删除字符串的格式(html标记)，然后重新添加

import re

def remove_html_tags(text):
    clean = re.compile('<.*?>')
    return re.sub(clean, '', text)

# 示例用法
html_string = '<p>This is a <strong>sample</strong> HTML string.</p>'
clean_text = remove_html_tags(html_string)
print(clean_text)

from bs4 import BeautifulSoup

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

# 示例用法
html_string = '<p>This is a <strong>sample</strong> HTML string.</p>'
clean_text = remove_html_tags(html_string)
print(clean_text)