Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-22 12:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity

ensure DOM HTML dump is non-zero length file when retrying

Browse source
This commit is contained in:
Nick Sweeting 2023-03-13 10:49:26 +00:00
parent f94e8cd9b2
commit 9599845b56
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
archivebox/extractors/dom.py
View file

@ -26,7 +26,8 @@ def should_save_dom(link: Link, out_dir: Optional[Path]=None, overwrite: Optiona
out_dir = out_dir or Path(link.link_dir)
if not overwrite and (out_dir / 'output.html').exists():
return False
if (out_dir / 'output.html').stat().st_size > 1:
return False
return SAVE_DOM