爬取校园新闻首页的新闻

1. 用requests库和BeautifulSoup库，爬取校园新闻首页新闻的标题、链接、正文。

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:
        print(news.select('.news-list-title'))
        t=news.select('.news-list-title')[0].text
        dt=news.select('.news-list-info')[0].contents[0].text
        a=news.select('a')[0].attrs['href']
        print(dt,t,a)

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。

for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        title = 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')
        d = soupd.select('#content')[0].text
        info = soupd.select('.show.info')[0].text
        print(info)
        dt = info.lstrip('发布时间:')[:19]#发布时间
        dt2 = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S')
        print(dt2)
        i = info.find('来源:')
        if i>0:
            s = info[info.find('来源:'):].split()[0].lstrip('来源:')#来源
            print(s)
        a = info.find('作者：')
        if a > 0:
            l = info[info.find('作者：'):].split()[0].replace('作者：')#作者
            print(l)
        y = info.find('摄影：')
        if y > 0:
            u = info[info.find('摄影：'):].split()[0].replace('摄影：')#摄影
            print(u)

3. 将其中的发布时间由str转换成datetime类型。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

gzccurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(gzccurl)
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']#链接
        time = news.select('.news-list-info')[0].contents[0].text
        dt = datetime.strptime(time,'%Y-%m-%d')
        source = news.select('.news-list-info')[0].contents[1].text#来源
        print(dt,'
',title,'
',url,'
',source,'
')