8 RFC 2732 : "Format for Literal IPv6 Addresses in URL's by R.Hinden, B.Carpenter
14 RFC 2368: "The mailto URL scheme", by P.Hoffman , L Masinter, J. Zwinski, July 1998.
19 RFC 1738: "Uniform Resource Locators (URL)" by T. Berners-Lee, L. Masinter, M.
137 def urlparse(url, scheme='', allow_fragments=True):  argument
138     """Parse a URL into 6 components:
143     tuple = urlsplit(url, scheme, allow_fragments)
144     scheme, netloc, url, query, fragment = tuple
145     if scheme in uses_params and ';' in url:
146         url, params = _splitparams(url)
149     return ParseResult(scheme, netloc, url, params, query, fragment)
151 def _splitparams(url):  argument
152     if '/'  in url:
153         i = url.find(';', url.rfind('/'))
155             return url, ''
157         i = url.find(';')
158     return url[:i], url[i+1:]
160 def _splitnetloc(url, start=0):  argument
161     delim = len(url)   # position of end of domain part of url, default is end
163         wdelim = url.find(c, start)        # find first of this delim
166     return url[start:delim], url[delim:]   # return (domain, rest)
168 def urlsplit(url, scheme='', allow_fragments=True):  argument
169     """Parse a URL into 5 components:
175     key = url, scheme, allow_fragments, type(url), type(scheme)
182     i = url.find(':')
184         if url[:i] == 'http': # optimize the common case
185             scheme = url[:i].lower()
186             url = url[i+1:]
187             if url[:2] == '//':
188                 netloc, url = _splitnetloc(url, 2)
191                     raise ValueError("Invalid IPv6 URL")
192             if allow_fragments and '#' in url:
193                 url, fragment = url.split('#', 1)
194             if '?' in url:
195                 url, query = url.split('?', 1)
196             v = SplitResult(scheme, netloc, url, query, fragment)
199         for c in url[:i]:
203             # make sure "url" is not actually a port number (in which case
205             rest = url[i+1:]
208                 scheme, url = url[:i].lower(), rest
210     if url[:2] == '//':
211         netloc, url = _splitnetloc(url, 2)
214             raise ValueError("Invalid IPv6 URL")
215     if allow_fragments and '#' in url:
216         url, fragment = url.split('#', 1)
217     if '?' in url:
218         url, query = url.split('?', 1)
219     v = SplitResult(scheme, netloc, url, query, fragment)
224     """Put a parsed URL back together again.  This may result in a
225     slightly different, but equivalent URL, if the URL that was parsed
228     scheme, netloc, url, params, query, fragment = data
230         url = "%s;%s" % (url, params)
231     return urlunsplit((scheme, netloc, url, query, fragment))
235     complete URL as a string. The data argument can be any five-item iterable.
236     This may result in a slightly different, but equivalent URL, if the URL that
239     scheme, netloc, url, query, fragment = data
240     if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
241         if url and url[:1] != '/': url = '/' + url
242         url = '//' + (netloc or '') + url
244         url = scheme + ':' + url
246         url = url + '?' + query
248         url = url + '#' + fragment
249     return url
251 def urljoin(base, url, allow_fragments=True):  argument
252     """Join a base URL and a possibly relative URL to form an absolute
255         return url
256     if not url:
261             urlparse(url, bscheme, allow_fragments)
263         return url
303 def urldefrag(url):  argument
304     """Removes any existing fragment from URL.
306     Returns a tuple of the defragmented URL and the fragment.  If
307     the URL contained no fragments, the second element is the
310     if '#' in url:
311         s, n, p, a, q, frag = urlparse(url)
315         return url, ''