文本分析

校园新闻内容提取。

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:
        title=news.select('.news-list-title')[0].text #标题
        url=news.select('a')[0]['href']#网址
        time=news.select('.news-list-info')[0].contents[0].text#时间
        bumen=news.select('.news-list-info')[0].contents[1].text#院系
        txt=news.select('.news-list-description')[0].text #正文
        print(time,title,bumen,txt,url)