爬取校园新闻首页的新闻

import requests
from bs4 import BeautifulSoup

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(dt,t,a)

for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        title = news.select('.news-list-title')[0].text
        a = news.select('a')[0].attrs['href']

        resd = requests.get(a)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')
        d = soupd.select('#content')[0].text
        info = soupd.select('.show.info')[0].text
        print(info)
        dt = info.lstrip('发布时间:')[:19]#发布时间
        dt2 = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S')
        print(dt2)
        i = info.find('来源:')
        if i>0:
            s = info[info.find('来源:'):].split()[0].lstrip('来源:')#来源
            print(s)
        a = info.find('作者：')
        if a > 0:
            l = info[info.find('作者：'):].split()[0].replace('作者：')#作者
            print(l)
        y = info.find('摄影：')
        if y > 0:
            u = info[info.find('摄影：'):].split()[0].replace('摄影：')#摄影
            print(u)

from datetime import datetime
        str = '2018-03-30 17:10:12 '
        dt=datetime.strptime('str,%Y-%a-%d %H:%M:%S')
        now = datetime.now()
        type(now)
        now.strptime('%Y-%a-%d %H:%M:%S')