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 new in soup.select('li'):
    if len(new.select('.news-list-info'))>0:
        s0 = new.select('.news-list-title')[0].text# 标题内容
        s1 = new.select('a')[0].attrs['href']  # 链接
        resd=requests.get(s1)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')
        s2 = soupd.select('#content')[0].text  #正文
        print(s1+'\n'+s0,s2)

 运行结果:

 

 

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 new in soup.select('li'):
    if len(new.select('.news-list-info'))>0:
        s1 = new.select('a')[0].attrs['href']  # 链接
        resd=requests.get(s1)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')
        info=soupd.select('.show-info')[0].text
        dt=info.lstrip('发布时间:')[:19]#发布时间
        sh=info[info.find('作者:'):].split()[0].lstrip('作者:') #作者
        sh1 = info[info.find('审核:'):].split()[0].lstrip('审核:')  # 审核
        sh2 = info[info.find('来源:'):].split()[0].lstrip('来源:')  # 来源
        print('发布时间:'+dt+'\t作者:'+sh+'\t审核:'+sh1+'\t来源:'+sh2)

  运行结果:

 

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
url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res=requests.get(url)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
for new in soup.select('li'):
    if len(new.select('.news-list-info'))>0:
        s1 = new.select('a')[0].attrs['href']  # 链接
        resd=requests.get(s1)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')
        info=soupd.select('.show-info')[0].text
        dt=info.lstrip('发布时间:')[:19]#发布时间
        dati=datetime.strptime(dt,'%Y-%m-%d %H:%M:%S')
        print(dati)

 运行结果:

 

posted on 2018-04-03 22:34  204罗德广  阅读(104)  评论(0编辑  收藏  举报