爬取校园新闻首页的新闻

import requests
newsurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(newsurl)  # 返回response对象
res.encoding = ‘utf-8‘
from bs4 import BeautifulSoup
soup = BeautifulSoup(res.text, ‘html.parser‘)

for news in soup.select("li"):

    if(len(news.select(‘.news-list-info‘))>0):
        print(news.select(‘a‘)[0].attrs[‘href‘])
        print(news.select(‘.news-list-title‘)[0].text)
        a = news.select(‘a‘)[0].attrs[‘href‘]
        rq = requests.get(a)
        rq.encoding="utf-8"
        soup2 =  BeautifulSoup(rq.text, ‘html.parser‘)
        print(soup2.select("#content")[0].text)

show = soup2.select(".show-info")[0].text.split()
dt = show[0].lstrip(‘发布时间:‘) + " " + show[1]
writer = show[2].lstrip(‘作者：‘)
sh = show[3].lstrip(‘审核：‘)
ly = show[4].lstrip(‘来源：‘)

print(dt,"\t", writer,"\t", sh, "\t",ly)

        from datetime import datetime
        da = datetime.strptime(dt,"%Y-%m-%d %H:%M:%S")
        print(type(da))
        print(da,writer,sh,ly)
        break;