Html解析 新工具 HtmlCleanner

    

Java代码

1.       HtmlCleaner cleaner = new HtmlCleaner();     
2.         
3.       TagNode node = cleaner.clean(new URL("http://finance.sina.com.cn/money/nmetal/20091209/10157077895.shtml"));     
4.       //按tag取.     
5.       Object[] ns = node.getElementsByName("title", true);    //标题     
6.         
7.       if(ns.length > 0) {     
8.           System.out.println("title="+((TagNode)ns[0]).getText());     
9.       }     
10.       // /html/body/div[2]/div[4]/div/div/div/div[2]/p  
11.       ns = node.evaluateXPath("//div[@class=\"blkContainerSblkCon\"]/p"); // 选取class为指定blkContainerSblkCon的 div下面的所有p标签  
12.       for (int i = 0; i < ns.length; i++) {  
13.          String in = cleaner.getInnerHtml((TagNode)ns[i]);  
14.            System.out.println("<p>"+in + "</p>");  
15. }  
16.       String in = cleaner.getInnerHtml((TagNode)ns[0]);  
17.       System.out.println(in);  
18.   
19.       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()); 

Java 代码

1.         HtmlCleaner cleaner = new HtmlCleaner();     
2.         String url = "http://finance.sina.com.cn/nmetal/hjfx.html";  
3.         URL _url = new URL(url);  
4.         TagNode node = cleaner.clean(_url);     
5.           
6.         //按tag取.     
7.         Object[] ns = node.getElementsByName("title", true);    //标题     
8.           
9.         if(ns.length > 0) {   
10.             System.out.println("title="+((TagNode)ns[0]).getText());     
11.         }    
12.           
13.           
14.         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  
15.         for (int i = 0; i < ns.length; i++) {  
16.               
17.             //取链接文本  
18. //           String in = cleaner.getInnerHtml((TagNode)ns[i]);  
19. //           System.out.println(in);  
20.               
21.             //获取链接的  
22.             TagNode n = (TagNode) ns[i];  
23. //          System.out.println(n.getAttributeByName("href"));  
24.             System.out.println(new URL(_url,n.getAttributeByName("href")).toString());  
25.         }  
26. //        String in = cleaner.getInnerHtml((TagNode)ns[0]);  
27. //        System.out.println(in);  
28.   
29. //        System.out.println(((TagNode)ns[0]).getText());  
30.           
31. //        System.out.println("ul/li:");     
32. //        //按xpath取     
33. //        ns = node.evaluateXPath("//div[@class='d_1']//li");     
34. //        for(Object on : ns) {     
35. //            TagNode n = (TagNode) on;     
36. //            System.out.println("\ttext="+n.getText());     
37. //        }     
38. //        System.out.println("a:");     
39. //        //按属性值取     
40. //        ns = node.getElementsByAttValue("name", "my_href", true, true);     
41. //        for(Object on : ns) {     
42. //            TagNode n = (TagNode) on;     
43. //            System.out.println("\thref="+n.getAttributeByName("href")+", text="+n.getText());     
44. //        }