#!/usr/bin/python
 
import re
 
def convertLinks(str):
    #crazy regex from Shag, based on http://flanders.co.nz/2009/11/08/a-good-url-regular-expression-repost/
 
    prog = re.compile(r'(?#FQURL)(?:(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/)(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)*(?#TopLevel Domains)(?:[a-z]+\.?))(?#Port)(?::[\d]{1,5})?\.?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/|)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?|(?#BareURL)(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)+(?#TopLevel Domains)(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|museum|travel|[a-z]{2}))(?#Port)(?::[\d]{1,5})?\.?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/|)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?)')
 
    return prog.sub(r'<a href="\g&lt;0&gt;">\g&lt;0&gt;</a>', str)
 
#single url
print convertLinks('http://tikirobot.net\n')
 
#string
print convertLinks('See http://tikirobot.net for more info.\n')
 
#string w/ anchor
print convertLinks('See http://tikirobot.net/#foo for more info.\n')
 
#two urls in a string
print convertLinks('See http://tikirobot.net or http://wikipedia.org for more info.\n')
 
#some test urls from flanders.co.nz
print convertLinks('This is a google search: http://www.google.com/search?q=good+url+regex&amp;rls=com.microsoft:*&amp;ie=UTF-8&amp;oe=UTF-8&amp;startIndex=&amp;startPage=1\n')
 
print convertLinks('ftp://joe:password@ftp.filetransferprotocal.com is a ftp url\n')
 
print convertLinks('There is a bare url google.ru somewhere in this sentence\n')
 
#test cases from shag
print convertLinks('query string: https://some-url.com/?query=&amp;name=joe&amp;filter=*.*\n')
 
print convertLinks('both a query string and an anchor with no host name separator slash: https://some-url.com?query=&amp;name=joe?filter=*.*#some_anchor\n')
 
print convertLinks('both a query string and an anchor: https://some-url.com/?query=&amp;name=joe&amp;filter=*.*#some_anchor\n')
 
print convertLinks('DNS name with a concluding period: http://some-url.com./\n')
 
print convertLinks('DNS name with a concluding period and query string: http://some-url.com./?foo=bar\n')
 
print convertLinks('single-component DNS name plus root: http://to./\n')
 
print convertLinks('single-component DNS name: http://to/\n')
 
print convertLinks('words with slashes: unread/unregistered\n')