import emoji #去掉表情等特殊字符 jieshao="包括表情的字符串" jieshao=emoji.demojize(jieshao)
def filter_emoji(self,desstr,restr='[emoji]'): ''' 过滤表情 ''' try: co = re.compile(u'[\U00010000-\U0010ffff]') except re.error: co = re.compile(u'[\uD800-\uDBFF][\uDC00-\uDFFF]') return co.sub(restr, desstr)
jieshao=self.filter_emoji(jieshao)
s = '\xe9\x9d\x92\xe8\x9b\x99\xe7\x8e\x8b\xe5\xad\x90' ss = s.encode('raw_unicode_escape') print(ss) # 结果:b'\xe9\x9d\x92\xe8\x9b\x99\xe7\x8e\x8b\xe5\xad\x90' sss = ss.decode() print(sss) 如果是中文混合这种乱码,则用循环删除掉 mys='宝石 \x9e\x9d\x99' sl = list(mys) i=0 while i<len(sl): s=sl[i] try: s=s.encode('raw_unicode_escape').decode('utf-8') i+=1 except: #删掉它 sl.remove(s) mys=''.join(mys) print(mys)