Java

Must-Match Patterns

See more Spider Examples

You may restrict the spider to only follow links that match any one of a set of "must-match" wildcard patterns. The AddMustMatchPattern can be called repeatedly to add must-match patterns. Chilkat2 Java

import com.chilkatsoft.chilkat2.Spider;

public class ChilkatExample {

    public static void main(String[] args) {
        boolean success = false;

        Spider spider = new Spider();

        // --------------------------------------------------------------------
        // Note: The URLs in this example are no longer valid.
        // You should replace the URLs with URLs from a site of your
        // own choosing -- preferably your own site if testing.
        // (Google's Directory no longer exists.)
        // --------------------------------------------------------------------

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

        spider.initialize("directory.google.com");
        spider.addUnspidered("http://directory.google.com/Top/Recreation/Outdoors/Hiking/Backpacking/");

        success = spider.crawlNext();

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

        // The output:
        // http://www.backpacker.com
        // http://www.cmc.org
        // http://www.backpacking.net
        // http://www.thebackpacker.com/
        // http://www.rei.com/online/store/LearnShareArticlesList?categoryId=Camping
        // http://www.trailspace.com/
        // http://www.catskillhikes.com/
        // http://gorp.away.com/gorp/location/asia/nepal/favpicks.htm
        // http://www.backpackinglight.com/cgi-bin/backpackinglight/index.html
        // http://www.yetizone.com/
        // http://www.backpackingfun.com
        // http://www.freezerbagcooking.com/
        // http://www.spadout.com/backpacking/
        // http://sierrabackpacker.com
        // http://www.abovecalifornia.com/
        // http://www.personal.psu.edu/faculty/r/p/rpc1/bbb/
        // http://www.thebackpackersguide.com
        // http://www.journeywest.com/WB/index.html
        // http://www.johann-sandra.com/backpackdir.htm
        // http://www.geocities.com/amytys/
        // http://www.cloudwalkersbasecamp.com
        // http://www.netbackpacking.com
        // http://members.tripod.com/~stooges/
        // http://www.thebackpackingsite.com
        // http://www.thruhikers.com/
        // http://www.redcompservices.com/AT/
        // http://members.aol.com/CMorHiker/backpack
        // http://mywebpages.comcast.net/midwestpacker/
        // http://www.midwesthiker.com/
        // http://www.WeBackpack.com
        // http://www.michiganhiker.com
        // http://www.host33.com/backpack/
        // http://www.wilderness-backpacking.com
        // http://www.thetravelmonkey.net
        // http://dmoz.org/cgi-bin/add.cgi?where=Recreation/Outdoors/Hiking/Backpacking
        // http://dmoz.org/about.html
        // http://dmoz.org/cgi-bin/apply.cgi?where=Recreation/Outdoors/Hiking/Backpacking
        // http://dmoz.org
        // http://dmoz.org/profiles/cdog.html
        // http://dmoz.org/profiles/justinwp.html

        // Do it again, but this time with avoid patterns.
        spider.initialize("directory.google.com");
        spider.addUnspidered("http://directory.google.com/Top/Recreation/Outdoors/Hiking/Backpacking/");

        // Add some must-match patterns:
        spider.addMustMatchPattern("*.com/*");
        spider.addMustMatchPattern("*.net/*");

        // Add some avoid-patterns:
        spider.addAvoidOutboundLinkPattern("*.mypages.*");
        spider.addAvoidOutboundLinkPattern("*.personal.*");
        spider.addAvoidOutboundLinkPattern("*.comcast.*");
        spider.addAvoidOutboundLinkPattern("*.aol.*");
        spider.addAvoidOutboundLinkPattern("*~*");

        success = spider.crawlNext();

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

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

        // Output:
        // http://www.thebackpacker.com/
        // http://www.rei.com/online/store/LearnShareArticlesList?categoryId=Camping
        // http://www.trailspace.com/
        // http://www.catskillhikes.com/
        // http://gorp.away.com/gorp/location/asia/nepal/favpicks.htm
        // http://www.backpackinglight.com/cgi-bin/backpackinglight/index.html
        // http://www.yetizone.com/
        // http://www.freezerbagcooking.com/
        // http://www.spadout.com/backpacking/
        // http://www.abovecalifornia.com/
        // http://www.journeywest.com/WB/index.html
        // http://www.johann-sandra.com/backpackdir.htm
        // http://www.geocities.com/amytys/
        // http://www.thruhikers.com/
        // http://www.redcompservices.com/AT/
        // http://www.midwesthiker.com/
        // http://www.host33.com/backpack/
    }
}