用requests库和BeautifulSoup4库爬取新闻列表

Posted 2020-10-08 哥哥让你爽

import requests
from bs4 import BeautifulSoup
jq=‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0926/8262.html‘
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)