mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-24 11:47:04 -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

10
archivebox/extractors/pdf.py
View file

@ -19,13 +19,17 @@ from ..config import (
from ..logging_util import TimedProgress
def get_output_path():
return 'output.pdf'
@enforce_types
def should_save_pdf(link: Link, out_dir: Optional[Path]=None, overwrite: Optional[bool]=False) -> bool:
if is_static_file(link.url):
return False
out_dir = out_dir or Path(link.link_dir)
if not overwrite and (out_dir / 'output.pdf').exists():
if not overwrite and (out_dir / get_output_path()).exists():
return False
return SAVE_PDF
@ -36,7 +40,7 @@ def save_pdf(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
"""print PDF of site to file using chrome --headless"""
out_dir = out_dir or Path(link.link_dir)
output: ArchiveOutput = 'output.pdf'
output: ArchiveOutput = get_output_path()
cmd = [
*chrome_args(),
'--print-to-pdf',
@ -51,7 +55,7 @@ def save_pdf(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
hints = (result.stderr or result.stdout).decode()
raise ArchiveError('Failed to save PDF', hints)
chmod_file('output.pdf', cwd=str(out_dir))
chmod_file(get_output_path(), cwd=str(out_dir))
except Exception as err:
status = 'failed'
output = err