Must-Match Patterns

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.

Download Chilkat Spider ActiveX

<?php

//  The Chilkat Spider component/library is free.
$spider = new COM("Chilkat.Spider");

//  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 ($i = 0; $i <= $spider->NumOutboundLinks - 1; $i++) {
    print $spider->getOutboundLink($i) . "\n";
}

//  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();

print '-----------------------' . "\n";

//  Display the outbound links
for ($i = 0; $i <= $spider->NumOutboundLinks - 1; $i++) {
    print $spider->getOutboundLink($i) . "\n";
}

//  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/

?>