java处理xml——Dom4j方式

原创

DanielMaster 2023-10-24 14:36:35 博主文章分类：Java ©著作权

文章标签 Java java xml 文章分类 Java 后端开发 yyds干货盘点

©著作权归作者所有：来自51CTO博客作者DanielMaster的原创作品，请联系作者获取转载授权，否则将追究法律责任

Maven依赖，1.6+版的Dom4j得引入jaxen包

<dependencies>
	<dependency>
		<groupId>jaxen</groupId>
		<artifactId>jaxen</artifactId>
		<version>1.1.6</version>
	</dependency>
	<dependency>
		<groupId>dom4j</groupId>
		<artifactId>dom4j</artifactId>
		<version>1.6</version>
	</dependency>
</dependencies>

字符串格式的xml

<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Java Tutorials and Examples</title><item><title><![CDATA[Java Tutorials]]></title><link>http://www.javacodegeeks.com/</link></item><item><title><![CDATA[Java Examples]]></title><link>http://examples.javacodegeeks.com/</link></item></channel><channel></channel></rss>

格式化的xml

<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
	<channel>
		<title>Java Tutorials and Examples</title>
		<item>
			<title>
				<![CDATA[Java Tutorials]]>
			</title>
			<link>http://www.javacodegeeks.com/</link>
		</item>
		<item>
			<title>
				<![CDATA[Java Examples]]>
			</title>
			<link>http://examples.javacodegeeks.com/</link>
		</item>
	</channel>
	<channel></channel>
</rss>

带namespace的xml

<dom:rss xmlns:dom="http://www.domstandard.org/dom/5" version="2.0"><dom:channel><dom:title>Java Tutorials and Examples</dom:title><dom:item><dom:title><![CDATA[Java Tutorials]]></dom:title><dom:link>http://www.javacodegeeks.com/</dom:link></dom:item><dom:item><dom:title><![CDATA[Java Examples]]></dom:title><dom:link>http://examples.javacodegeeks.com/</dom:link></dom:item></dom:channel><dom:channel></dom:channel></dom:rss>

完整代码：

package com.blog.dom4j;

import org.dom4j.*;

import java.util.*;

/**
 * @Author Daniel
 * @Description 使用Dom4j解析xml
 **/
public class Dom4jAPI {
    static Document doc = null;
    static Element root = null;

    public static void main(String[] args) {
        String xml = "<rss version=\"2.0\"><channel><title>Java Tutorials and Examples</title><item><title><![CDATA[Java Tutorials]]></title><link>http://www.javacodegeeks.com/</link></item><item><title><![CDATA[Java Examples]]></title><link>http://examples.javacodegeeks.com/</link></item></channel><channel><title><title></title></title><title></title></channel></rss>";
        try {
            doc = DocumentHelper.parseText(xml);

        } catch (DocumentException e) {
            e.printStackTrace();
        }
        root = doc.getRootElement();
//        traverse(root);
//        create();
//        update();
//        retrieve();
//        delete();
//        deleteNameSpace();
        String res = doc.asXML();

        //去掉第一行的注释
        System.out.println(res.substring(res.indexOf(">") + 1).trim());
    }

    public static void create() {
        //两种方式添加节点
        Element newTag1 = root.addElement("books");
        newTag1.setText("addElement");
        newTag1.addAttribute("bookid", "1");

        Element newTag2 = DocumentHelper.createElement("books");
        newTag2.setText("createElement");
        newTag2.addAttribute("bookid", "2");
        root.add(newTag2);

        //克隆一个节点，这里克隆第一个channel节点
        Element element = (Element) root.selectSingleNode("//channel").clone();
        root.add(element);
    }

    public static void update() {
        //修改节点名
        root.setName("root");
    }

    public static void retrieve() {
        // "/"表示从当前元素对象下一级开始找，"//"表示从整个文件个根节点开始找
        //selectNodes返回所有符合传入的XPath节点的集合
        List<Element> titleList = root.selectNodes("//title");
        for (Element element : titleList) {
            System.out.println("name:" + element.getName() + ",path:" + element.getPath());
        }
        Node titleNode = root.selectSingleNode("//title");
        System.out.println("titleNode name:" + titleNode.getName() + ",titleNode path:" + titleNode.getPath());

        //获取指定位置的指定节点的个数（获取第二个channel下的所有的title）
        String XPath = "/rss/channel[2]//title";
        int count = doc.numberValueOf("count(" + XPath + ")").intValue();
        System.out.println(XPath + "出现的次数为：" + count);

        //拿到第一个channel的path:/rss/channel
        Element channelElement = (Element) root.selectSingleNode("//channel");
        //获取相同path的第2个元素，等同于/rss/channel[2]
        System.out.println(channelElement.getXPathResult(2).getPath());
        //判断某个element是否为单标签
        Node channel2 = root.selectSingleNode("//channel[2]");
        boolean flag = channel2.hasContent();
        System.out.println("第二个channel不为单标签：" + flag);

    }

    public static void delete() {
        //删除第二个channel
        Node channel2 = root.selectSingleNode("//channel[2]");
        root.remove(channel2);
    }

    //遍历整个xml的path
    public static void traverse(Element root) {
        //root.elements遍历root下一级的所有元素
        List<Element> rootList = root.elements();
        for (Element element : rootList) {
            System.out.println(element.getPath());
            traverse(element);
        }
    }

    //删除xml中所有的namespace
    public static void deleteNameSpace() {
        String namespaceXml = "<dom:rss xmlns:dom=\"http://www.domstandard.org/dom/5\" version=\"2.0\"><dom:channel><dom:title>Java Tutorials and Examples</dom:title><dom:item><dom:title><![CDATA[Java Tutorials]]></dom:title><dom:link>http://www.javacodegeeks.com/</dom:link></dom:item><dom:item><dom:title><![CDATA[Java Examples]]></dom:title><dom:link>http://examples.javacodegeeks.com/</dom:link></dom:item></dom:channel><dom:channel></dom:channel></dom:rss>";
        Document document = null;
        try {
            document = DocumentHelper.parseText(namespaceXml);
        } catch (DocumentException e) {
            e.printStackTrace();
        }
        //Load parse class
        document.accept(new Dom4jNameSpaceCleaner());
    }
}

Dom4jNameSpaceCleaner类，这里继承Dom4j中的VisitorSupport类来实现加载前删除命名空间

package com.blog.dom4j;

import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.Namespace;
import org.dom4j.VisitorSupport;
import org.dom4j.tree.DefaultElement;

/**
 * @Author Daniel
 * @Description 删除root与子节点的namespace
 **/
public class Dom4jNameSpaceCleaner extends VisitorSupport {

    //Remove root namespace
    public void visit(Document document) {
        ((DefaultElement) document.getRootElement())
                .setNamespace(Namespace.NO_NAMESPACE);
        document.getRootElement().additionalNamespaces().clear();
    }


    //Remove element namespace
    public void visit(Element node) {
        if (node instanceof DefaultElement) {
            ((DefaultElement) node).setNamespace(Namespace.NO_NAMESPACE);
        }
    }
}