utils.py 文件源码

def pdf_date(path):

    """
    Extract a date from PDF file metadata.

    Args:
        path (str): The file path.

    Returns:
        datetime: The created date.
    """

    reader = PdfFileReader(path)

    # Get rid of `D:` prefix and timezone.
    stamp = reader.documentInfo['/CreationDate']
    match = re.search('\d+', stamp)

    return datetime.strptime(
        match.group(),
        '%Y%m%d%H%M%S'
    )