# -*- coding:utf8 -*- import requests import lxml.html # 获取html内容中的a链接与内容 chapters_url = "http://www.civil.tsinghua.edu.cn/ce/83.html" html = requests.get(chapters_url).content selector = lxml.html.fromstring(html) res = selector.xpath("///a/text()") res1 = selector.xpath("///a/@href") # print(res) # print(res1) for i,s in enumerate(res): print(res1[i]) print(s)