Html解析 新工具 HtmlCleanner

    

      HtmlCleaner cleaner = new HtmlCleaner();

      TagNode node = cleaner.clean(new URL("http://finance.sina.com.cn/money/nmetal/20091209/10157077895.shtml"));
      //按tag取.
      Object[] ns = node.getElementsByName("title", true);    //标题

      if(ns.length > 0) {
          System.out.println("title="+((TagNode)ns[0]).getText());
      }
      // /html/body/div[2]/div[4]/div/div/div/div[2]/p
      ns = node.evaluateXPath("//div[@class=\"blkContainerSblkCon\"]/p"); // 选取class为指定blkContainerSblkCon的 div下面的所有p标签
      for (int i = 0; i < ns.length; i++) {
         String in = cleaner.getInnerHtml((TagNode)ns[i]);
           System.out.println("<p>"+in + "</p>");
}
      String in = cleaner.getInnerHtml((TagNode)ns[0]);
      System.out.println(in);

      System.out.println(((TagNode)ns[0]).getText());

        HtmlCleaner cleaner = new HtmlCleaner();   
        
        TagNode node = cleaner.clean(new URL("http://finance.sina.com.cn/money/nmetal/20091209/10157077895.shtml"));   
        //按tag取.   
        Object[] ns = node.getElementsByName("title", true);    //标题   
        
        if(ns.length > 0) {   
            System.out.println("title="+((TagNode)ns[0]).getText());   
        }   
        // /html/body/div[2]/div[4]/div/div/div/div[2]/p
        ns = node.evaluateXPath("//div[@class=\"blkContainerSblkCon\"]/p"); //选取class为指定blkContainerSblkCon的div下面的所有p标签
        for (int i = 0; i < ns.length; i++) {
        	 String in = cleaner.getInnerHtml((TagNode)ns[i]);
             System.out.println("<p>"+in + "</p>");
		}
        String in = cleaner.getInnerHtml((TagNode)ns[0]);
        System.out.println(in);

        System.out.println(((TagNode)ns[0]).getText()); 

        HtmlCleaner cleaner = new HtmlCleaner();
        String url = "http://finance.sina.com.cn/nmetal/hjfx.html";
        URL _url = new URL(url);
        TagNode node = cleaner.clean(_url);

        //按tag取.
        Object[] ns = node.getElementsByName("title", true);    //标题

        if(ns.length > 0) {
            System.out.println("title="+((TagNode)ns[0]).getText());
        }


        ns = node.evaluateXPath("//*[@class='Frame-Row3-01-C']/table[2]/tbody/tr/td/a"); // 选取class为指定blkContainerSblkCon的 div下面的所有p
        for (int i = 0; i < ns.length; i++) {

            //取链接文本
//           String in = cleaner.getInnerHtml((TagNode)ns[i]);
//           System.out.println(in);

            //获取链接的
            TagNode n = (TagNode) ns[i];
//          System.out.println(n.getAttributeByName("href"));
            System.out.println(new URL(_url,n.getAttributeByName("href")).toString());
        }
//        String in = cleaner.getInnerHtml((TagNode)ns[0]);
//        System.out.println(in);

//        System.out.println(((TagNode)ns[0]).getText());

//        System.out.println("ul/li:");
//        //按xpath取
//        ns = node.evaluateXPath("//div[@class='d_1']//li");
//        for(Object on : ns) {
//            TagNode n = (TagNode) on;
//            System.out.println("\ttext="+n.getText());
//        }
//        System.out.println("a:");
//        //按属性值取
//        ns = node.getElementsByAttValue("name", "my_href", true, true);
//        for(Object on : ns) {
//            TagNode n = (TagNode) on;
//            System.out.println("\thref="+n.getAttributeByName("href")+", text="+n.getText());
//        }