Created
October 21, 2015 16:58
-
-
Save faisalmahmud/e86c31d20705cbb8d44e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment