Web Crawler – PHP

$target_url = $_GET["url"];
if (empty($target_url)) {$target_url = "http://kittell.net";}

echo "<h1>" . $target_url . "</h1>";

$userAgent = 'Googlebot/2.1 (http://www.googlebot.com/bot.html)';

// make the cURL request to $target_url
$ch = curl_init();
curl_setopt($ch, CURLOPT_USERAGENT, $userAgent);
curl_setopt($ch, CURLOPT_URL,$target_url);
curl_setopt($ch, CURLOPT_FAILONERROR, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch, CURLOPT_TIMEOUT, 10);
$html= curl_exec($ch);
if (!$html) {
	echo "<br />cURL error number:" .curl_errno($ch);
	echo "<br />cURL error:" . curl_error($ch);
	exit;
}

// parse the html into a DOMDocument
$dom = new DOMDocument();
@$dom->loadHTML($html);

// grab all the on the page
$xpath = new DOMXPath($dom);
$hrefs = $xpath->evaluate("/html/body//a");

for ($i = 0; $i < $hrefs->length; $i++) {
	$href = $hrefs->item($i);
	$url = $href->getAttribute('href');
	echo "<br />$url";
}

Example:
” . $target_url . “

“;

$userAgent = ‘Googlebot/2.1 (http://www.googlebot.com/bot.html)’;

// make the cURL request to $target_url
$ch = curl_init();
curl_setopt($ch, CURLOPT_USERAGENT, $userAgent);
curl_setopt($ch, CURLOPT_URL,$target_url);
curl_setopt($ch, CURLOPT_FAILONERROR, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch, CURLOPT_TIMEOUT, 10);
$html= curl_exec($ch);
if (!$html) {
echo “
cURL error number:” .curl_errno($ch);
echo “
cURL error:” . curl_error($ch);
exit;
}

// parse the html into a DOMDocument
$dom = new DOMDocument();
@$dom->loadHTML($html);

// grab all the on the page
$xpath = new DOMXPath($dom);
$hrefs = $xpath->evaluate(“/html/body//a”);

for ($i = 0; $i < $hrefs->length; $i++) {
$href = $hrefs->item($i);
$url = $href->getAttribute(‘href’);
echo “
$url”;
}
?>