从文本字符串和超链接中提取HyperLink到URL和文本

<a\s+(?:[^>]*?\s+)?href=(["'])(.*?)\1.*?>(.*?)<\/a>

import re

def extract_hyperlinks(text):
    pattern = r'<a\s+(?:[^>]*?\s+)?href=(["\'])(.*?)\1.*?>(.*?)<\/a>'
    matches = re.findall(pattern, text)
    
    hyperlinks = []
    for match in matches:
        url = match[1]
        text = match[2]
        hyperlinks.append((url, text))
    
    return hyperlinks

# 示例文本
text = '<a href="https://www.example.com">Example</a> is a website for <a href="https://www.example.com/about">about</a> information.'

# 提取超链接
hyperlinks = extract_hyperlinks(text)

# 打印结果
for hyperlink in hyperlinks:
    url, text = hyperlink
    print(f"URL: {url}")
    print(f"Text: {text}")
    print()

URL: https://www.example.com
Text: Example

URL: https://www.example.com/about
Text: about