用DOM解析XML

示例1：

package com.shengsiyuan.xml.dom;

import java.io.File;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;

public class DomTest1
{
	public static void main(String[] args) throws Exception
	{
		// step 1: 获得dom解析器工厂（工作的作用是用于创建具体的解析器）
		DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
		
//		System.out.println("class name: " + dbf.getClass().getName());
		
		// step 2:获得具体的dom解析器
		DocumentBuilder db = dbf.newDocumentBuilder();
		
//		System.out.println("class name: " + db.getClass().getName());
		
		// step3: 解析一个xml文档，获得Document对象（根结点）
		Document document = db.parse(new File("candidate.xml"));
		
		NodeList list = document.getElementsByTagName("PERSON");
		
		for(int i = 0; i < list.getLength(); i++)
		{
			Element element = (Element)list.item(i);
			
			String content = element.getElementsByTagName("NAME").item(0).getFirstChild().getNodeValue();
			
			System.out.println("name:" + content);
			
			content = element.getElementsByTagName("ADDRESS").item(0).getFirstChild().getNodeValue();
			
			System.out.println("address:" + content);
			
			content = element.getElementsByTagName("TEL").item(0).getFirstChild().getNodeValue();
			
			System.out.println("tel:" + content);
			
			content = element.getElementsByTagName("FAX").item(0).getFirstChild().getNodeValue();
			
			System.out.println("fax:" + content);
			
			content = element.getElementsByTagName("EMAIL").item(0).getFirstChild().getNodeValue();
			
			System.out.println("email:" + content);
			
			System.out.println("--------------------------------------");
		}
	}
}

示例2：

package com.shengsiyuan.xml.dom;

import java.io.File;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

public class DomTest2
{
	public static void main(String[] args) throws Exception
	{
		DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
		
		DocumentBuilder db = dbf.newDocumentBuilder();
		
		Document doc = db.parse(new File("student.xml"));
		
//		System.out.println(doc.getXmlEncoding());
//		System.out.println(doc.getXmlVersion());
//		System.out.println(doc.getXmlStandalone());
		
		//获得文档的根元素节点
		Element root = doc.getDocumentElement();
		
		System.out.println(root.getTagName());
		
		NodeList list = root.getChildNodes();
		
		System.out.println(list.getLength());
		
		for(int i = 0; i < list.getLength(); i++)
		{
			System.out.println(list.item(i).getNodeName());
		}
		
		System.out.println("----------------------------------");
		
		for(int i = 0; i < list.getLength(); i++)
		{
			Node n = list.item(i);
			
			System.out.println(n.getNodeType() + " : " + n.getNodeValue());
		}
		
		System.out.println("----------------------------------");
		
		for(int i = 0; i < list.getLength(); i++)
		{
			Node n = list.item(i);
			
			System.out.println(n.getTextContent());
		}
		
		System.out.println("----------------------------------");
		
		NodeList nodeList = doc.getElementsByTagName("学生");
		
		for(int i = 0; i < nodeList.getLength(); i++)
		{
			NamedNodeMap nnm = nodeList.item(i).getAttributes();
			
			String attrName = nnm.item(0).getNodeName();
			System.out.print(attrName);
			
			System.out.print("=");
			
			String attrValue = nnm.item(0).getNodeValue();
			
			System.out.println(attrValue);
		}
	}
}

示例3：

package com.shengsiyuan.xml.dom;

import java.io.File;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Attr;
import org.w3c.dom.Comment;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

/**
 * 使用递归解析给定的任意一个xml文档并且将其内容输出到命令行上
 * @author zhanglong
 *
 */
public class DomTest3
{
	public static void main(String[] args) throws Exception
	{
		DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
		DocumentBuilder db = dbf.newDocumentBuilder();
		
		Document doc = db.parse(new File("student.xml"));
		//获得根元素结点
		Element root = doc.getDocumentElement();
		
		parseElement(root);
	}
	
	private static void parseElement(Element element)
	{
		String tagName = element.getNodeName();
		
		NodeList children = element.getChildNodes();
		
		System.out.print("<" + tagName);
		
		//element元素的所有属性所构成的NamedNodeMap对象，需要对其进行判断
		NamedNodeMap map = element.getAttributes();
		
		//如果该元素存在属性
		if(null != map)
		{
			for(int i = 0; i < map.getLength(); i++)
			{
				//获得该元素的每一个属性
				Attr attr = (Attr)map.item(i);
				
				String attrName = attr.getName();
				String attrValue = attr.getValue();
				
				System.out.print(" " + attrName + "=\"" + attrValue + "\"");
			}
		}
		
		System.out.print(">");
		
		for(int i = 0; i < children.getLength(); i++)
		{
			Node node = children.item(i);
			//获得结点的类型
			short nodeType = node.getNodeType();
			
			if(nodeType == Node.ELEMENT_NODE)
			{
				//是元素，继续递归
				parseElement((Element)node);
			}
			else if(nodeType == Node.TEXT_NODE)
			{
				//递归出口
				System.out.print(node.getNodeValue());
			}
			else if(nodeType == Node.COMMENT_NODE)
			{
				System.out.print("<!--");
				
				Comment comment = (Comment)node;
				
				//注释内容
				String data = comment.getData();
				
				System.out.print(data);
				
				System.out.print("-->");
			}
		}
		
		System.out.print("</" + tagName + ">");
	}
}