爬取校园新闻首页的新闻

Posted 2020-10-29 090伍明航

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。

import requests
from bs4 import BeautifulSoup
from datetime import datetime

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:
        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)#爬取校园新闻首页新闻的标题、链接
        res2 = requests.get(a)
        res2.encoding = \'utf-8\'
        soup2 = BeautifulSoup(res2.text, \'html.parser\')
        te = soup2.select(\'#content\')[0].text
        print(te)#爬取校园新闻首页新闻的正文

        ifd = soup2.select(\'.show-info\')[0].text
        dt2 = ifd.lstrip(\'发布时间:\')[:19]
        print(dt2)#获取每篇新闻的发布时间

        i = ifd.find(\'作者：\')
        if i>0:
            s = ifd[ifd.find(\'作者：\'):].split()[0].lstrip(\'作者：\')
            print(s)#获取每篇新闻的作者。

        q = ifd.find(\'来源：\')
        if q > 0:
            b = ifd[ifd.find(\'来源：\'):].split()[0].lstrip(\'来源：\')
            print(b)#获取每篇新闻的来源。

        c = ifd.find(\'摄影：\')
        if c > 0:
            n = ifd[ifd.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')
            print(n)#获取每篇新闻的摄影。

        dtn = datetime.strptime(dt2,\'%Y-%m-%d %H:%M:%S\')#将其中的发布时间由str转换成datetime类型。
        print(dtn)
        break

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,\'\\n\',title,\'\\n\',url,\'\\n\',source,\'\\n\')