Java操作xml

dom解析XML

<?xml version="1.0" encoding="utf-8" ?>
<books>

  <book category ="文学">
      <title>西游记</title>
      <author>吴承恩</author>
      <publish>人民文学出版社</publish>
  </book>

    <book category ="历史">
        <title>魏晋南北朝</title>
        <author>陈寅格</author>
        <publish>人民文学出版社</publish>
    </book>

</books>

代码实现过程

package com.shanghai.xml;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.io.File;
import java.io.IOException;

import static javax.xml.parsers.DocumentBuilderFactory.newDefaultInstance;

public class Driver {

    public static void main(String[] args) {
//        创建新的XML文档对象
        File xmlFile=new File("D:\\project\\CheckXML\\src\\main\\resources\\book.xml");
//        调用newDefaultInstance() 方法得到创建DOM 解析器工厂
        DocumentBuilderFactory documentBuilderFactory=
                newDefaultInstance();
        try {


            DocumentBuilder documentBuilder=documentBuilderFactory.newDocumentBuilder();
//            调用DOM解析器对象的parse()方法解析XML文档，得到文档的Docment对象
            Document document=documentBuilder.parse(xmlFile);
            document.getDocumentElement().normalize();
            System.out.println("Root element:\t"+document.getDocumentElement().getNodeName());
            System.out.println("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~");
//            逐级解析节点
            NodeList nodeList=document.getElementsByTagName("book");
//            遍历结点，输出结果
            for (int i = 0; i <nodeList.getLength() ; i++) {
                Node node=nodeList.item(i);
                System.out.println("Node name:\t"+node.getNodeName());
                Element element= (Element) node;

                System.out.println("\n\n**************************************\n\n");
                if(node.getNodeType()==Element.ELEMENT_NODE){
                    System.out.println("book category:\t"+element.getAttribute("category"));
                    System.out.println("title name:\t"+element.getElementsByTagName("title").item(0).getTextContent());

                    System.out.println("author name:\t"+element.getElementsByTagName("author").item(0).getTextContent());

                    System.out.println("publish:\t"+element.getElementsByTagName("publish").item(0).getTextContent());

                    System.out.println("\n\n**************************************\n\n");
                }

            }
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

DOM4J解析XML示例

<?xml version="1.0" encoding="UTF-8" ?>
<图书信息>
    <图书>
        <书名>西游记</书名>
        <作者>吴承恩</作者>
        <出版社>人民文学出版社</出版社>
    </图书>

    <图书>
        <书名>魏晋南北朝</书名>
        <作者>陈寅格</作者>
        <出版社>人民文学出版社</出版社>
    </图书>

</图书信息>

代码实现详细过程

package com.dom4j;

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

import java.io.File;
import java.util.Iterator;
import java.util.List;

public class ReadXMLHandler {
    public  void readXML(String xmlPath){
//        指定要解析的文件
        File file=new File(xmlPath);
//        选定解析方式
        SAXReader saxReader=new SAXReader();

        try {
//            具体解析XML文档
            Document document=saxReader.read(file);
//            获取根节点
            Element root=document.getRootElement();
            Element foo;


    //方法1
            Iterator iterator0= root.elementIterator("图书");
            while (iterator0.hasNext()){
                foo= (Element) iterator0.next();
                System.out.println("书名"+foo.elementText("书名"));
                System.out.println("作者"+foo.elementText("作者"));
                System.out.println("出版社"+foo.elementText("出版社"));
                System.out.println("============================================");
            }

    //方法2
            List nodes=root.elements("图书");
            for (Iterator iterator1=nodes.iterator();iterator1.hasNext();) {
                foo= (Element) iterator1.next();
                for (Iterator iterator2=foo.elementIterator();iterator2.hasNext();) {
                    Element element= (Element) iterator2.next();
                    System.out.println(element.getName()+":"+element.getText()+":");

                }
                System.out.println("============================================");
            }
        } catch (DocumentException e) {
            e.printStackTrace();
        }
    }
}

测试

package com.test;

import com.dom4j.ReadXMLHandler;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;


import java.io.File;
import java.util.Iterator;

public class Test {
    public static void main(String[] args) {
        String xmlFile="D:\\project\\CheckDom4j\\src\\main\\resources\\books.xml";
        ReadXMLHandler readXMLHandler=new ReadXMLHandler();
        readXMLHandler.readXML(xmlFile);
    }
}