mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-21 18:35:23 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

load EXTRACTORS dynamically using importlib.import_module

Browse source
This commit is contained in:
Nick Sweeting 2024-05-11 22:28:59 -07:00
parent c7f55fc3ba
commit 457c42bf84
No known key found for this signature in database
18 changed files with 198 additions and 40 deletions
Download patch file Download diff file Expand all files Collapse all files

8
archivebox/extractors/title.py
View file

@ -60,6 +60,7 @@ class TitleParser(HTMLParser):
if tag.lower() == "title":
self.inside_title_tag = False
@enforce_types
def get_html(link: Link, path: Path, timeout: int=TIMEOUT) -> str:
"""
@ -84,6 +85,13 @@ def get_html(link: Link, path: Path, timeout: int=TIMEOUT) -> str:
else:
return document
def get_output_path():
# TODO: actually save title to this file
# (currently only saved in ArchiveResult.output as charfield value, not saved to filesystem)
return 'title.json'
@enforce_types
def should_save_title(link: Link, out_dir: Optional[str]=None, overwrite: Optional[bool]=False) -> bool:
# if link already has valid title, skip it