Apache Xerces DOM Parser - Parse XML Document

Steps to Using DOM

Following are the steps used while parsing a document using DOM Parser.

• Import XML-related packages.
• Create a DocumentBuilder
• Create a Document from a file or stream
• Extract the root element
• Examine attributes
• Examine sub-elements
  

Import XML-related packages

import org.w3c.dom.*;
import javax.xml.parsers.*;
import java.io.*;

Create a DocumentBuilder

DocumentBuilderFactory factory =
DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();

Create a Document from a file or stream

StringBuilder xmlStringBuilder = new StringBuilder();
xmlStringBuilder.append("<?xml version="1.0"?> <class> </class>");
ByteArrayInputStream input =  new ByteArrayInputStream(
   xmlStringBuilder.toString().getBytes("UTF-8"));
Document doc = builder.parse(input);

Extract the root element

Element root = document.getDocumentElement();

Examine attributes

//returns specific attribute
getAttribute("attributeName"); 
//returns a Map (table) of names/values
getAttributes(); 

Examine sub-elements

//returns a list of subelements of specified name
getElementsByTagName("subelementName"); 
//returns a list of all child nodes
getChildNodes(); 

Demo Example

Here is the input xml file we need to parse:

<?xml version="1.0"?>
<class>
   <student rollno="393">
      <firstname>Dinkar</firstname>
      <lastname>Kad</lastname>
      <nickname>Dinkar</nickname>
      <marks>85</marks>
   </student>
   <student rollno="493">
      <firstname>Vineet</firstname>
      <lastname>Gupta</lastname>
      <nickname>Vinni</nickname>
      <marks>95</marks>
   </student>
   <student rollno="593">
      <firstname>Jasvir</firstname>
      <lastname>Singh</lastname>
      <nickname>Jazz</nickname>
      <marks>90</marks>
   </student>
</class>

Demo Example:
DomParserDemo.java

package com.tutorialspoint.xml;

import java.io.File;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.DocumentBuilder;
import org.w3c.dom.Document;
import org.w3c.dom.NodeList;
import org.w3c.dom.Node;
import org.w3c.dom.Element;

public class DomParserDemo {
   public static void main(String[] args){

      try { 
         File inputFile = new File("input.txt");
         DocumentBuilderFactory dbFactory 
            = DocumentBuilderFactory.newInstance();
         DocumentBuilder dBuilder = dbFactory.newDocumentBuilder();
         Document doc = dBuilder.parse(inputFile);
         doc.getDocumentElement().normalize();
         System.out.println("Root element :" 
            + doc.getDocumentElement().getNodeName());
         NodeList nList = doc.getElementsByTagName("student");
         System.out.println("----------------------------");
         for (int temp = 0; temp < nList.getLength(); temp++) {
            Node nNode = nList.item(temp);
            System.out.println("\nCurrent Element :" 
               + nNode.getNodeName());
            if (nNode.getNodeType() == Node.ELEMENT_NODE) {
               Element eElement = (Element) nNode;
               System.out.println("Student roll no : " 
                  + eElement.getAttribute("rollno"));
               System.out.println("First Name : " 
                  + eElement
                  .getElementsByTagName("firstname")
                  .item(0)
                  .getTextContent());
               System.out.println("Last Name : " 
               + eElement
                  .getElementsByTagName("lastname")
                  .item(0)
                  .getTextContent());
               System.out.println("Nick Name : " 
               + eElement
                  .getElementsByTagName("nickname")
                  .item(0)
                  .getTextContent());
               System.out.println("Marks : " 
               + eElement
                  .getElementsByTagName("marks")
                  .item(0)
                  .getTextContent());
            }
         }
      } catch (Exception e) {
         e.printStackTrace();
      }
   }
}

This would produce the following result:

Root element :class
----------------------------

Current Element :student
Student roll no : 393
First Name : Dinkar
Last Name : Kad
Nick Name : Dinkar
Marks : 85

Current Element :student
Student roll no : 493
First Name : Vineet
Last Name : Gupta
Nick Name : Vinni
Marks : 95

Current Element :student
Student roll no : 593
First Name : Jasvir
Last Name : Singh
Nick Name : Jazz
Marks : 90