utils.py 文件源码

def is_html(first_bytes):
    """ Detect whether a file contains HTML by examining its first bytes. """

    BOMS = [
        (b'\xef\xbb\xbf', 'utf-8'),
        (b'\x00\x00\xfe\xff', 'utf-32-be'),
        (b'\xff\xfe\x00\x00', 'utf-32-le'),
        (b'\xff\xfe', 'utf-16-le'),
        (b'\xfe\xff', 'utf-16-be'),
    ]
    for bom, enc in BOMS:
        if first_bytes.startswith(bom):
            s = first_bytes[len(bom):].decode(enc, 'replace')
            break
    else:
        s = first_bytes.decode('utf-8', 'replace')

    return re.match(r'^\s*<', s)