Java 解析XML dom4j

阅读更多

对于Java解析XML有很多种方法，不过用的最多应该就是dom4j了。先来无事，稍微研究一下它。

 

1．下载

下载地址：http://sourceforge.net/projects/dom4j

目前最高版本为1.6.1。

dom4j1.6.1的完整版大约11M，是一个名为dom4j-1.6.1.zip的压缩包，解压后有一个dom4j-1.6.1.jar文件，这就是应用时需要引入的类包，另外还需要引入jaxen-1.1-beta-6.jar文件，否则执行时可能抛java.lang.NoClassDefFoundError: org/jaxen/JaxenException异常，其他的包可以选择用之。

 

2.应用

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.net.MalformedURLException;
import java.util.Iterator;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.CDATA;
import org.dom4j.Comment;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.DocumentType;
import org.dom4j.Element;
import org.dom4j.Namespace;
import org.dom4j.Node;
import org.dom4j.ProcessingInstruction;
import org.dom4j.Text;
import org.dom4j.VisitorSupport;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

/**
 * @author:kenny dong
 */
public class Dom4JDemo {

	/**
	 * @param args
	 * @throws DocumentException 
	 * @throws IOException 
	 */
	public static void main(String[] args) throws DocumentException, IOException {
		Dom4JDemo demo = new Dom4JDemo();
		Document doc = demo.read("D:/Demo.xml");
		//demo.IteratorAllElement(demo.getRootElement(doc));
		//demo.IteratorSpecialElement(demo.getRootElement(doc),"journal");
		//demo.IteratorAttribute(demo.getRootElement(doc));
		//demo.treeWalk(doc);
		//doc.accept(new MyVisitor());
		//demo.selectSingleNodeTest(doc);
		demo.writeToFile(demo.createDocument());
		demo.decorateOutputXML(demo.createDocument());

	}
	/**
	 * read from outside
	 * @param fileName
	 * @return
	 * @throws MalformedURLException
	 * @throws DocumentException
	 */
	public Document read(String fileName) throws MalformedURLException, DocumentException {
	       SAXReader reader = new SAXReader();
	       Document document = reader.read(new File(fileName));
	       return document;
	 }
	
	/**
	 * get root element
	 * @param doc
	 * @return
	 */
	 public Element getRootElement(Document doc){
	       return doc.getRootElement();
	  }
	 
	 /**
	  * iterator all element by iterator
	  * @param root
	  */
	 public void IteratorAllElement(Element root){
		 for ( Iterator i = root.elementIterator(); i.hasNext(); ) {
		       Element element = (Element) i.next();
		       System.out.println(element.getName() + "\n" + element.asXML());
		   }
	 }
	 
	 /**
	  * iterator specail element by name
	  * @param root
	  * @param elementName
	  */
	 public void IteratorSpecialElement(Element root,String elementName){
		 for ( Iterator i = root.elementIterator(elementName); i.hasNext();) {
		       Element element = (Element) i.next();
		       System.out.println(element.getName() + "\n" + element.asXML());
		    }
	 }
	 
	 /**
	  * iterator all attributes
	  * @param root
	  */
	 public void IteratorAttribute(Element root){
		 for ( Iterator i = root.attributeIterator(); i.hasNext(); ) {
		       Attribute attribute = (Attribute) i.next();
		       System.out.println(attribute.getName() + "\n" + attribute.asXML());
		    }
	 }
	 
	 /**
	  * iterator all elements by recursion
	  * @param doc
	  */
	 public void treeWalk(Document doc) {
	       treeWalk(getRootElement(doc));
	    }
	 public void treeWalk(Element element) {
	       for (int i = 0, size = element.nodeCount(); i < size; i++){
	           Node node = element.node(i);
	           if (node instanceof Element) {
	              treeWalk((Element) node);
	           } else {
	        	   System.out.println(node.asXML());
	           }
	       }
	}
	 
	 public void selectSingleNodeTest(Document doc){
		 Node node = doc.selectSingleNode("//journal/article");
		System.out.println("select single node " + node.asXML());
	 }
	 
	 public void selectNodesTest(Document document) {
	        List list = document.selectNodes("//journal/article" );
	        for(Object node : list){
	        	if(node instanceof Element){
	        		((Element) node).asXML();
	        	}
	        }
	   }
	 
	 public void findLinks(Document document) throws DocumentException {
	        List list = document.selectNodes("//a/@href");
	        for (Iterator iter = list.iterator(); iter.hasNext(); ) {
	            Attribute attribute = (Attribute) iter.next();
	            String url = attribute.getValue();
	            System.out.println("url " + url);
	        }
	     }
	 
	 public Document stringToDocument(String str) throws DocumentException{
		 return DocumentHelper.parseText(str);
	 }
	 
	 public Document createDocument() {
	       Document document = DocumentHelper.createDocument();// create docment
	       Element root = document.addElement("root");// create the root Element
           root.addElement("author")// create child Element
              .addAttribute("name", "James")// add attribute for the child Element
              .addAttribute("location", "UK")
              .addText("James Strachan")
              .addComment("This is the first author");// add text for the child Element
           
           root.addElement("author")
              .addAttribute("name", "Bob")
              .addAttribute("location", "US")
              .addText("Bob McWhirter");
           System.out.println(document.asXML());
	       return document;
	    }
	 
	 public void writeToFile(Document doc) throws IOException{
		 XMLWriter writer = new XMLWriter(new FileWriter("d:/output.xml"));
	      writer.write(doc);
	      writer.close();
	 }
	 
	 public void decorateOutputXML(Document doc) throws IOException{
		   FileWriter outputStream = new FileWriter("d:/output1.xml");
		   XMLWriter writer;
		   OutputFormat format;
	       format = OutputFormat.createPrettyPrint();//the default pretty printing format
	       //format = OutputFormat.createCompactFormat();//default compact format
	       //format = new OutputFormat("aaaa", false);// custom format
	       writer= new XMLWriter(outputStream, format );
	       writer.write(doc);
	       writer.close();
	 }
	 
	 public void moidfyXML(Document doc){
		 Element root = doc.getRootElement();
		 Attribute author = root.attribute("author");// select attribute
		 root.remove(author);// remove attribute
		 root.addAttribute("user", "user_kenny");// add new attribute
		 
	 }
}

class MyVisitor extends VisitorSupport {
    public void visit(Element element){
        System.out.println("element " + element.getName());
    }
    public void visit(Attribute attr){
        System.out.println("atrribute " + attr.getName());
    }
    
    public void visit(Node node){
    	 System.out.println("node " + node.asXML());
    }
    
    public void visit(Text text){
   	 System.out.println("text " + text.asXML());
   }
    
    public void visit(ProcessingInstruction pro){
    	 System.out.println("ProcessingInstruction " + pro.asXML());
    }
    
    
    public void visit(Namespace namespace){
   	 System.out.println("Namespace " + namespace.asXML());
   }
    
    public void visit(Comment comment){
      	 System.out.println("Comment " + comment.asXML());
      }
    
    public void visit(CDATA data){
     	 System.out.println("CDATA " + data.asXML());
     }
    
    public void visit(DocumentType docType){
     	 System.out.println("DocumentType " + docType.asXML());
     }
    
    
    public void visit(Document doc){
     	 System.out.println("Document " + doc.asXML());
     }
    
 }