爬取校园新闻首页的新闻

Posted 2020-10-29 guangp

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

2. 分析info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
re=requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
re.encoding=‘utf-8‘


from bs4 import BeautifulSoup
soup = BeautifulSoup(re.text,‘html.parser‘)
#获取所有的新闻标题
# for i in soup.select(‘.news-list-title‘):
#     print(i)
#获取所有的新闻标题的描述
# for j in soup.select(‘.news-list-description‘):
#     print(j)
#获取所有新闻标题的链接
# for k in soup.find_all(‘a‘):
#     print(k[‘href‘])
# print(soup.select(‘.news-list-title‘)[0].text)

for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        t=news.select(‘.news-list-title‘)[0].text
        # d=news.select(‘.news-list-description‘)[0].text
        a=news.select(‘a‘)[0].attrs
        print(t,a[‘href‘])
        re1 = requests.get(a[‘href‘])
        re1.encoding = "utf-8"
        soup1 = BeautifulSoup(re1.text, ‘html.parser‘)
        content = soup1.select(‘#content‘)[0].text
        show = soup1.select(‘.show-info‘)[0].text
        print(show)
        print(content)

 

import requests
re=requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
re.encoding=‘utf-8‘


from bs4 import BeautifulSoup
soup = BeautifulSoup(re.text,‘html.parser‘)
#获取所有的新闻标题
# for i in soup.select(‘.news-list-title‘):
#     print(i)
#获取所有的新闻标题的描述
# for j in soup.select(‘.news-list-description‘):
#     print(j)
#获取所有新闻标题的链接
# for k in soup.find_all(‘a‘):
#     print(k[‘href‘])
# print(soup.select(‘.news-list-title‘)[0].text)

for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        t=news.select(‘.news-list-title‘)[0].text
        # d=news.select(‘.news-list-description‘)[0].text
a=news.select(‘a‘)[0].attrs
        print(t,a[‘href‘])
        re1 = requests.get(a[‘href‘])
        re1.encoding = "utf-8"
soup1 = BeautifulSoup(re1.text, ‘html.parser‘)
        content = soup1.select(‘#content‘)[0].text
        show = soup1.select(‘.show-info‘)[0].text
        print(show)
        print(content)