mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-16 08:04:26 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Refactor should_save_extractor methods to accept overwrite parameter

Browse source
This commit is contained in:
Dan Arnfield 2021-01-21 15:45:11 -06:00
parent 553c3ca219
commit 5420903102
14 changed files with 56 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

8
archivebox/extractors/title.py
View file

@ -61,12 +61,12 @@ class TitleParser(HTMLParser):
@enforce_types
def should_save_title(link: Link, out_dir: Optional[str]=None) -> bool:
# if link already has valid title, skip it
if link.title and not link.title.lower().startswith('http'):
def should_save_title(link: Link, out_dir: Optional[str]=None, overwrite: Optional[bool]=False) -> bool:
if is_static_file(link.url):
return False
if is_static_file(link.url):
# if link already has valid title, skip it
if not overwrite and link.title and not link.title.lower().startswith('http'):
return False
return SAVE_TITLE