Detect URLs in a string and wrap with “<a

Question

I am looking to write something that seems like it should be easy enough, but for whatever reason I\'m having a tough time getting my head around it.

I am looking to

Answer 1

Googled solutions:

#---------- find_urls.py----------#
# Functions to identify and extract URLs and email addresses

import re

def fix_urls(text):
    pat_url = re.compile(  r'''
                     (?x)( # verbose identify URLs within text
         (http|ftp|gopher) # make sure we find a resource type
                       :// # ...needs to be followed by colon-slash-slash
            (\w+[:.]?){2,} # at least two domain groups, e.g. (gnosis.)(cx)
                      (/?| # could be just the domain name (maybe w/ slash)
                [^ \n\r"]+ # or stuff then space, newline, tab, quote
                    [\w/]) # resource name ends in alphanumeric or slash
         (?=[\s\.,>)'"\]]) # assert: followed by white or clause ending
                         ) # end of match group
                           ''')
    pat_email = re.compile(r'''
                    (?xm)  # verbose identify URLs in text (and multiline)
                 (?=^.{11} # Mail header matcher
         (?)'"\]]) # assert: followed by white or clause ending
                         ) # end of match group
                           ''')

    for url in re.findall(pat_url, text):
       text = text.replace(url[0], '%(url)s' % {"url" : url[0]})

    for email in re.findall(pat_email, text):
       text = text.replace(email[1], '%(email)s' % {"email" : email[1]})

    return text

if __name__ == '__main__':
    print fix_urls("test http://google.com asdasdasd some more text")

EDIT: Adjusted to your needs