如何在不删除html标记的情况下将html转换为文本

import re

def html_to_text(html):
    # 使用正则表达式匹配HTML标签并替换为空字符串
    text = re.sub('<[^<]+?>', '', html)
    # 替换HTML实体
    text = re.sub('&nbsp;', ' ', text)
    text = re.sub('&amp;', '&', text)
    # 返回纯文本
    return text

html = '<p>This is <b>bold</b> and <i>italic</i> text.</p>'
text = html_to_text(html)
print(text)
# Output: This is bold and italic text.

from bs4 import BeautifulSoup

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

html = '<p>This is <b>bold</b> and <i>italic</i> text.</p>'
text = html_to_text(html)
print(text)
# Output: This is bold and italic text.

import html2text

def html_to_text(html):
    text = html2text.html2text(html)
    return text

html = '<p>This is <b>bold</b> and <i>italic</i> text.</p>'
text = html_to_text(html)
print(text)
# Output: This is bold and italic text.