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#日期
        t = news.select('.news-list-title')[0].text#标题
        a = news.select('a')[0].attrs['href']#链接

        resd = requests.get(a)
        resd.encoding='utf-8'
        soupd = BeautifulSoup(resd.text,'html.parser')#新闻详情页

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

        print(dati,t,a,sh,c)
        break