正则表达式从HTML链接中提取URL

import re

html = '''<a href="https://www.example.com">Example</a>
           <a href="https://www.google.com">Google</a>
           <a href="https://www.amazon.com">Amazon</a>'''

pattern = r'href="(.*?)"'
urls = re.findall(pattern, html)

print(urls)

['https://www.example.com', 'https://www.google.com', 'https://www.amazon.com']