爬取校园新闻首页的新闻

Posted 2020-10-29 phoenlix

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:
        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‘]
        print("date = "+d, "text = "+t, "href = "+a)

　　

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‘]
        # print("date = "+d, "text = "+t, "href = "+a)


        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")
        # print(info)
        print(info[0].text)

　　

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‘]
        # print("date = "+d, "text = "+t, "href = "+a)


        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")
        # print(info)
        # print(info[0].text)
        #
        # info_text = ‘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      点击：次‘
        dt = info[0].text.lstrip(‘发布时间:‘)[:19]
        sh = info[0].text[info[0].text.find(‘审核：‘):].split()[0].lstrip(‘审核：‘)
        print(type(dt), dt)
        from datetime import datetime

        date_format = datetime.strptime(dt, ‘%Y-%m-%d %H:%M:%S‘)
        print(type(date_format), date_format)