如何使用python从html中删除标记

from bs4 import BeautifulSoup

def remove_tags(html):
    soup = BeautifulSoup(html, 'html.parser')
    text = soup.get_text()
    return text

html = '<p>This is a <b>sample</b> HTML.</p>'
text = remove_tags(html)
print(text)

import re

def remove_tags(html):
    cleanr = re.compile('<.*?>')
    text = re.sub(cleanr, '', html)
    return text

html = '<p>This is a <b>sample</b> HTML.</p>'
text = remove_tags(html)
print(text)

from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
    def __init__(self):
        super().__init__()
        self.text = ''

    def handle_data(self, data):
        self.text += data

def remove_tags(html):
    parser = MyHTMLParser()
    parser.feed(html)
    return parser.text

html = '<p>This is a <b>sample</b> HTML.</p>'
text = remove_tags(html)
print(text)