Java

A Simple Web Crawler

See more Spider Examples

This demonstrates a very simple web crawler using the Chilkat Spider component. Java

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[])
  {
    boolean success = false;

    CkSpider spider = new CkSpider();

    CkStringArray seenDomains = new CkStringArray();
    CkStringArray seedUrls = new CkStringArray();

    seenDomains.put_Unique(true);
    seedUrls.put_Unique(true);

    //  You will need to change the start URL to something else...
    seedUrls.Append("http://something.whateverYouWant.com/");

    //  Set outbound URL exclude patterns
    //  URLs matching any of these patterns will not be added to the 
    //  collection of outbound links.
    spider.AddAvoidOutboundLinkPattern("*?id=*");
    spider.AddAvoidOutboundLinkPattern("*.mypages.*");
    spider.AddAvoidOutboundLinkPattern("*.personal.*");
    spider.AddAvoidOutboundLinkPattern("*.comcast.*");
    spider.AddAvoidOutboundLinkPattern("*.aol.*");
    spider.AddAvoidOutboundLinkPattern("*~*");

    //  Use a cache so we don't have to re-fetch URLs previously fetched.
    spider.put_CacheDir("c:/spiderCache/");
    spider.put_FetchFromCache(true);
    spider.put_UpdateCache(true);

    while (seedUrls.get_Count() > 0) {

        String url = seedUrls.pop();
        spider.Initialize(url);

        //  Spider 5 URLs of this domain.
        //  but first, save the base domain in seenDomains
        String domain = spider.getUrlDomain(url);
        seenDomains.Append(spider.getBaseDomain(domain));

        int i;

        for (i = 0; i <= 4; i++) {
            success = spider.CrawlNext();
            if (success == true) {

                //  Display the URL we just crawled.
                System.out.println(spider.lastUrl());

                //  If the last URL was retrieved from cache,
                //  we won't wait.  Otherwise we'll wait 1 second
                //  before fetching the next URL.
                if (spider.get_LastFromCache() != true) {
                    spider.SleepMs(1000);
                    }

                }
            else {
                //  cause the loop to exit..
                i = 999;
                }

            }

        //  Add the outbound links to seedUrls, except
        //  for the domains we've already seen.
        for (i = 0; i <= spider.get_NumOutboundLinks() - 1; i++) {

            url = spider.getOutboundLink(i);
            String domain = spider.getUrlDomain(url);
            String baseDomain = spider.getBaseDomain(domain);
            if (seenDomains.Contains(baseDomain) == false) {
                //  Don't let our list of seedUrls grow too large.
                if (seedUrls.get_Count() < 1000) {
                    seedUrls.Append(url);
                    }

                }

            }

        }
  }
}