Avoiding Outbound Links Matching Patterns

The spider accumulates outbound links when crawling. Your program may specify any number of "avoid patterns" to prevent any link matching at least one of the wildcarded patterns from being added.

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();

    //  First, we'll get the outbound links for a page in the
    //  Google directory.  Then we'll add some avoid patterns
    //  and then re-fetch, to see it work...

    spider.Initialize("directory.google.com");
    spider.AddUnspidered("http://directory.google.com/Top/Recreation/Food/Cheese/");

    boolean success;
    success = spider.CrawlNext();

    //  Display the outbound links
    int i;
    String url;
    for (i = 0; i <= spider.get_NumOutboundLinks() - 1; i++) {
        System.out.println(spider.getOutboundLink(i));
    }

    //  The output:
    //  http://www.cheese.com/
    //  http://www.cheesediaries.com/
    //  http://www.WisDairy.com/
    //  http://www.newenglandcheese.com
    //  http://www.ilovecheese.com
    //  http://www.cheesefromspain.com
    //  http://www.realcaliforniacheese.com/
    //  http://www.frencheese.co.uk/
    //  http://www.cheesesociety.org/
    //  http://www.specialcheese.com/queso.htm
    //  http://www.franceway.com/cheese/intro.htm
    //  http://www.foodsubs.com/Chesfirm.html
    //  http://www.cheeseboard.co.uk/
    //  http://www.thecheeseweb.com/
    //  http://www.vtcheese.com/
    //  http://www.coldbacon.com/cheese.html
    //  http://www.norwegiancheeses.co.uk/
    //  http://www.reluctantgourmet.com/cheese.htm
    //  http://www.lancewood.co.za/
    //  http://www.switzerlandcheese.ca
    //  http://www.frenchcheese.dk/
    //  http://www.dolcevita.com/cuisine/cheese/cheese.htm
    //  http://cheeseisland.net/
    //  http://www.cheestrings.ca/
    //  http://www.dreamcheese.co.uk
    //  http://hgic.clemson.edu/factsheets/HGIC3506.htm
    //  http://www.epicurious.com/cooking/how_to/food_dictionary/entry?id=1815
    //  http://www.mousetrapcheese.co.uk
    //  http://taquitos.net/yum/gc.shtml
    //  http://www.greek-recipe.com/static/greek-cheese
    //  http://www.park.org/Netherlands/pavilions/food_and_markets/cheese/introduction.html
    //  http://www.dairyfarmers.org/engl/recipes/4_1.asp
    //  http://www.prairieridgecheese.com/wischeesguid.html
    //  http://dmoz.org/cgi-bin/add.cgi?where=Recreation/Food/Cheese
    //  http://dmoz.org/about.html
    //  http://dmoz.org/cgi-bin/apply.cgi?where=Recreation/Food/Cheese

    //  Do it again, but this time with avoid patterns.
    spider.Initialize("directory.google.com");
    spider.AddUnspidered("http://directory.google.com/Top/Recreation/Food/Cheese/");

    //  Add some avoid patterns:
    spider.AddAvoidOutboundLinkPattern("*dmoz.org*");
    spider.AddAvoidOutboundLinkPattern("*?id=*");
    spider.AddAvoidOutboundLinkPattern("*.co.uk*");
    success = spider.CrawlNext();

    System.out.println("-----------------------");

    //  Display the outbound links
    for (i = 0; i <= spider.get_NumOutboundLinks() - 1; i++) {
        System.out.println(spider.getOutboundLink(i));
    }

    //  Output:
    //  http://www.cheese.com/
    //  http://www.cheesediaries.com/
    //  http://www.WisDairy.com/
    //  http://www.newenglandcheese.com
    //  http://www.ilovecheese.com
    //  http://www.cheesefromspain.com
    //  http://www.realcaliforniacheese.com/
    //  http://www.cheesesociety.org/
    //  http://www.specialcheese.com/queso.htm
    //  http://www.franceway.com/cheese/intro.htm
    //  http://www.foodsubs.com/Chesfirm.html
    //  http://www.thecheeseweb.com/
    //  http://www.vtcheese.com/
    //  http://www.coldbacon.com/cheese.html
    //  http://www.reluctantgourmet.com/cheese.htm
    //  http://www.lancewood.co.za/
    //  http://www.switzerlandcheese.ca
    //  http://www.frenchcheese.dk/
    //  http://www.dolcevita.com/cuisine/cheese/cheese.htm
    //  http://cheeseisland.net/
    //  http://www.cheestrings.ca/
    //  http://hgic.clemson.edu/factsheets/HGIC3506.htm
    //  http://taquitos.net/yum/gc.shtml
    //  http://www.greek-recipe.com/static/greek-cheese
    //  http://www.park.org/Netherlands/pavilions/food_and_markets/cheese/introduction.html
    //  http://www.dairyfarmers.org/engl/recipes/4_1.asp
    //  http://www.prairieridgecheese.com/wischeesguid.html

  }
}