regex to capture and validate url, currently support capture scheme, username, password, host, port, path, query and fragment

regex_url.py

import re

regex_url = re.compile("^(?:(?P<scheme>https?|ftps?):\/\/)?(?:(?:(?P<username>[\w\.\-\+%!$&'\(\)*\+,;=]+):*(?P<password>[\w\.\-\+%!$&'\(\)*\+,;=]+))@)?(?P<host>[a-z0-9-]+(?:\.[a-z0-9-]+)*(?:\.[a-z\.]{2,6})+)(?:\:(?P<port>[0-9]+))?(?P<path>\/(?:[\w_ \/\-\.~%!\$&\'\(\)\*\+,;=:@]+)?)?(?:\?(?P<query>[\w_ \-\.~%!\$&\'\(\)\*\+,;=:@\/]*))?(?:(?P<fragment>#[\w_ \-\.~%!\$&\'\(\)\*\+,;=:@\/]*))?$", re.IGNORECASE)

example_url = "http://username:[email protected]:130892/some/path/to/folder?query1=1&query2=2#go-to-fragment"

match_test = re.match(regex_url, example_url)
if match_test:
    print match_test.groupdict()