ajinabraham · September 21, 2015 15:23
diff --git a/python_url_extractor_regex.py b/python_url_extractor_regex.py

 import re, urllib

 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]))')

 for line in urllib.urlopen("http://daringfireball.net/misc/2010/07/url-matching-regex-test-data.text"):
    print [ mgroups[0] for mgroups in PAT.findall(line) ]

	import re, urllib

	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]))')

	for line in urllib.urlopen("http://daringfireball.net/misc/2010/07/url-matching-regex-test-data.text"):
	print [ mgroups[0] for mgroups in PAT.findall(line) ]