用requests库和BeautifulSoup4库爬取新闻列表

import requests
from bs4 import BeautifulSoup
net = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(net)
res.encoding=‘utf-8‘
doc = BeautifulSoup(res.text,‘html.parser‘,from_encoding=‘utf-8‘)
for news in doc.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        title = news.select(‘.news-list-title‘)[0].text
        url = news.select(‘a‘)[0][‘href‘]
        time = news.select(‘.news-list-info‘)[0].contents[0].text
        main = news.select(‘.news-list-description‘)[0].text
        source = news.select(‘.news-list-info‘)[0].contents[1].text
        print(‘Url：{}‘.format(news.select(‘a‘)[0][‘href‘]))
        print(‘标题：{}‘.format(news.select(‘.news-list-title‘)[0].text))
        print(‘正文：{}‘.format(news.select(‘.news-list-description‘)[0].text))
        print(‘时间：{}‘.format(news.select(‘.news-list-info‘)[0].contents[0].text))
        print(‘来源：{}‘.format(news.select(‘.news-list-info‘)[0].contents[1].text))