// a simple web crawler example

// v1.1

//



$toplink = "http://edmondhui.homeip.net/blog";

$depth = 2;



walkIt($toplink,1);



function walkIt($link, $level) {

	global $depth;

	if ($level <= $depth) {

		$content = file($link);

		if ($content != false) {

			$content = html_entity_decode(implode($content));

			//

			// IF NEED, PAGE CONTENTS PROCESS AND SAVE TO DB HERE

			//

			preg_match_all("/href=\".*?\"/i", $content, $matches);

			$matches = array_unique($matches[0]);

			foreach ($matches as $idx => $url) {

				$url = substr($url, 6, -1);

				if (strstr($url, "http://") != false) {

					for ($i = 0; $i < $level; $i++) { echo '  '; }

					echo "$url\n";

					walkIt($url, $level+1);

				}

			}

		} else {

			echo "failed to crawle - $link\n";

		}

	}

}

?>