import html2text
import re
import pandas as pd
with open('../jxufetext.html', 'r', encoding='utf-8') as f:
text = f.read()
text2 = re.compile('<.*?>(.*)<.*?>').findall(text)
#注意到有很多空格，删去并获得列表
#text2 = [i for i in text2 if i!='']
#提取标签内的文字
#word2 = re.compile('(.*?)').findall(text2)
word = []
for i in text2:
if "(.*)<.*?>').findall(i)
for i in wordlist1:
word.append(i)
elif "" in i:
wordlist2 = re.compile('(.*)(.*)').findall(i)
for i in wordlist2:
word.append(i)
elif "" in i:
wordlist3 = re.compile('(.*)').findall(i)
for i in wordlist3:
word.append(i)
elif "