1. 用requests库和BeautifulSoup库,爬取校园新闻首页新闻的标题、链接、正文。
2. 分析字符串,获取每篇新闻的发布时间,作者,来源,摄影等信息。
3. 将其中的发布时间由str转换成datetime类型。
4. 将完整的代码及运行结果截图发布在作业上。
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
t = 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')
c = soupd.select('#content')[0].text
info = soupd.select('.show-info')[0].text
dt = info.lstrip('发布时间:')[:19]
dati = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S')
sh = info[info.find('审核:'):].split()[0].lstrip('审核:')
zz = info[info.find('作者:'):].split()[0].lstrip('作者:')
print(d, t, c, a)
print(info)
print(dati, sh, zz)
break