正则表达式使用Python从HTML的href属性中提取URL

import re

url = '<p>Hello World</p><a href="http://example.com">More Examples</a><a href="http://example2.com">Even More Examples</a>'urls = re.findall('https?://(?:[-w.]|(?:%[da-fA-F]{2}))+', url)>>> print urls['http://example.com', 'http://example2.com']