爬取校园新闻

str = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')

str.encoding = 'utf-8'

 

from bs4 import BeautifulSoup

soup=BeautifulSoup(str.text,'html.parser')

#print(soup)

 

d=soup.select('li')

for news in d:

    if len(news.select('.news-list-title')) > 0:

        t=print(news.select('.news-list-title')[0].text)

        a=news.select('a')[0].attrs

        print(a['href'])

 

        strd = requests.get(a['href'])

        strd.encoding = 'utf-8'

        soupd = BeautifulSoup(strd.text, 'html.parser')

        cont=soupd.select('#content')

        timet=soupd.select('.show-info')

        print(timet[0].text[0:25])

        print(timet[0].text[30:38])

        print(timet[0].text[38:45])

        print(timet[0].text[46:56])

        print(timet[0].text[62:])