用requests库和BeautifulSoup4库，爬取校园新闻列表的时间、标题、链接、来源。

 

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:

title=news.select('.news-list-title')[0].text #标题

time=news.select('.news-list-info')[0].contents[0].text#时间

url1=news.select('a')[0]['href']#url

bumen=news.select('.news-list-info')[0].contents[1].text#部门

description=news.select('.news-list-description')[0].text #描述

print(time,title,bumen,url)

• 选一个自己感兴趣的主题，做类似的操作，为“爬取网络数据并进行文本分析”做准备。

 

import requests

from bs4 import BeautifulSoup

jq='http://news.qq.com/l/milite/milgn/list2010122872223.htm'

res = requests.get(jq)

res.encoding='gb2312'

soup = BeautifulSoup(res.text,'html.parser')

for news in soup.select('li'):

if len(news.select('a'))>0:

title=news.select('a')[0].text

url=news.select('a')[0]['href']

#time=news.select('span')[0].contents[0].text

#print(time,title,url)

print(title,url)