PHP Extension

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. PHP Extension

<?php

include("chilkat.php");

$success = false;

$spider = new CkSpider();

// --------------------------------------------------------------------
// Note: The URLs in this example are no longer valid.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 ($i = 0; $i <= $spider->get_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->get_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

?>