从Web抓取中删除HTML

import re

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

html_content = '<p>This is a <strong>sample</strong> HTML text.</p>'
clean_text = remove_html_tags(html_content)
print(clean_text)

This is a sample HTML text.

def remove_html_tags(text):
    while '<' in text and '>' in text:
        start = text.index('<')
        end = text.index('>')
        text = text[:start] + text[end+1:]
    return text

html_content = '<p>This is a <strong>sample</strong> HTML text.</p>'
clean_text = remove_html_tags(html_content)
print(clean_text)

This is a sample HTML text.

from bs4 import BeautifulSoup

html_content = '<p>This is a <strong>sample</strong> HTML text.</p>'
soup = BeautifulSoup(html_content, 'html.parser')
clean_text = soup.get_text()
print(clean_text)

This is a sample HTML text.