Google keyword position check not working well

Question

I need to check keyword position on google for a list of domains.

Example:

Domain1.com

• keyword1 - GOOGLE_POSITION
• keyword2 - GOOGLE_POSITION
• keyword3 - GOOGLE_POSITION

Domain2.com

• keyword1 - GOOGLE_POSITION
• keyword2 - GOOGLE_POSITION
• keyword3 - GOOGLE_POSITION

Here it's my code:

 <?php

///////// GOOGLE KEYWORD RANK - start

// this function get invokes when user click particular link once after create account (for resume creation)
function getmethod_setCurloption($ch,$ckfile,$google_url)
{
//$useragent="Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.1) Gecko/20061204 Firefox/2.0.0.1";
//curl_setopt($ch, CURLOPT_USERAGENT, $useragent); 

    curl_setopt($ch, CURLOPT_COOKIEFILE, $ckfile); //The name of the file containing the cookie data. The cookie file can be in Netscape format, or just plain HTTP-style headers dumped into a file. 
    curl_setopt($ch, CURLOPT_URL,$google_url); // The URL to fetch. This can also be set when initializing a session with curl_init().
    curl_setopt ($ch, CURLOPT_COOKIEJAR, $ckfile);  // The name of a file to save all internal cookies to when the connection closes. 
    curl_setopt($ch, CURLOPT_HEADER,0); // TRUE to include the header in the output. 
    curl_setopt($ch,CURLOPT_AUTOREFERER,1); // TRUE to automatically set the Referer: field in requests where it follows a Location: redirect. 
    curl_setopt($ch, CURLOPT_RETURNTRANSFER,1); // TRUE to return the transfer as a string of the return value of curl_exec() instead of outputting it out directly. 
    curl_setopt($ch, CURLOPT_POST,0); //TRUE to do a regular HTTP POST. This POST is the normal application/x-www-form-urlencoded kind, most commonly used by HTML forms. 
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    //curl_setopt($ch, CURLOPT_REFERER,"http://qualitypointtech.net");
    curl_setopt($ch,CURLOPT_HTTPHEADER,array ("Accept: text/plain"));
    return $data = curl_exec($ch);
}
function removew($urlstring) // function for removed www
{
    if(strstr($urlstring,"www"))
    {
        $urlstring_arr=explode("www.",$urlstring);
        return $removedw=$urlstring_arr[0].$urlstring_arr[1];
    }
    else 
       return $urlstring;
}
function getTodayDate()
{
    $todayDate=date("d-m-y");
    $todayDate=str_replace("-","",$todayDate);

    return $todayDate;
}
function extract_string($string, $start, $end)// extract portion of string between two delimiters
{
    $pos = stripos($string, $start);

    $str = substr($string, $pos);
    $str_two = substr($str, strlen($start));

    $second_pos = stripos($str_two, $end);

    $str_three = substr($str_two, 0, $second_pos);

    $portion_of_string = trim($str_three); // remove whitespaces

    return $portion_of_string;

}

function googlerank($keyword,$filestring,$position,$searchname)//function for google rank
{

    if(!$ch = curl_init()) //Check for error while initializing cURL session
    { 
        echo "Could not initialize cURL session.\n";
        die;
    }
    $pagination=1;
    $no_of_pagelink=0; // start page
    $totalcount=1;

     $ckfile = tempnam("/tmp", "CURLCOOKIE"); // generate the cookie file
     $curl_googleUrl="http://www.".$searchname."/search?hl=en&q=".urlencode($keyword);//."+site=".urlencode($filestring);

     $data =getmethod_setCurloption($ch,$ckfile,$curl_googleUrl); // using cURL method get all data from selected url

     while(true) // loop execute until reaching last page
     {
       // echo "<b>Extract link from ".$pagination." page</b>"; echo "<br>"; display the number of pages
         /*------- scrap all links from webpage --------------------------*/
      // parse the data into a DOMDocument

      $dom = new DOMDocument();
      @$dom->loadHTML($data);

      // grab all the on the page

      $xpath = new DOMXPath($dom);

      $hrefs = $xpath->evaluate("/html/body//li[@class='g']//h3[@class='r']//a");
      $linkcount=$hrefs->length;

         for ($i = 0; $i < $linkcount; $i++)
         {

            $href = $hrefs->item($i);
            $url = $href->getAttribute('href');

            $filestring=removew($filestring);
            $url=removew($url);

            if (!strstr( $url,$filestring))
            {
              //echo "The string '$filestring' was not found in the url '$url'";
            } 
            else
            {   
            //echo $filestring.$url.$totalcount.$pagination;
            $searchDetails=array($filestring,$url,$totalcount,$pagination);
            return $searchDetails;
            exit;
            }
            if($totalcount==$position)
            {
              return ;
              exit;
            }
            $totalcount++;
        }

         if (!strstr($data,"Next")) //if (intval($pageno)>7)
         {   

            break;
         }

         sleep(rand(2,5));
         $no_of_pagelink=$no_of_pagelink+10;
         $pagination++;
         flush();
        $curl_googleUrl="http://www.".$searchname."/search?hl=ro&q=".urlencode($keyword)."&start=".$no_of_pagelink."&sa=N";
        $data =getmethod_setCurloption($ch,$ckfile,$curl_googleUrl); // using cURL method get all data from selected url
   } //end of while loop
}

function getPosition($dom,$key){
            $keyword=$key;
            $filestring=$dom;
            $position='100';
            $searchname= 'google.ro';

            $siteDetails=googlerank($keyword,$filestring,$position,$searchname);
            $userenterdsite=$siteDetails[0];
            $url=$siteDetails[1];
            $totalcount=$siteDetails[2];
            $pagination=$siteDetails[3];
            $start_string="/url?q=";
            $end_string="&sa=";
            $url=extract_string($url,$start_string,$end_string);

            if(count($siteDetails)>0)
            {
               return $totalcount;

            }
            else
            {

                return 0;

            }
}

I call my function with: $position = getPosition(DOMAIN_NAME,KEYWORD); It is working but sometimes it returns me 0 almost instant, I have some website that have 10 keywords my script returns the correct position only for first 4-5 then goes with 0 on all keywords.

How can I fix it. Or where I can find another script?

Answer 1

I suspect it's because Google is recognizing that you are doing searches too fast and thus are not human. If you printed out the dump from the Google page I think you'd see that.

Try using sleep(_SOME_NUMBER_); where _SOME_NUMBER_ is the number of seconds you want the script to pause between every search. I would start with sleep(60);

This is untested just working from my own experience and memory.

Best, Tim

P.S. Let me know if that solves your problem. Then repost the corrected code for the next person once it's working.