Python爬虫实战：获取网页标题并解析

import requests from lxml import etree

url = 'http://renwen.sanyau.edu.cn/?article/14263.html' res = requests.get(url)

print('服务器状态码：', res.status_code) print('服务器返回编码：', res.encoding)

html = etree.HTML(res.text) newtitle = html.xpath('//h1[@class='article-title']/text()')[0] print('新闻标题：', newtitle)