用requests库和BeautifulSoup4库爬取新闻列表

import requests
from bs4 import BeautifulSoup
from datetime import datetime

wangzhan='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res =requests.get(wangzhan)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')

def getdetail(url):
    resd =requests.get(url)
    resd.encoding='utf-8'
    soupd=BeautifulSoup(resd.text,'html.parser')
    return (soupd.select('.show-content')[0].text)




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
        dt=datetime.strptime(time,'%Y-%m-%d')
        source=news.select('.news-list-info')[0].contents[1].text
        detail=getdetail(url)

        print(dt,title,url,source,detail)
        break

import requests
from bs4 import BeautifulSoup
from datetime import datetime

wangzhan='http://news.baidu.com/'
res =requests.get(wangzhan)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')



for news in soup.select('strong'):
    title=news.select('a')[0].text
    url=news.select('a')[0]['href']
    print(title,url)

   

 

转载于:https://www.cnblogs.com/c-s-y/p/7608210.html