Question

我正在为我公司建立一个plagiarsm检查工具，但在计算唯一性因素方面存在问题。

通过使用GSERP将代码段搜索到Google来进行计算。然后该脚本检查结果是否在哪里，然后片段不是唯一的。

这是我的代码;

。。

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

$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+=8) {
        $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;
}

。。

任何人都知道我可能做错了什么或者我怎么能做到最好？

抄袭工具唯一性检测

0 个答案: