Get all hyper links from a web page : HTML Parser « Network « Java Tutorial


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

public class Main {
  public static void main(String args[]) throws Exception {
    URL url = new URL(args[0]);
    Reader reader = new InputStreamReader((InputStream) url.getContent());
    System.out.println("<HTML><HEAD><TITLE>Links for " + args[0] + "</TITLE>");
    System.out.println("<BASE HREF=\"" + args[0] + "\"></HEAD>");
    new ParserDelegator().parse(reader, new LinkPage(), false);

class LinkPage extends HTMLEditorKit.ParserCallback {

  public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
    if (t == HTML.Tag.A) {
      System.out.println("<A HREF=\"" + a.getAttribute(HTML.Attribute.HREF) + "\">"
          + a.getAttribute(HTML.Attribute.HREF) + "</A><BR>");


19.26.HTML Parser
19.26.1.Getting the Links in an HTML Document
19.26.2.Getting the Text in an HTML Document
19.26.3.Escape HTML special characters from a String
19.26.4.Using javax.swing.text.html.HTMLEditorKit to parse html document
19.26.5.Extract links from an HTML page
19.26.6.extends HTMLEditorKit.ParserCallback
19.26.7.HTML parser based on HTMLEditorKit.ParserCallback
19.26.8.Find and display hyperlinks contained within a web page
19.26.9.Get all hyper links from a web page
19.26.10.HTML Parser