如何从html5标记字符串中提取属性

import re

def extract_attributes(html_string):
    # 定义正则表达式匹配模式
    pattern = r'\s+(\w+)\s*=\s*["\']([^"\']+)["\']'
    
    # 使用正则表达式匹配属性
    matches = re.findall(pattern, html_string)
    
    # 解析属性并存储
    attributes = {}
    for match in matches:
        attribute_name = match[0]
        attribute_value = match[1]
        attributes[attribute_name] = attribute_value
    
    return attributes

# 示例用法
html_string = '<div class="container" id="myDiv" data-toggle="modal">Hello, World!</div>'
attributes = extract_attributes(html_string)
print(attributes)

{'class': 'container', 'id': 'myDiv', 'data-toggle': 'modal'}