:35 -03:00
|
|
|
uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms',
|
2006-04-01 02:11:07 -04:00
|
|
|
'gopher', 'rtsp', 'rtspu', 'sip', 'sips', '']
|
2004-05-07 02:50:35 -03:00
|
|
|
uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news',
|
2006-01-20 13:24:23 -04:00
|
|
|
'nntp', 'wais', 'https', 'shttp', 'snews',
|
|
|
|
'file', 'prospero', '']
|
1994-09-12 07:36:35 -03:00
|
|
|
|
|
|
|
# Characters valid in scheme names
|
2000-12-19 12:48:13 -04:00
|
|
|
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
|
|
|
|
'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
|
|
|
'0123456789'
|
|
|
|
'+-.')
|
1994-09-12 07:36:35 -03:00
|
|
|
|
1997-07-14 16:08:15 -03:00
|
|
|
MAX_CACHE_SIZE = 20
|
1996-05-28 20:54:24 -03:00
|
|
|
_parse_cache = {}
|
|
|
|
|
|
|
|
def clear_cache():
|
2001-01-14 23:34:38 -04:00
|
|
|
"""Clear the parse cache."""
|
2008-01-11 14:04:55 -04:00
|
|
|
_parse_cache.clear()
|
1996-05-28 20:54:24 -03:00
|
|
|
|
|
|
|
|
2008-01-11 14:04:55 -04:00
|
|
|
class ResultMixin(object):
|
|
|
|
"""Shared methods for the parsed result objects."""
|
2006-04-01 18:14:43 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def username(self):
|
|
|
|
netloc = self.netloc
|
|
|
|
if "@" in netloc:
|
2008-01-04 21:21:57 -04:00
|
|
|
userinfo = netloc.rsplit("@", 1)[0]
|
2006-04-01 18:14:43 -04:00
|
|
|
if ":" in userinfo:
|
|
|
|
userinfo = userinfo.split(":", 1)[0]
|
|
|
|
return userinfo
|
|
|
|
return None
|
|
|
|
|
|
|
|
@property
|
|
|
|
def password(self):
|
|
|
|
netloc = self.netloc
|
|
|
|
if "@" in netloc:
|
2008-01-04 21:21:57 -04:00
|
|
|
userinfo = netloc.rsplit("@", 1)[0]
|
2006-04-01 18:14:43 -04:00
|
|
|
if ":" in userinfo:
|
|
|
|
return userinfo.split(":", 1)[1]
|
|
|
|
return None
|
|
|
|
|
|
|
|
@property
|
|
|
|
def hostname(self):
|
2010-04-15 23:46:46 -03:00
|
|
|
netloc = self.netloc.split('@')[-1]
|
|
|
|
if '[' in netloc and ']' in netloc:
|
|
|
|
return netloc.split(']')[0][1:].lower()
|
|
|
|
elif ':' in netloc:
|
|
|
|
return netloc.split(':')[0].lower()
|
|
|
|
elif netloc == '':
|
|
|
|
return None
|
|
|
|
else:
|
|
|
|
return netloc.lower()
|
2006-04-01 18:14:43 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def port(self):
|
2010-04-15 23:46:46 -03:00
|
|
|
netloc = self.netloc.split('@')[-1].split(']')[-1]
|
|
|
|
if ':' in netloc:
|
|
|
|
port = netloc.split(':')[1]
|
2006-04-01 18:14:43 -04:00
|
|
|
return int(port, 10)
|
2010-04-15 23:46:46 -03:00
|
|
|
else:
|
|
|
|
return None
|
2006-04-01 18:14:43 -04:00
|
|
|
|
2008-01-11 14:04:55 -04:00
|
|
|
from collections import namedtuple
|
2006-04-01 18:14:43 -04:00
|
|
|
|
2008-01-11 14:04:55 -04:00
|
|
|
class SplitResult(namedtuple('SplitResult', 'scheme netloc path query fragment'), ResultMixin):
|
2006-04-01 18:14:43 -04:00
|
|
|
|
|
|
|
__slots__ = ()
|
|
|
|
|
|
|
|
def geturl(self):
|
|
|
|
return urlunsplit(self)
|
|
|
|
|
|
|
|
|
2008-01-11 14:04:55 -04:00
|
|
|
class ParseResult(namedtuple('ParseResult', 'scheme netloc path params query fragment'), ResultMixin):
|
2006-04-01 18:14:43 -04:00
|
|
|
|
|
|
|
__slots__ = ()
|
|
|
|
|
|
|
|
def geturl(self):
|
|
|
|
return urlunparse(self)
|
|
|
|
|
|
|
|
|
|
|
|
def urlparse(url, scheme='', allow_fragments=True):
|
2001-01-14 23:34:38 -04:00
|
|
|
"""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."""
|
2001-11-15 22:52:57 -04:00
|
|
|
tuple = urlsplit(url, scheme, allow_fragments)
|
|
|
|
scheme, netloc, url, query, fragment = tuple
|
|
|
|
if scheme in uses_params and ';' in url:
|
|
|
|
url, params = _splitparams(url)
|
|
|
|
else:
|
|
|
|
params = ''
|
2006-04-01 18:14:43 -04:00
|
|
|
return ParseResult(scheme, netloc, url, params, query, fragment)
|
2001-11-15 22:52:57 -04:00
|
|
|
|
|
|
|
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:]
|
|
|
|
|
2005-01-09 11:29:10 -04:00
|
|
|
def _splitnetloc(url, start=0):
|
2008-01-05 18:19:06 -04:00
|
|
|
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)
|
2005-01-09 11:29:10 -04:00
|
|
|
|
2006-04-01 18:14:43 -04:00
|
|
|
def urlsplit(url, scheme='', allow_fragments=True):
|
2001-11-15 22:52:57 -04:00
|
|
|
"""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."""
|
2006-04-01 18:14:43 -04:00
|
|
|
allow_fragments = bool(allow_fragments)
|
2007-12-13 13:58:23 -04:00
|
|
|
key = url, scheme, allow_fragments, type(url), type(scheme)
|
2001-01-14 23:34:38 -04:00
|
|
|
cached = _parse_cache.get(key, None)
|
|
|
|
if cached:
|
|
|
|
return cached
|
|
|
|
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
|
|
|
|
clear_cache()
|
2001-11-15 22:52:57 -04:00
|
|
|
netloc = query = fragment = ''
|
2001-01-14 23:34:38 -04:00
|
|
|
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] == '//':
|
2005-01-09 11:29:10 -04:00
|
|
|
netloc, url = _splitnetloc(url, 2)
|
2010-04-22 09:10:13 -03:00
|
|
|
if (('[' in netloc and ']' not in netloc) or
|
|
|
|
(']' in netloc and '[' not in netloc)):
|
|
|
|
raise ValueError("Invalid IPv6 URL")
|
2001-11-15 22:52:57 -04:00
|
|
|
if allow_fragments and '#' in url:
|
|
|
|
url, fragment = url.split('#', 1)
|
|
|
|
if '?' in url:
|
|
|
|
url, query = url.split('?', 1)
|
2006-04-01 18:14:43 -04:00
|
|
|
v = SplitResult(scheme, netloc, url, query, fragment)
|
|
|
|
_parse_cache[key] = v
|
|
|
|
return v
|
2011-04-15 07:07:33 -03:00
|
|
|
for c in url[:i]:
|
|
|
|
if c not in scheme_chars:
|
|
|
|
break
|
|
|
|
else:
|
|
|
|
try:
|
|
|
|
# make sure "url" is not actually a port number (in which case
|
|
|
|
# "scheme" is really part of the path
|
|
|
|
_testportnum = int(url[i+1:])
|
|
|
|
except ValueError:
|
2010-08-04 01:45:31 -03:00
|
|
|
scheme, url = url[:i].lower(), url[i+1:]
|
2010-02-19 03:32:48 -04:00
|
|
|
|
|
|
|
if url[:2] == '//':
|
2005-01-09 11:29:10 -04:00
|
|
|
netloc, url = _splitnetloc(url, 2)
|
2010-04-22 09:10:13 -03:00
|
|
|
if (('[' in netloc and ']' not in netloc) or
|
|
|
|
(']' in netloc and '[' not in netloc)):
|
|
|
|
raise ValueError("Invalid IPv6 URL")
|
2001-11-15 22:52:57 -04:00
|
|
|
if allow_fragments and scheme in uses_fragment and '#' in url:
|
|
|
|
url, fragment = url.split('#', 1)
|
|
|
|
if scheme in uses_query and '?' in url:
|
|
|
|
url, query = url.split('?', 1)
|
2006-04-01 18:14:43 -04:00
|
|
|
v = SplitResult(scheme, netloc, url, query, fragment)
|
|
|
|
_parse_cache[key] = v
|
|
|
|
return v
|
1994-09-12 07:36:35 -03:00
|
|
|
|
2008-08-02 21:51:02 -03:00
|
|
|
def urlunparse(data):
|
2001-01-14 23:34:38 -04:00
|
|
|
"""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)."""
|
2008-08-02 21:51:02 -03:00
|
|
|
scheme, netloc, url, params, query, fragment = data
|
2001-11-15 22:52:57 -04:00
|
|
|
if params:
|
|
|
|
url = "%s;%s" % (url, params)
|
|
|
|
return urlunsplit((scheme, netloc, url, query, fragment))
|
|
|
|
|
2008-08-02 21:51:02 -03:00
|
|
|
def urlunsplit(data):
|
2010-06-28 10:56:46 -03:00
|
|
|
"""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)."""
|
2008-08-02 21:51:02 -03:00
|
|
|
scheme, netloc, url, query, fragment = data
|
2002-10-14 16:59:54 -03:00
|
|
|
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
|
2001-01-14 23:34:38 -04:00
|
|
|
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 url
|
1994-09-12 07:36:35 -03:00
|
|
|
|
2006-04-01 18:14:43 -04:00
|
|
|
def urljoin(base, url, allow_fragments=True):
|
2001-01-14 23:34:38 -04:00
|
|
|
"""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
|
|
|
|
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 url
|
|
|
|
if scheme in uses_netloc:
|
|
|
|
if netloc:
|
|
|
|
return urlunparse((scheme, netloc, path,
|
|
|
|
params, query, fragment))
|
|
|
|
netloc = bnetloc
|
|
|
|
if path[:1] == '/':
|
|
|
|
return urlunparse((scheme, netloc, path,
|
|
|
|
params, query, fragment))
|
2010-12-17 00:56:02 -04:00
|
|
|
if not path and not params:
|
2008-08-14 13:51:00 -03:00
|
|
|
path = bpath
|
2010-12-17 00:56:02 -04:00
|
|
|
params = bparams
|
2008-08-14 13:51:00 -03:00
|
|
|
if not query:
|
|
|
|
query = bquery
|
|
|
|
return urlunparse((scheme, netloc, path,
|
|
|
|
params, query, fragment))
|
2001-01-14 23:34:38 -04:00
|
|
|
segments = bpath.split('/')[:-1] + path.split('/')
|
|
|
|
# XXX The stuff below is bogus in various ways...
|
|
|
|
if segments[-1] == '.':
|
|
|
|
segments[-1] = ''
|
|
|
|
while '.' in segments:
|
|
|
|
segments.remove('.')
|
|
|
|
while 1:
|
|
|
|
i = 1
|
|
|
|
n = len(segments) - 1
|
|
|
|
while i < n:
|
|
|
|
if (segments[i] == '..'
|
|
|
|
and segments[i-1] not in ('', '..')):
|
|
|
|
del segments[i-1:i+1]
|
|
|
|
break
|
|
|
|
i = i+1
|
|
|
|
else:
|
|
|
|
break
|
|
|
|
if segments == ['', '..']:
|
|
|
|
segments[-1] = ''
|
|
|
|
elif len(segments) >= 2 and segments[-1] == '..':
|
|
|
|
segments[-2:] = ['']
|
|
|
|
return urlunparse((scheme, netloc, '/'.join(segments),
|
|
|
|
params, query, fragment))
|
1994-09-12 07:36:35 -03:00
|
|
|
|
1996-05-28 20:54:24 -03:00
|
|
|
def urldefrag(url):
|
2001-01-14 23:34:38 -04:00
|
|
|
"""Removes any existing fragment from URL.
|
1996-05-28 20:54:24 -03:00
|
|
|
|
2001-01-14 23:34:38 -04:00
|
|
|
Returns a tuple of the defragmented URL and the fragment. If
|
|
|
|
the URL contained no fragments, the second element is the
|
|
|
|
empty string.
|
|
|
|
"""
|
2001-11-15 22:52:57 -04:00
|
|
|
if '#' in url:
|
|
|
|
s, n, p, a, q, frag = urlparse(url)
|
|
|
|
defrag = urlunparse((s, n, p, a, q, ''))
|
|
|
|
return defrag, frag
|
|
|
|
else:
|
|
|
|
return url, ''
|
1996-05-28 20:54:24 -03:00
|
|
|
|
2008-09-03 19:35:50 -03:00
|
|
|
# unquote method for parse_qs and parse_qsl
|
2010-05-25 12:20:46 -03:00
|
|
|
# Cannot use directly from urllib as it would create a circular reference
|
|
|
|
# because urllib uses urlparse methods (urljoin). If you update this function,
|
|
|
|
# update it also in urllib. This code duplication does not existin in Python3.
|
2010-03-18 09:14:15 -03:00
|
|
|
|
|
|
|
_hexdig = '0123456789ABCDEFabcdef'
|
2010-05-25 12:20:46 -03:00
|
|
|
_hextochr = dict((a+b, chr(int(a+b,16)))
|
|
|
|
for a in _hexdig for b in _hexdig)
|
2008-09-03 19:35:50 -03:00
|
|
|
|
|
|
|
def unquote(s):
|
|
|
|
"""unquote('abc%20def') -> 'abc def'."""
|
|
|
|
res = s.split('%')
|
2010-05-25 12:20:46 -03:00
|
|
|
# fastpath
|
|
|
|
if len(res) == 1:
|
|
|
|
return s
|
|
|
|
s = res[0]
|
|
|
|
for item in res[1:]:
|
2008-09-03 19:35:50 -03:00
|
|
|
try:
|
2010-05-25 12:20:46 -03:00
|
|
|
s += _hextochr[item[:2]] + item[2:]
|
2008-09-03 19:35:50 -03:00
|
|
|
except KeyError:
|
2010-05-25 12:20:46 -03:00
|
|
|
s += '%' + item
|
2008-09-03 19:35:50 -03:00
|
|
|
except UnicodeDecodeError:
|
2010-05-25 12:20:46 -03:00
|
|
|
s += unichr(int(item[:2], 16)) + item[2:]
|
|
|
|
return s
|
2008-09-03 19:35:50 -03:00
|
|
|
|
|
|
|
def parse_qs(qs, keep_blank_values=0, strict_parsing=0):
|
|
|
|
"""Parse a query given as a string argument.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
|
2010-08-09 17:18:04 -03:00
|
|
|
qs: percent-encoded query string to be parsed
|
2008-09-03 19:35:50 -03:00
|
|
|
|
|
|
|
keep_blank_values: flag indicating whether blank values in
|
2010-08-09 17:18:04 -03:00
|
|
|
percent-encoded queries should be treated as blank strings.
|
2008-09-03 19:35:50 -03:00
|
|
|
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.
|
|
|
|
"""
|
|
|
|
dict = {}
|
|
|
|
for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):
|
|
|
|
if name in dict:
|
|
|
|
dict[name].append(value)
|
|
|
|
else:
|
|
|
|
dict[name] = [value]
|
|
|
|
return dict
|
|
|
|
|
|
|
|
def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
|
|
|
|
"""Parse a query given as a string argument.
|
|
|
|
|
|
|
|
Arguments:
|
|
|
|
|
2010-08-09 17:18:04 -03:00
|
|
|
qs: percent-encoded query string to be parsed
|
2008-09-03 19:35:50 -03:00
|
|
|
|
|
|
|
keep_blank_values: flag indicating whether blank values in
|
2010-08-09 17:18:04 -03:00
|
|
|
percent-encoded queries should be treated as blank strings. A
|
2008-09-03 19:35:50 -03:00
|
|
|
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.
|
|
|
|
|
|
|
|
Returns a list, as G-d intended.
|
|
|
|
"""
|
|
|
|
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
|
|
|
|
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 = unquote(nv[0].replace('+', ' '))
|
|
|
|
value = unquote(nv[1].replace('+', ' '))
|
|
|
|
r.append((name, value))
|
|
|
|
|
|
|
|
return r
|