Function save_pdf

archivebox/extractors/pdf.py:35–70

print PDF of site to file using chrome --headless

(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT)

@enforce_types
def save_pdf(link: Link, 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)
    output: ArchiveOutput = 'output.pdf'
    cmd = [
        *chrome_args(),
        '--print-to-pdf',
        link.url,
    ]
    status = 'succeeded'
    timer = TimedProgress(timeout, prefix='      ')
    try:
        result = run(cmd, cwd=str(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=str(out_dir))
    except Exception as err:
        status = 'failed'
        output = err
        chrome_cleanup()
    finally:
        timer.end()


    return ArchiveResult(
        cmd=cmd,
        pwd=str(out_dir),
        cmd_version=CHROME_VERSION,
        output=output,
        status=status,
        **timer.stats,
    )