java html parsing

Use class HTMLEditorKit in java

Hi Friend,

To parse HTML file,try the following code:

import java.io.*;
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import javax.swing.text.html.parser.*;

public class ParseHTML extends HTMLEditorKit.ParserCallback {
public void handleText(char[] data, int pos){
System.out.println(new String(data));
}
public void handleStartTag(HTML.Tag tag, MutableAttributeSet att, int pos){
System.out.println("Start tag: " + tag);
}
public void handleEndTag(HTML.Tag tag, int pos){
System.out.println("End tag: " + tag);
}
public void handleSimpleTag(HTML.Tag tag, MutableAttributeSet att, int pos){
if (tag == HTML.Tag.META){
String name1=(String)att.getAttribute(HTML.Attribute.NAME);
if (name1 != null){
System.out.println("META name1: " + name1);
}
String content1 = (String)att.getAttribute(HTML.Attribute.CONTENT);
if (content1 != null){
System.out.println("META content1: " + content1);
}
}
}
public static void main(String argv[]) {
try {
Reader read = new FileReader("a.html");
ParserDelegator parser = new ParserDelegator();
HTMLEditorKit.ParserCallback callback = new ParseHTML();
parser.parse(read, callback, false);
}
catch (IOException e) {
e.printStackTrace();
}
}
}

But first of all you need to create a html file.

Thanks