1、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
res=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
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
url=news.select('a')[0]['href']
time=news.select('.news-list-info')[0].contents[0].text
laiyuan=news.select('.news-list-info')[0].contents[1].text
print(title,url,time,laiyuan)
2、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
res=requests.get('http://trips.tuniu.com/search?q=%E9%9F%B6%E5%85%B3')
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
for trips in soup.select('li'):
if len(trips.select('.list-name'))>0:
title=trips.select('.list-name')[0].text
url=trips.select('a')[0]['href']
print(title,url)