爬取校园新闻首页的新闻

import requests
from bs4 import BeautifulSoup
from datetime import datetime

url = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, "html.parser")

# for news in soup.select('li'):
#     if len(news.select('.news-list-title'))>0:
#         t = news.select('.news-list-title')[0].text
#         dt = news.select('.news-list-info')[0].contents[0].text
#         a = news.select('a')[0].attrs['href']
#         print(t,dt,a)
#         break


for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        t = news.select('.news-list-title')[0].text   #标题
        a = news.select('a')[0].attrs['href']        #链接
        # print(a)
        resd = requests.get(a)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text,'html.parser')
        # print(soupd.select('.show-info')[0].text)   #正文

        info = soupd.select('.show-info')[0].text
        dt = info.lstrip('发布时间')[1:20]  # 发布时间
        dt = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S')
        print(dt)

        i = info.find('来源：')
        z = info.find('作者：')
        sy = info.find('摄影：')
        if i > 0:
            s = info[info.find('来源：'):].split()[0].lstrip('来源：')
            z = info[info.find('作者：'):].split()[0].lstrip('作者：')
            sy = info[info.find('摄影：'):].split()[0].lstrip('摄影：')
            print(s, z, sy)