1
0
Fork 0
mirror of synced 2024-06-24 17:10:21 +12:00

dont parse quotes as part of urls

This commit is contained in:
Nick Sweeting 2019-02-04 18:54:02 -08:00
parent af8b9b5fdf
commit 3ac0efb619

View file

@ -43,7 +43,7 @@ base_url = lambda url: without_scheme(url) # uniq base url used to dedupe links
short_ts = lambda ts: ts.split('.')[0]
URL_REGEX = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))[^<]+'
URL_REGEX = 'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))[^<\""]+'
def check_dependencies():