java解析xml文件

xml文件内容：

<?xml version="1.0" encoding="UTF-8"?>
<bookstore>
    <book id="1" lazy="false">
        <name>冰与火之歌</name>
        <author>乔治马丁</author>
        <year>2014</year>
        <price>89</price>
    </book>
    <book id="2" lazy="true">
        <name>安徒生童话</name>
        <year>2004</year>
        <price>77</price>
        <language>English</language>
    </book>    
</bookstore>

1.使用dom4j解析xml：

/**
 * @author zy
 *dom4j解析xml文档是性能最好的解析方式
 */
package com.channelsoft.dom4j;


import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

public class DOM4jTest {
	@SuppressWarnings("unchecked")
	public static void main(String[] args) throws Exception {
		//创建SAXReader对象
		SAXReader reader = new SAXReader();
		Document document= reader.read("dom.xml");
		Element root = document.getRootElement();
		//获取根节点bookstore
		//System.out.println(root.getName());
		//通过迭代器遍历
		/*Iterator it = root.elementIterator();
		while(it.hasNext()) {
			Element ele = (Element) it.next();//book节点
			List<Attribute> attr = ele.attributes();//book节点所有属性
			for (Attribute attribute : attr) {
				System.out.println(attribute.getName() + ":" + attribute.getValue());
			}
			
			Iterator eleIt = ele.elementIterator();
			while(eleIt.hasNext()) {
				Element bookChild = (Element) eleIt.next();
				System.out.println(bookChild.getName() + ":" + bookChild.getStringValue());
			}
		}*/
 		
		List<Element> elements = root.elements();
		for (Element element : elements) {
			//System.out.println(element.getName() + ":" + element.getStringValue());
			//element包含整个book元素及其子元素
			List<Attribute> attrs = element.attributes();//book元素的所有属性
			for (Attribute attribute : attrs) {
				System.out.println(attribute.getName() + ":" + attribute.getValue());
			}
			List<Element> bookChilds = element.elements();
			for (Element bookChild : bookChilds) {
				System.out.println(bookChild.getName() + ":" + bookChild.getStringValue());
			}
			System.out.println("***********************************");
		}
	}
}

2.使用dom解析将xml：

/**
 * @author zy
 *dom解析将xml文档转换成dom树放在内存，因此对于文档太大的xml会耗会太多内存
 */
package com.channelsoft.dom;

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

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

public class DOMTest {
	public static void main(String[] args) throws Exception {
		// 创建一个DocumentBuilderFactory对象
		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
		// 创建DocumentBuilder对象
		DocumentBuilder db = factory.newDocumentBuilder();
		// 将xml加载到当前项目下
		Document document = db.parse("dom.xml");
		// 遍历多有book节点
		NodeList bookList = document.getElementsByTagName("book");
		int len = bookList.getLength();
		System.out.println("一个有" + len + "个book节点");
		for (int i = 0; i < len; i++) {
			//获取book节点
			Node node = bookList.item(i);
			//获取book节点的所有属性
			NamedNodeMap nodeMap = node.getAttributes();
			for (int j = 0; j < nodeMap.getLength(); j++) {
				//遍历book节点的属性
				Node child = nodeMap.item(j);
				System.out.println(child.getNodeName() + ":" + child.getNodeValue());
			}
			//获取book节点的所有子节点
			NodeList childNodes = node.getChildNodes();
			int childLen = childNodes.getLength();
			System.out.println("子节点长度:" + childLen);
			for(int k = 0; k < childLen; k++) {
				Node childNode = childNodes.item(k);//包含五个空白节点（text类型）和四个元素节点
				if(childNode.getNodeType() == Node.ELEMENT_NODE) {
					System.out.println(childNode.getNodeName() + ":" + childNode.getFirstChild().getNodeValue());
				}
			}
		}
	}
}