Function save_headers

archivebox/extractors/headers.py:34–70

Download site headers

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

@enforce_types
def save_headers(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
    """Download site headers"""

    out_dir = Path(out_dir or link.link_dir)
    output_folder = out_dir.absolute()
    output: ArchiveOutput = 'headers.json'

    status = 'succeeded'
    timer = TimedProgress(timeout, prefix='      ')

    cmd = [
        CURL_BINARY,
        *CURL_ARGS,
        '--head',
        '--max-time', str(timeout),
        *(['--user-agent', '{}'.format(CURL_USER_AGENT)] if CURL_USER_AGENT else []),
        *([] if CHECK_SSL_VALIDITY else ['--insecure']),
        link.url,
    ]
    try:
        json_headers = get_headers(link.url, timeout=timeout)
        output_folder.mkdir(exist_ok=True)
        atomic_write(str(output_folder / "headers.json"), json_headers)
    except (Exception, OSError) as err:
        status = 'failed'
        output = err
    finally:
        timer.end()

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