朗文字典数据清洗

import re
from bs4 import BeautifulSoup
import time
file1 = open(r'C:\朗文双解_g_1.csv', 'a',encoding='utf-8')
with open(r'C:\朗文双解ffffff.txt',encoding='utf-8') as file:
    conten = file.readlines()
    for lin in conten:
        word=re.findall(r'^.*\t', lin)[0]
        str_first1 = re.sub('<span class="cn_txt"> ', '<span class="cn_txt"> |', str(lin))

        soup = BeautifulSoup(str(str_first1), 'html.parser')
        # soup = BeautifulSoup(str(str_first1),'lxml')
        # print(soup)
        # yb=soup.findAll(name="span", attrs={"class": ("PRON")})
        en_1_g = soup.findAll(name="span", attrs={"class": ("english LDOCE_switch_lang switch_children")})
        for i in en_1_g:
            print(word,i.get_text())
            gg = str(word)+'\t'+i.get_text()+'\n'
            print(gg)
            file1.write(gg)

        en_2_g=soup.findAll(name="span", attrs={"class": ("SIGNPOST LDOCE_switch_lang LDOCE5pp_sensefold_other")})

        for ii in en_2_g:
            print(word,i.get_text())
            gg = str(word)+'\t'+ii.get_text()+'\n'
            print(gg)
            file1.write(gg)

        # en_3_g=soup.findAll(name="span", attrs={"class": ("DEF LDOCE_switch_lang switch_siblings")})
        # ff=[]
        #
        # for i2 in en_3_g:
        #     ff.append(i2.get_text())
        # print(word,ff)
        # gg = str(word) + '\t' + str(ff) + '\n'
        # file1.write(gg)

            # print(word,i.get_text())
            # gg = str(word)+'\t'+i2.get_text()+'\n'
            # print(gg)
            # file1.write(gg)