Robots Blog

#!/usr/bin/python
 
import re
 
def convertLinks(str):
    #crazy regex from http://flanders.co.nz/2009/11/08/a-good-url-regular-expression-repost/
    prog = re.compile(r'(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/|~\/|\/)?(?#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<0>">\g<0></a>', str)
 
#single url        
print convertLinks('http://tikirobot.net\n')
 
#string
print convertLinks('See http://tikirobot.net 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&rls=com.microsoft:*&ie=UTF-8&oe=UTF-8&startIndex=&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')
 
#This one fails
print convertLinks('This one fails: both a query string and an anchor: https://some-url.com?query=&name=joe?filter=*.*#some_anchor\n')