Decodifica um url em partes

da_urllib.py

# -*- coding: utf-8 -*-
# da_urllib.py
# by [email protected]
import urllib


def urldencode(params):
    resp = {}
    for item in params.split('&'):
        if not item:
            continue
        ritem = item.split('=')
        value = None
        if len(ritem) > 1:
            value = urllib.unquote_plus(''.join(ritem[1:]))
        if ritem[0] not in resp:
            resp[ritem[0]] = value
        else:
            if not isinstance(resp[ritem[0]], list):
                resp[ritem[0]] = [resp[ritem[0]]]
            resp[ritem[0]].append(value)
    return resp
    return dict((
        (ritem[0], None if len(ritem) == 1
        else urllib.unquote_plus(''.join(ritem[1:])))
        for ritem in (item.split('=')
        for item in params.split('&') if item)
    ))

def extract_url(url):
    protocol = 'http'
    host = None
    path = None
    fragment = None
    if '://' in url:
        rurl = url.split('://')
        protocol = rurl[0]
        url = ''.join(rurl[1:])
    if '/' in url:
        rurl = url.split('/')
        host = rurl[0]
        url = '/'.join(rurl[1:])
    if '?' in url:
        rurl = url.split('?')
        path = rurl[0]
        url = ''.join(rurl[1:])
    if '#' in url:
        rurl = url.split('#')
        fragment = '#'.join(rurl[1:])
        url = rurl[0]
    return dict(
        protocol=protocol,
        host=host,
        path=path,
        fragment=fragment,
        query=urldencode(url)
    )

if __name__ == '__main__':
    import pprint
    pprint.pprint((urldencode('')))
    # {}
    pprint.pprint((urldencode('a=SleX&c=cc&b=Slex+%26+CIA&teste')))
    # {'a': 'SleX', 'b': 'Slex & CIA', 'c': 'cc', 'teste': None}
    pprint.pprint(
        extract_url(
            url=(
                'http://www.slex.com.br/teste/aaa'
            )
        )
    )
    # {'fragment': None,
    #  'host': 'www.slex.com.br',
    #  'path': None,
    #  'protocol': 'http',
    #  'query': {'teste/aaa': None}}
    pprint.pprint(
        extract_url(
            url=(
                'http://www.slex.com.br/teste/aaa?' +
                'a=SleX&c=cc&b=Slex+%26+CIA&teste'
            )
        )
    )
    # {'fragment': None,
    #  'host': 'www.slex.com.br',
    #  'path': 'teste/aaa',
    #  'protocol': 'http',
    #  'query': {'a': 'SleX', 'b': 'Slex & CIA', 'c': 'cc', 'teste': None}}
    pprint.pprint(
        extract_url(
            url=(
                'http://www.slex.com.br/teste/aaa?' +
                'nome=SleX&nome=Alex&c=cc&b=Slex+%26+CIA&teste#ancora'
            )
        )
    )
    # {'fragment': 'ancora',
    #  'host': 'www.slex.com.br',
    #  'path': 'teste/aaa',
    #  'protocol': 'http',
    #  'query': {'b': 'Slex & CIA',
    #            'c': 'cc',
    #            'nome': ['SleX', 'Alex'],
    #           'teste': None}}