mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-17 20:01:44 +02:00
Code Issues Releases Wiki Activity

Merge pull request #1242 from benmuth/fix-titles-with-empty-tag

Browse Source
This commit is contained in:
Nick Sweeting
2023-10-09 21:39:26 -07:00
committed by GitHub
parent 4950cee3b6 77917e9b55
commit dcef217e5e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
archivebox/extractors/title.py
View File

@@ -26,7 +26,7 @@ from ..logging_util import TimedProgress
HTML_TITLE_REGEX = re.compile( HTML_TITLE_REGEX = re.compile(
r'<title.*?>' # start matching text after <title> tag r'<title.*?>' # start matching text after <title> tag
r'(.[^<>]+)', # get everything up to these symbols r'([^<>]+)', # get everything up to these symbols
re.IGNORECASE | re.MULTILINE | re.DOTALL | re.UNICODE, re.IGNORECASE | re.MULTILINE | re.DOTALL | re.UNICODE,
) )