PHP and CURL

class Core {

function __construct($url = "http://kryptonite-dove.com", $agent = "FireFox") {

    // Preset user agents, could be written into a module to more easily update
    $objUserAgents = new stdClass;
      $objUserAgents->Alias = (object) array(
            FireFox => "Mozilla/5.0 (Windows NT 5.1; rv:2.0b9pre) Gecko/20110105 Firefox/4.0b9pre",
            IE => "IE",
            Chrome => "Chrome",
            Safari => "Safari",
            ByteMe => "Robot Byte.Me.uk");


    // Parse & encode the url
    $url = $this->parseURL($url);
        $this->initcURL($url, $objUserAgents->Alias->$agent);
}



 private function initcURL($url, $useragent) {
    // Initiate curl session
     $ch = curl_init();

     // Set curl headers including user agent
        curl_setopt($ch, CURLOPT_USERAGENT, $useragent);
        curl_setopt($ch, CURLOPT_URL, $url);
        curl_setopt($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);

     // Execute 
        $this->html = curl_exec($ch);

        // Check for failure
        if (!$this->html) {
            echo "<br />Error number: " .curl_errno($ch);
            echo "\n<br />Error: " . curl_error($ch);
            exit;
        }

    // Else close curl session  
     curl_close($ch);       

     $this->url = $url;

 }


 private function parseURL($urlToParse) {

    // Remove http(s):// if entered
    $regex = '#^https?://#';
        $urlToParse = preg_replace($regex, "", strtolower($urlToParse));

        //echo $urlToParse;

    // Check if whats left is a valid URL
    $regex = '_^(?:(?:https?|ftp)://)(?:\S+(?::\S*)?@)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)(?:\.(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)*(?:\.(?:[a-z\x{00a1}-\x{ffff}]{2,})))(?::\d{2,5})?(?:/[^\s]*)?$_iuS';

    // Add http
        $urlToParse = "http://".$urlToParse;

    // Check if URL is a valid match
    if ($isURL = preg_match($regex, $urlToParse) == true) {
         // Return
         return $parsedURL = $urlToParse;
    } else {
        echo "Error: URL is not valid.";
        exit;
    }        
 }



 public function scrapeAnchors($url, $html) {

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

        // grab all the on the page
        $xpath = new DOMXPath($dom);
        $tags = $xpath->evaluate("/html/body//a");
        $anchor_count = 0;

                echo "<h1>{$url}.</h1>\n\r\n\r";
                echo "\n\r<ul>";

                for ($i = 0; $i < $tags->length; $i++) {
                    $href = $tags->item($i);
                    $url = $href->getAttribute('href');
                    //$title = $href->getAttribute('title');



                        if ($url != "#" && $url != "javascript:void(0)" && $url != "javascript:void(0);") {
                            echo "\n\t<li><a href='//byte.me.uk/index.php?url={$url}'>{$url}</a> {$title}</li>";    
                            $anchor_count++;
                        }


                }

                echo "\n\r</ul>";           
                    echo "\n\r\n\r<i>{$anchor_count} links found.</i>"; 

 }

public function displayAsText($url, $html) {
    $dom = new DOMDocument();
        echo strip_tags($dom->loadHTML($html));



}


}