Android™

CanonicalizeUrl

See more Spider Examples

The CanonicalizeUrl method is a utility function that canonicalizes a URL into a standard form to avoid duplicates. For example, "http://www.chilkatsoft.com/" and "http://www.chilkatsoft.com/default.asp" are the same URL. Android™

// Important: Don't forget to include the call to System.loadLibrary
// as shown at the bottom of this code sample.
package com.test;

import android.app.Activity;
import com.chilkatsoft.*;

import android.widget.TextView;
import android.os.Bundle;

public class SimpleActivity extends Activity {

  private static final String TAG = "Chilkat";

  // Called when the activity is first created.
  @Override
  public void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);

    CkSpider spider = new CkSpider();

    //  Does a DNS lookup to find the default domain, which may or may not include the "www." depending on the DNS results.
    //  Also domain names are converted to lowercase:
    Log.i(TAG, spider.canonicalizeUrl("http://www.ChilkatSoft.com/"));

    //  CanonicalizeUrl will drop the HTML fragment:
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/purchase2.asp#buyZip"));

    //  If a username/password is in the URL, it gets dropped:
    Log.i(TAG, spider.canonicalizeUrl("http://username:password@www.chilkatsoft.com/purchase2.asp#buyZip"));

    //  Port 80 and 443 are dropped:
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com:80/purchase2.asp"));
    Log.i(TAG, spider.canonicalizeUrl("https://www.paypal.com:443/"));

    //  Removes default pages:
    //  default.asp, index.html, index.htm, default.html, index.htm, default.htm
    //  index.php, index.asp, default.php, .cfm, .aspx, ,php3, .pl, .cgi, .txt, .shtml, .phtml
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/index.asp"));
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/index.asp"));
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/index.php"));
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/index.pl"));
    Log.i(TAG, spider.canonicalizeUrl("http://www.chilkatsoft.com/index.htm"));

    //  Output:
    //  http://chilkatsoft.com/
    //  http://chilkatsoft.com/purchase2.asp
    //  http://chilkatsoft.com/purchase2.asp
    //  http://chilkatsoft.com/purchase2.asp
    //  https://www.paypal.com/
    //  http://chilkatsoft.com/
    //  http://chilkatsoft.com/
    //  http://chilkatsoft.com/
    //  http://chilkatsoft.com/
    //  http://chilkatsoft.com/

  }

  static {
      System.loadLibrary("chilkat");

      // Note: If the incorrect library name is passed to System.loadLibrary,
      // then you will see the following error message at application startup:
      //"The application <your-application-name> has stopped unexpectedly. Please try again."
  }
}