mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-28 05:34:14 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: pdf uses snapshot instead of link

Browse source
This commit is contained in:
Cristian 2020-12-29 13:58:51 -05:00
parent 5cf9ca0e2c
commit 756b7fc76d
1 changed files with 8 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

14
archivebox/extractors/pdf.py
View file

@ -3,6 +3,8 @@ __package__ = 'archivebox.extractors'
from pathlib import Path
from typing import Optional
from django.db.models import Model
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
from ..system import run, chmod_file
from ..util import (
@ -19,9 +21,9 @@ from ..logging_util import TimedProgress
@enforce_types
def should_save_pdf(link: Link, out_dir: Optional[Path]=None) -> bool:
out_dir = out_dir or Path(link.link_dir)
if is_static_file(link.url):
def should_save_pdf(snapshot: Model, out_dir: Optional[Path]=None) -> bool:
out_dir = out_dir or Path(snapshot.snapshot_dir)
if is_static_file(snapshot.url):
return False
if (out_dir / "output.pdf").exists():
@ -31,15 +33,15 @@ def should_save_pdf(link: Link, out_dir: Optional[Path]=None) -> bool:
@enforce_types
def save_pdf(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) -> ArchiveResult:
def save_pdf(snapshot: Model, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) -> ArchiveResult:
"""print PDF of site to file using chrome --headless"""
out_dir = out_dir or Path(link.link_dir)
out_dir = out_dir or Path(snapshot.snapshot_dir)
output: ArchiveOutput = 'output.pdf'
cmd = [
*chrome_args(TIMEOUT=timeout),
'--print-to-pdf',
link.url,
snapshot.url,
]
status = 'succeeded'
timer = TimedProgress(timeout, prefix=' ')