mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-24 19:54:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

new archivebox update speed improvements

Browse source
This commit is contained in:
Nick Sweeting 2024-02-22 04:49:09 -08:00
parent 2d32f05a62
commit 6a4e568d1b
8 changed files with 36 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

2
archivebox/extractors/title.py
View file

@ -75,7 +75,7 @@ def get_html(link: Link, path: Path, timeout: int=TIMEOUT) -> str:
with open(abs_path / source, "r", encoding="utf-8") as f:
document = f.read()
break
except (FileNotFoundError, TypeError):
except (FileNotFoundError, TypeError, UnicodeDecodeError):
continue
if document is None:
return download_url(link.url, timeout=timeout)