python 提取网页 charset

def pick_charset(html):
    """
    从文本中提取 meta charset
    :param html:
    :return:
    """
    charset = None
    m = re.compile('<meta .*(http-equiv="?Content-Type"?.*)?charset="?([a-zA-Z0-9_-]+)"?', re.I).search(html)
    if m and m.lastindex == 2:
        charset = m.group(2).lower()
    return charset