Jump to content

Plagiarism Checking Tool Help


Mikho

Recommended Posts

I am building a plagiarsm checking tool for my company but have problems on calculating the uniqueness factor.

 

Calculation works by searching the snippet into Google using GSERP.  The script then checks if there where results then snippet is not unique.

 

This is my code;

 

$snippet = '"' . join(" ", array_slice($contentArray, $start, $limit)) . '"';

$start += $limit;
$end += $limit;
$counter++;

$url = '';
$lang = 'en';

$gserp = (g_serp($snippet, $url, $lang));
$gserpCount = count($gserp);

. . .


. . .

error_reporting(E_ALL ^ E_NOTICE);

//helper function -- file_get_contents using curl
function file_get_contents_curl($url, $referer = '', $ua = '') {
    $ch = curl_init($url);

    curl_setopt($ch, CURLOPT_HEADER, FALSE);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);

    if ($referer != '') {
        curl_setopt($ch, CURLOPT_REFERER, $referer);
    }

    if ($ua != '') {
        curl_setopt($ch, CURLOPT_USERAGENT, $ua);
    }

    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE);
    curl_setopt($ch, CURLOPT_TIMEOUT, 30);

    $data = curl_exec($ch);

    curl_close($ch);

    return $data;
}

//this is the main function
function g_serp($keyword, $url, $lang = 'en') {
    $results = array();
    $g_url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&q=' . urlencode($keyword) .
            '&rsz=large&userip=' . $_SERVER['REMOTE_DDR'] . '&hl=' . $lang;

    for ($i = 0; $i < 64; $i+= {
        $start = $i;
        $referer = $_SERVER['HTTP_REFERER']; //change this into your real domain
        $rawdata = file_get_contents_curl($g_url . '&start=' . $start, $referer, $_SERVER['HTTP_USER_AGENT']);
        $decoded = json_decode($rawdata, TRUE); //decode as assoc array

        if (is_array($decoded['responseData']['results'])) {
            $pos = $start;

            foreach ($decoded['responseData']['results'] as $result) {
                //if (substr_count(strtolower($result['url']), $url)) {
//                    $GLOBALS['index'] = $pos + 1;
//                }
                
                $res['position'] = $pos + 1;
                $res['title'] = $result['titleNoFormatting'];
                $res['url'] = $result['unescapedUrl'];
                
                array_push($results, $res);

                $pos++;
            }
        }
    }
    
    return $results;
}
Anyone have any idea what I may be doing wrong or how best I can go about this?
Link to comment
https://forums.phpfreaks.com/topic/277869-plagiarism-checking-tool-help/
Share on other sites

Archived

This topic is now archived and is closed to further replies.

×
×
  • Create New...

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.