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‘)
print(soup.select(‘.news-list‘)[0].select(‘li‘))
for new in soup.select(‘.news-list‘)[0].select(‘li‘):
    # 标题
    ti = new.select(‘.news-list-title‘)[0].text
    # 时间
    tim = new.select(‘span‘)[0].text
    # 来源
    source = new.select(‘span‘)[1].text
    print(‘标题：‘+ ti + ‘ 时间：‘+ tim + ‘ 来源：‘+ source)
    # 链接
    a = new.select(‘a‘)[0].attrs[‘href‘]
    resd = requests.get(a)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)
    # 正文
    print(‘正文:‘)
    content = soupd.select(‘#content‘)[0].text.split()
    for c in content:
        print(c)
 
info = ‘发布时间:2018-04-01 11:57:00      作者：陈流芳  审核：权麟春  来源：马克思主义学院‘
dt = info.lstrip(‘发布时间:‘)[:15]
print(dt)
print(info.find(‘作者‘))#找到‘时间’位置
print(info[info.find(‘审核‘):].split()[0].lstrip(‘审核：‘))
print(info[info.find(‘作者：‘):info.find(‘审核：‘)])
 
from datetime import datetime
now = datetime.now()
print(now)
print(tim)
da = datetime.strptime(tim, ‘%Y-%m-%d‘)
print(da)
n = now.strftime(‘%y/%m/%d‘)
print(n)