#coding=utf-8 #python 2.x import re import urllib def getHtml(url): page=urllib.urlopen(url) html=page.read() return html html=getHtml("http://www.jianshu.com") reg=r'<h4 class="title"><a target="_blank" href="(.*?)">(.*?)</a>' hotre=re.compile(reg) artlist=re.findall(hotre,html) for article in artlist: for com in article: print com