jodd jerry 解析html

最新推荐文章于 2021-09-12 14:32:23 发布

qq_19396231

最新推荐文章于 2021-09-12 14:32:23 发布

阅读量382

点赞数

分类专栏： java操作office，xml等工具方法

本文链接：https://blog.csdn.net/qq_19396231/article/details/84718961

版权

9 篇文章 0 订阅

订阅专栏

http://jodd.org/doc/jerry/index.html

http://www.oschina.net/code/snippet_12_7758

 
    public class AllMusicNewReleases {

02

 
   03     public static void main(String[] args) throws IOException {

04

 
   05         // download the page super-efficiently

 
   06         File file = new File(SystemUtil.getTempDir(), "allmusic.html");

 
   07         NetUtil.downloadFile("http://allmusic.com", file);

08

 
   09         // create Jerry, i.e. document context

 
   10         Jerry doc = Jerry.jerry(FileUtil.readString(file));

11

 
   12         // parse

 
   13         doc.$("div#new_releases div.list_item").each(new JerryFunction() {

 
   14             public boolean onNode(Jerry $this, int index) {

 
   15                 System.out.println("-----");

 
   16                 System.out.println($this.$("div.album_title").text());

 
   17                 System.out.println($this.$("div.album_artist").text().trim());

 
   18                 return true;

 
   19             }

 
   20         });

 
   21     }

22}

关注