Get Base Domains

Demonstrates how to accumulate a list of unique domain names referenced from outbound URLs.

Download Chilkat Java Library

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    // The Chilkat Spider component/library is free.
    CkSpider spider = new CkSpider();

    CkStringArray domainList = new CkStringArray();

    // Set the Unique property so that duplicates are not added.
    domainList.put_Unique(true);

    // Crawl the home page of joelonsoftware.com and get the outbound URLs
    spider.Initialize("www.joelonsoftware.com");
    spider.AddUnspidered("http://www.joelonsoftware.com/");

    boolean success;
    success = spider.CrawlNext();

    // Build a list of unique domains.
    int i;
    String url;
    for (i = 0; i <= spider.get_NumOutboundLinks() - 1; i++) {
        url = spider.getOutboundLink(i);
        domainList.Append(spider.getDomain(url));
    }

    // Display the domains.
    for (i = 0; i <= domainList.get_Count() - 1; i++) {
        System.out.println(domainList.getString(i));
        System.out.println(spider.getBaseDomain(domainList.getString(i))
             + "\n");
    }

  }
}