用requests库和BeautifulSoup4库爬取新闻列表

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

url_main="http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url_main)
res.encoding = 'utf-8'

soup = BeautifulSoup(res.text,'html.parser')
li = soup.select('li')
for li_title in li:
    if len(li_title.select('.news-list-title'))>0:
        herf = li_title.select('a')[0]['href']
        title = li_title.select('.news-list-title')[0].text
        time = li_title.select('span')[0].text
        info = li_title.select('span')[1].text
        li_res = requests.get(herf)
        li_res.encoding = 'utf-8'
        li_soup = BeautifulSoup(li_res.text,'html.parser')
        li_text = li_soup.select('.show-content')[0].text
        print(time,title,herf,info,'\n',li_text)

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
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)