mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 22:54:27 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix url parsing through quotes

Browse source
This commit is contained in:
Nick Sweeting 2020-08-18 08:04:57 -04:00
parent a218ceb4e8
commit 3658153cf8
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
archivebox/util.py
View file

@ -59,7 +59,7 @@ URL_REGEX = re.compile(
r'(?:[a-zA-Z]|[0-9]' # followed by allowed alphanum characters r'(?:[a-zA-Z]|[0-9]' # followed by allowed alphanum characters
r'|[$-_@.&+]|[!*\(\),]' # or allowed symbols r'|[$-_@.&+]|[!*\(\),]' # or allowed symbols
r'|(?:%[0-9a-fA-F][0-9a-fA-F]))' # or allowed unicode bytes r'|(?:%[0-9a-fA-F][0-9a-fA-F]))' # or allowed unicode bytes
r'[^\]\[\(\)<>\""\'\s]+', # stop parsing at these symbols r'[^\]\[\(\)<>"\'\s]+', # stop parsing at these symbols
re.IGNORECASE, re.IGNORECASE,
) )