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






  1. Java
  2. Network Protocol
  3. HTML Parser

Get all hyper links from a web page

 


import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.URL;

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>");
    System.out.println("<BODY>");
    new ParserDelegator().parse(reader, new LinkPage(), false);
    System.out.println("</BODY></HTML>");
  }
}

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>");
    }
  }

}








Related examples in the same category

1.Escape HTML special characters from a String
2.Using javax.swing.text.html.HTMLEditorKit to parse html document
3.Extract links from an HTML page
4.extends HTMLEditorKit.ParserCallback
5.HTML parser based on HTMLEditorKit.ParserCallback
6.Getting the Links in an HTML Document
7.Getting the Text in an HTML Document
8.Find and display hyperlinks contained within a web page
9.Use regular expression to get web page title