A couple of decent regular expressions to find URLs and email addresses

usefUlll_regex.py

#A couple of decent regular expressions to find URLs and email addresses
 
urlRe = re.compile(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
#See http://www.regular-expressions.info/email.html
emailRe = re.compile(r'[a-zA-Z0-9+_\-\.]+@[0-9a-zA-Z][.-0-9a-zA-Z]*\.[a-zA-Z]+')
 
someString = "Lorem ipsum dolor http://google.com/ consectetuer elit. Aliquam \
scelerisque felis. Nulla lacinia - info@subdomain.mah.se. Suspendisse elementum \
lacus. Suspendisse potenti. Etiam et id lorem congue aliquam. Aenean venenatis, \
elit commodo pretium aliquet, dolor webmaster@yahoo.com, ut iaculis est ante at \
nisl. Nam auctor. Curabitur id dolor. http://www.last.fm sem fermentum libero."
 
print urlRe.findall(someString)
print emailRe.findall(someString)
 
# This will generate the following:
# ['http://google.com/', 'http://www.last.fm']
# ['info@subdomain.mah.se', 'webmaster@yahoo.com']