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

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

9
archivebox/extractors/dom.py
View file

@ -19,6 +19,9 @@ from ..config import (
from ..logging_util import TimedProgress
def get_output_path():
return 'output.html'
@enforce_types
def should_save_dom(link: Link, out_dir: Optional[Path]=None, overwrite: Optional[bool]=False) -> bool:
@ -26,8 +29,8 @@ def should_save_dom(link: Link, out_dir: Optional[Path]=None, overwrite: Optiona
return False
out_dir = out_dir or Path(link.link_dir)
if not overwrite and (out_dir / 'output.html').exists():
if (out_dir / 'output.html').stat().st_size > 1:
if not overwrite and (out_dir / get_output_path()).exists():
if (out_dir / get_output_path()).stat().st_size > 1:
return False
return SAVE_DOM
@ -37,7 +40,7 @@ def save_dom(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
"""print HTML of site to file using chrome --dump-html"""
out_dir = out_dir or Path(link.link_dir)
output: ArchiveOutput = 'output.html'
output: ArchiveOutput = get_output_path()
output_path = out_dir / output
cmd = [
*chrome_args(),