dom4j 的小小测试

 
@Test  
    public void gogo() throws IOException{  
        InputStream in = this.getClass().getClassLoader()  
                .getResourceAsStream("content.html");  
        byte[] content = new byte[in.available()];  
        in.read(content);  
          
        Document document;  
        org.dom4j.Document document2;  
        InputStream inputStream = null;  
        try {  
            inputStream = new ByteArrayInputStream(content);  
            Tidy tidy = new Tidy();  
            init(tidy);  
            document = tidy.parseDOM(inputStream, null);  
            DOMReader domReader = new DOMReader();  
            document2 = domReader.read(document);  
            XPath path = DocumentHelper.createXPath("/html/body/table[3]/tbody/tr/td/table/tbody/tr/td/table/tbody/tr[2]/td/div[4]");  //xpath 路径   
            Node node  = path.selectSingleNode(document2);  
            System.out.println(node.getUniquePath());  //xpath   
            System.out.println(node.getNodeTypeName()); // Element   
            System.out.println(node.getName()); //div   
            System.out.println(node.asXML()); // 原始文本   
            System.out.println("kjl"+node.getText()); //null    
            System.out.println(node.getStringValue()); //除去 标签   
            System.out.println(node.getPath()); // 不知道和 uniquepath 什么关系   
            System.out.println(node.getParent().asXML()); // 获取 dom 父节点   
        } finally {  
            Closeables.close(inputStream, false); // guava api 这个测试时完全可以不要，只是我在测试时刚好加了这个dependency   
        }  
    }