Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2025-02-16 21:38:33 +00:00
Code Issues Projects Releases Packages Wiki Activity

dont parse quotes as part of urls

Browse source
This commit is contained in:
Nick Sweeting 2019-02-04 18:54:02 -08:00
parent af8b9b5fdf
commit 3ac0efb619
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
archivebox/util.py
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():