mirror of
https://github.com/ArchiveBox/ArchiveBox
synced 2024-12-12 13:52:30 +00:00
69 lines
1.6 KiB
Python
69 lines
1.6 KiB
Python
__package__ = 'archivebox.extractors'
|
|
|
|
import os
|
|
|
|
from typing import Optional
|
|
|
|
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
|
|
from ..system import run, chmod_file
|
|
from ..util import (
|
|
enforce_types,
|
|
is_static_file,
|
|
chrome_args,
|
|
)
|
|
from ..config import (
|
|
TIMEOUT,
|
|
SAVE_PDF,
|
|
CHROME_VERSION,
|
|
)
|
|
from ..cli.logging import TimedProgress
|
|
|
|
|
|
@enforce_types
|
|
def should_save_pdf(link: Link, out_dir: Optional[str]=None) -> bool:
|
|
out_dir = out_dir or link.link_dir
|
|
if is_static_file(link.url):
|
|
return False
|
|
|
|
if os.path.exists(os.path.join(out_dir, 'output.pdf')):
|
|
return False
|
|
|
|
return SAVE_PDF
|
|
|
|
|
|
@enforce_types
|
|
def save_pdf(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
|
|
"""print PDF of site to file using chrome --headless"""
|
|
|
|
out_dir = out_dir or link.link_dir
|
|
output: ArchiveOutput = 'output.pdf'
|
|
cmd = [
|
|
*chrome_args(TIMEOUT=timeout),
|
|
'--print-to-pdf',
|
|
link.url,
|
|
]
|
|
status = 'succeeded'
|
|
timer = TimedProgress(timeout, prefix=' ')
|
|
try:
|
|
result = run(cmd, cwd=out_dir, timeout=timeout)
|
|
|
|
if result.returncode:
|
|
hints = (result.stderr or result.stdout).decode()
|
|
raise ArchiveError('Failed to save PDF', hints)
|
|
|
|
chmod_file('output.pdf', cwd=out_dir)
|
|
except Exception as err:
|
|
status = 'failed'
|
|
output = err
|
|
finally:
|
|
timer.end()
|
|
|
|
|
|
return ArchiveResult(
|
|
cmd=cmd,
|
|
pwd=out_dir,
|
|
cmd_version=CHROME_VERSION,
|
|
output=output,
|
|
status=status,
|
|
**timer.stats,
|
|
)
|