from collections import namedtuple from ..exceptions import LocationParseError url_attrs = ['scheme', 'auth', 'host', 'port', 'path', 'query', 'fragment'] class Url(namedtuple('Url', url_attrs)): """ Datastructure for representing an HTTP URL. Used as a return value for :func:`parse_url`. """ slots = () def __new__(cls, scheme=None, auth=None, host=None, port=None, path=None, query=None, fragment=None): return super(Url, cls).__new__(cls, scheme, auth, host, port, path, query, fragment) @property def hostname(self): """For backwards-compatibility with urlparse. We're nice like that.""" return self.host @property def request_uri(self): """Absolute path including the query string.""" uri = self.path or '/' if self.query is not None: uri += '?' + self.query return uri @property def netloc(self): """Network location including host and port""" if self.port: return '%s:%d' % (self.host, self.port) return self.host def split_first(s, delims): """ Given a string and an iterable of delimiters, split on the first found delimiter. Return two split parts and the matched delimiter. If not found, then the first part is the full input string. Example:: >>> split_first('foo/bar?baz', '?/=') ('foo', 'bar?baz', '/') >>> split_first('foo/bar?baz', '123') ('foo/bar?baz', '', None) Scales linearly with number of delims. Not ideal for large number of delims. """ min_idx = None min_delim = None for d in delims: idx = s.find(d) if idx < 0: continue if min_idx is None or idx < min_idx: min_idx = idx min_delim = d if min_idx is None or min_idx < 0: return s, '', None return s[:min_idx], s[min_idx+1:], min_delim def parse_url(url): """ Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is performed to parse incomplete urls. Fields not provided will be None. Partly backwards-compatible with :mod:`urlparse`. Example:: >>> parse_url('http://google.com/mail/') Url(scheme='http', host='google.com', port=None, path='/', ...) >>> parse_url('google.com:80') Url(scheme=None, host='google.com', port=80, path=None, ...) >>> parse_url('/foo?bar') Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...) """ # While this code has overlap with stdlib's urlparse, it is much # simplified for our needs and less annoying. # Additionally, this implementations does silly things to be optimal # on CPython. if not url: # Empty return Url() scheme = None auth = None host = None port = None path = None fragment = None query = None # Scheme if '://' in url: scheme, url = url.split('://', 1) # Find the earliest Authority Terminator # (http://tools.ietf.org/html/rfc3986#section-3.2) url, path_, delim = split_first(url, ['/', '?', '#']) if delim: # Reassemble the path path = delim + path_ # Auth if '@' in url: # Last '@' denotes end of auth part auth, url = url.rsplit('@', 1) # IPv6 if url and url[0] == '[': host, url = url.split(']', 1) host += ']' # Port if ':' in url: _host, port = url.split(':', 1) if not host: host = _host if port: # If given, ports must be integers. if not port.isdigit(): raise LocationParseError(url) port = int(port) else: # Blank ports are cool, too. (rfc3986#section-3.2.3) port = None elif not host and url: host = url if not path: return Url(scheme, auth, host, port, path, query, fragment) # Fragment if '#' in path: path, fragment = path.split('#', 1) # Query if '?' in path: path, query = path.split('?', 1) return Url(scheme, auth, host, port, path, query, fragment) def get_host(url): """ Deprecated. Use :func:`.parse_url` instead. """ p = parse_url(url) return p.scheme or 'http', p.hostname, p.port