mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-13 06:34:25 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

prefer dom dump to singlefile for generating readability output

Browse source
This commit is contained in:
Nick Sweeting 2024-01-03 20:11:06 -08:00
parent 78d942ac22
commit db2984e47b
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
archivebox/extractors/title.py
View file

@ -66,7 +66,9 @@ def get_html(link: Link, path: Path, timeout: int=TIMEOUT) -> str:
""" """
canonical = link.canonical_outputs() canonical = link.canonical_outputs()
abs_path = path.absolute() abs_path = path.absolute()
sources = [canonical["singlefile_path"], canonical["wget_path"], canonical["dom_path"]]
# prefer chrome-generated DOM dump to singlefile as singlefile output often includes HUGE url(data:image/...base64) strings that crash parsers
sources = [canonical["dom_path"], canonical["singlefile_path"], canonical["wget_path"]]
document = None document = None
for source in sources: for source in sources:
try: try: