ArchiveBox/archivebox/extractors/pdf.py

70 lines
1.6 KiB
Python
Raw Normal View History

2019-04-27 21:26:24 +00:00
__package__ = 'archivebox.extractors'
import os
from typing import Optional
2019-05-01 03:13:04 +00:00
from ..index.schema import Link, ArchiveResult, ArchiveOutput, ArchiveError
2020-06-26 02:14:40 +00:00
from ..system import run, chmod_file
2019-04-27 21:26:24 +00:00
from ..util import (
enforce_types,
is_static_file,
chrome_args,
)
from ..config import (
TIMEOUT,
SAVE_PDF,
CHROME_VERSION,
)
from ..logging_util import TimedProgress
2019-04-27 21:26:24 +00:00
@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:
2020-06-26 02:14:40 +00:00
result = run(cmd, cwd=out_dir, timeout=timeout)
2019-04-27 21:26:24 +00:00
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()
2019-04-27 21:26:24 +00:00
return ArchiveResult(
cmd=cmd,
pwd=out_dir,
cmd_version=CHROME_VERSION,
output=output,
status=status,
**timer.stats,
)