#coding=utf-8

import re

import codecs

def strs_filter(file):

    with codecs.open(file,"r","utf8") as f,codecs.open("result.txt","a+","utf8") as c:

        lines=f.readlines()

        for line in lines:

            # line=line.decode('utf8')

            re_html=re.compile('<[^>]+>'.decode('utf8'))#从'<'开始匹配，不是'>'的字符都跳过，直到'>'

            re_punc=re.compile('[\s+\.\!\/_,$%^*(+\"\']+|[+——！，。？、~@#￥%……&*“”《》：（）]+'.decode('utf8'))#去除标点符号

            re_digits_letter=re.compile('\w+'.decode('utf8'))#去除数字及字母

            line=re_html.sub('',line)

            line=re_punc.sub("",line)

            line=re_digits_letter.sub("",line)

            c.write(line)

strs_filter("strip.txt")