Regex pattern to split the hostname from url path

url_regex.py

import re 
def url_path_to_dict(path):
    pattern = (r'^'
               r'((?P<schema>.+?)://)?'
               r'((?P<user>.+?)(:(?P<password>.*?))?@)?'
               r'(?P<host>.*?)'
               r'(:(?P<port>\d+?))?'
               r'(?P<path>/.*?)?'
               r'(?P<query>[?].*?)?'
               r'$'
               )
    regex = re.compile(pattern)
    m = regex.match(path)
    d = m.groupdict() if m is not None else None

    return d

def main():
    return (url_path_to_dict(
        'http://ibrahim:password@example.example.com/example/example/example.html'))
    
data = main()

print(data)

# output:

{
  'schema': 'http',
  'user': 'ibrahim', 
  'password': 'password', 
  'host': 'example.example.com',
  'port': None,
  'path': '/example/example/example.html',
  'query': None
}