爬取校园新闻首页的新闻

import requests
from bs4 import BeautifulSoup
from datetime import datetime

res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')
for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        #d = news.select('.news-list-info')[0].contents[0].text
        t = news.select('.news-list-title')[0].text #标题
        m = news.select('.news-list-description')[0].text #内容
        a = news.select('a')[0].attrs['href']#链接

        print(t,a,m)

        resd = requests.get(a)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')

        c = soupd.select('#content')[0].text
        print(c) #正文
        info = soupd.select('.show-info')[0].text
        print(info)
        dt = info.lstrip('发布时间:')[:19]
        dati = datetime.strptime(dt,'%Y-%m-%d %H:%M:%S')
        sh = info[info.find('来源：'):].split()[0].lstrip('来源：')
        wr = info[info.find('作者：'):info.find('审核：')].lstrip('作者：').split()[0]
        ph = info[info.find('摄影：'):].split()[0].lstrip('摄影：')
        print(dati,wr,sh,ph)
        break