Python에서 HTML 태그를 제거하는 방법

import re
from bs4 import BeautifulSoup
from lxml import etree
 
html = &#39;<p>你好</p><br/><font>哈哈</font><b>大家好</b>&#39;
 
# 方法一
pattern = re.compile(r&#39;<[^>]+>&#39;,re.S)
result = pattern.sub(&#39;&#39;, html)
print(result)
 <br># 方法二
soup = BeautifulSoup(html,&#39;html.parser&#39;)
print(soup.get_text())
 
# 方法三
response = etree.HTML(text=html)
# print(dir(response))
print(response.xpath(&#39;string(.)&#39;))
 
 
# 你好哈哈大家好
# 你好哈哈大家好
# 你好哈哈大家好