requests, Beautifusoup 爬取新浪新闻资讯

import requests
from bs4 import BeautifulSoup

res = requests.get(‘http://news.sina.com.cn/china‘)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text, ‘html.parser‘)

for news in soup.select(‘.news-item‘):
    if len(news.select(‘h2‘)) > 0:
        h2 = news.select(‘h2‘)[0].text
        time = news.select(‘.time‘)[0].text
        a = news.select(‘a‘)[0][‘href‘]
        print(time, h2, a)

requests, Beautifusoup 爬取新浪新闻资讯

原文：http://www.cnblogs.com/minorblog/p/7629125.html