Look for specific tag types, such as HTML.Tag.H1, HTML.Tag.H2 : HTML Document « Swing « Java Tutorial

1. Java Tutorial
2. Swing
3. HTML Document

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;

import javax.swing.text.AttributeSet;
import javax.swing.text.Element;
import javax.swing.text.ElementIterator;
import javax.swing.text.StyleConstants;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLDocument;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;

public class MainClass {

  public static void main(String args[]) throws Exception {
    URL url = new URL("http://www.google.com");
    URLConnection connection = url.openConnection();
    InputStream is = connection.getInputStream();
    InputStreamReader isr = new InputStreamReader(is);
    BufferedReader br = new BufferedReader(isr);

    HTMLEditorKit htmlKit = new HTMLEditorKit();
    HTMLDocument htmlDoc = (HTMLDocument) htmlKit.createDefaultDocument();
    HTMLEditorKit.Parser parser = new ParserDelegator();
    HTMLEditorKit.ParserCallback callback = htmlDoc.getReader(0);
    parser.parse(br, callback, true);

    Element element;
    ElementIterator iterator = new ElementIterator(htmlDoc);
    while ((element = iterator.next()) != null) {
      AttributeSet attributes = element.getAttributes();
      Object name = attributes.getAttribute(StyleConstants.NameAttribute);
    
      if ((name instanceof HTML.Tag)
          && (name == HTML.Tag.H1 || name == HTML.Tag.H2 || name == HTML.Tag.P )) {
        // Build up content text as it may be within multiple elements
        int count = element.getElementCount();
        for (int i = 0; i < count; i++) {
          Element child = element.getElement(i);
          AttributeSet childAttributes = child.getAttributes();
          if (childAttributes.getAttribute(StyleConstants.NameAttribute) == HTML.Tag.CONTENT) {
            int startOffset = child.getStartOffset();
            int endOffset = child.getEndOffset();
            int length = endOffset - startOffset;
            System.out.println(htmlDoc.getText(startOffset, length));
          }
        }
      }
    }
  }

}

14.37.HTML Document
	14.37.1.	HTML Tag Constants
	14.37.2.	Iterating Across HTML Documents for Links
	14.37.3.	Look for specific tag types, such as HTML.Tag.H1, HTML.Tag.H2
	14.37.4.	ElementIterator Class
	14.37.5.	Finding out interested element
	14.37.6.	HyperlinkListener Example