Python3:从字符串中移除超文本标记语言，所有的例子都是简单的“仅标签”移除

import re

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

text = "<p>This is a <b>sample</b> text with <i>HTML</i> tags.</p>"
clean_text = remove_html_tags(text)
print(clean_text)  # 输出：This is a sample text with HTML tags.

from bs4 import BeautifulSoup

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

text = "<p>This is a <b>sample</b> text with <i>HTML</i> tags.</p>"
clean_text = remove_html_tags(text)
print(clean_text)  # 输出：This is a sample text with HTML tags.

from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
    def __init__(self):
        super().__init__()
        self.clean_text = []

    def handle_data(self, data):
        self.clean_text.append(data)

    def get_clean_text(self):
        return ''.join(self.clean_text)

def remove_html_tags(text):
    parser = MyHTMLParser()
    parser.feed(text)
    return parser.get_clean_text()

text = "<p>This is a <b>sample</b> text with <i>HTML</i> tags.</p>"
clean_text = remove_html_tags(text)
print(clean_text)  # 输出：This is a sample text with HTML tags.