gistfile1.txt

import re
import HTMLParser

def get_urls_from_text(text):
    # See: http://daringfireball.net/2010/07/improved_regex_for_matching_urls
    # Copied from http://copia.posthaven.com/finding-urls-in-plain-text
    parser = HTMLParser.HTMLParser()
    GRUBER_URLINTEXT_PAT = re.compile(ur'(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'".,<>?\xab\xbb\u201c\u201d\u2018\u2019]))')
    # Remove HTML entities from url
    urls = [parser.unescape(mgroups[0]) for mgroups in GRUBER_URLINTEXT_PAT.findall(text)]
    return urls