python3 怎么爬取新闻网站?
先开个坑,以后再填吧.......
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 | import requests from bs4 import BeautifulSoup def content(url): text = requests.get(url) text.encoding = 'utf-8' soup2 = BeautifulSoup(text.text, 'html5lib' ) header2 = soup2.select( 'h1' )[ 0 ].text text2 = soup2.select( '#artibody' )[ 0 ].text time2 = soup2.select( '.time-source' )[ 0 ].text print (header2,text2,time2, '\n\n\n' ) res = requests.get( 'http://news.sina.com.cn/china/' ) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, "html5lib" ) for news in soup.select( '.news-item' ): if len (news.select( 'h2' )) > 0 : header = news.select( 'h2' )[ 0 ].text link = news.select( 'a' )[ 0 ][ 'href' ] time = news.select( '.time' )[ 0 ].text print (link,time) content(link) |
为了更好
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】博客园社区专享云产品让利特惠,阿里云新客6.5折上折
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步