Using javax.swing.text.html.HTMLEditorKit to parse html document : HTML Parser « Network « Java Tutorial

1. Java Tutorial
2. Network
3. HTML Parser

import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.List;

import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML.Tag;
import javax.swing.text.html.HTMLEditorKit.ParserCallback;
import javax.swing.text.html.parser.ParserDelegator;

public class Main {
  public static void main(String[] args) throws Exception {
    final List<String> list = new ArrayList<String>();
    ParserDelegator parserDelegator = new ParserDelegator();
    ParserCallback parserCallback = new ParserCallback() {
      public void handleText(final char[] data, final int pos) {
        list.add(new String(data));
      }

      public void handleStartTag(Tag tag, MutableAttributeSet attribute, int pos) {
      }

      public void handleEndTag(Tag t, final int pos) {
      }

      public void handleSimpleTag(Tag t, MutableAttributeSet a, final int pos) {
      }

      public void handleComment(final char[] data, final int pos) {
      }

      public void handleError(final java.lang.String errMsg, final int pos) {
      }
    };
    parserDelegator.parse(new FileReader("a.html"), parserCallback, true);
    System.out.println(list);
  }
}