getEncoding.py 文件源码

 复制代码def decode_html(html_string):
    """??BS4?UnicodeDammit???????, ???unicode??, ???????100%, ????????
    """
    dammit = UnicodeDammit(html_string, ['GB2312', 'GBK', 'GB18030'], smart_quotes_to="html", is_html=True)
    doc = dammit.unicode_markup
    #print("dammit —— ", dammit.original_encoding)
    # FIXME ???????'ISO-8859-2', ??????, ????????????
    if dammit.original_encoding == 'ISO-8859-2':
        enc = get_encoding(html_string)
        print(enc)
        enc ="utf-8"
        doc = html_string.decode(enc)
    elif not dammit.unicode_markup:
        raise UnicodeDecodeError("Failed to detect encoding, tried [%s]", ', '.join(dammit.triedEncodings))
    # print(doc.encode('utf-8'))
    return doc