python 处理html文本的中文字符gbk转utf-8

Posted 2020-09-23

#中文字符gbk转utf-8
    def gbk2utf8(self,raw):
        rs=raw.encode(‘raw_unicode_escape‘) #转为机器识别字符串
        s=repr(rs)
        ss=unicode(eval(s),"gbk")     #gbk解码为unicode
        utf8_str=ss.encode(‘utf-8‘)    #unicode编码为utf-8
        return utf8_str