In [1]:

    

import re


    

In [2]:

    

url = 'https://duckduckgo.com/l/?kh=-1&uddg=https%3A%2F%2Fdocs.python.org%2F3.3%2Flibrary%2Fre.html'


    

In [3]:

    

prefix_pattern = re.compile(r'^https://duckduckgo.com/.*?&uddg=')
url = re.sub(prefix_pattern, '', url, 1)
url


    

    
Out[3]:





'https%3A%2F%2Fdocs.python.org%2F3.3%2Flibrary%2Fre.html'

In [4]:

    

escape_pattern = re.compile(r'%([0-9A-F][0-9A-F])')
re.split(escape_pattern, url)


    

    
Out[4]:





['https',
 '3A',
 '',
 '2F',
 '',
 '2F',
 'docs.python.org',
 '2F',
 '3.3',
 '2F',
 'library',
 '2F',
 're.html']

In [5]:

    

from urllib.parse import unquote


    

In [6]:

    

unquote(url)


    

    
Out[6]:





'https://docs.python.org/3.3/library/re.html'

In [7]:

    

#!/usr/bin/env python3

import sys
import re
from urllib.parse import unquote

def main(lines):
    prefix_pattern = re.compile(r'^https://duckduckgo.com/.*?&uddg=')

    for url in lines:
        # print(1, repr(url))
        url = re.sub(prefix_pattern, '', url, 1)
        # print(2, repr(url))
        print(unquote(url))

if __name__ == '__main__':
    # main(sys.stdin)
    main(['https://duckduckgo.com/l/?kh=-1&uddg=https%3A%2F%2Fdocs.python.org%2F3.3%2Flibrary%2Fre.html'])


    

    




https://docs.python.org/3.3/library/re.html