Question

我正在尝试从Google学者个人资料中抓取出版物，但是我不知道如何从个人资料中抓取每个出版物，我知道个人资料页面可以显示的最大出版物是此问题每页100个：

Google Scholar profile scrape PHP

我只想知道如何将URL应用于我的php代码，以便我可以从配置文件中获取每个出版物并将它们插入到数组中

我可以使用以下代码将每个出版物放在一个页面中：

<?php 
set_time_limit(0);  
include 'simple_html_dom.php';

$data = json_decode(file_get_contents('php://input'),true);
$scholarID =  $data["gScholarID"];
$kodeDosen = $data["kodeDosen"];
$page = 1;
$offset = ($page - 1)* 100;
$cStart = 0+$offset;
$profile = 'https://scholar.google.com/citations?user='.$scholarID.'&hl=en&cstart='.$cStart.'&view_op=list_works&pagesize=100';
$html = file_get_html($profile);
$table = $html->find('#gsc_a_t',0);
$rowData = array();

foreach($table->find('tr.gsc_a_tr') as $row){
    $paperjudul  = $row->find('td.gsc_a_t a', 0)->plaintext;
    $paper['kodeDosen'] = $kodeDosen;
    $paper['judul'] = $paperjudul;
    $cited   = $row->find('td.gsc_a_c', 0)->plaintext;
    if($cited === ''){
        $cited = 0;
    }
    $cited = preg_replace('/[\*]+/', '', $cited);
    $paper['citedBy'] = $cited;
    $paper['namaJurnal']    = $row->find('td.gsc_a_t .gs_gray', 1)->plaintext;
    if($paper['namaJurnal'] === ''){
        $paper['namaJurnal'] = 'n/a';
    }
    $paper['periode']   = $row->find('td.gsc_a_y', 0)->plaintext;
    if($paper['periode'] === ' '){
        $paper['periode'] = 'n/a';
    }
    $paper['status'] = 'Published';
    $rowData[] = $paper;
}

print_r($rowData);


?>

我只想知道如何将此代码应用于多个页面，以从Google学者个人资料中获取所有出版物

Answer 1

我找到了一种有效的方法，首先，我创建了一个循环，该循环在网页上搜索以表明该页面没有要显示的出版物，然后插入包含出版物的url，然后我将其循环以将出版物刮到网址。这是我使用的代码：

<?php 
set_time_limit(0);  
include 'simple_html_dom.php';
include 'connectdb.php';

$scholarID =  $_GET["gScholarID"];
$kodeDosen = $_GET["kodeDosen"];

$page = 1;
$finalPage = false;

$sqlTest = 'INSERT INTO tbl_publikasi(kodeDosen,jenis,namaJurnal,judul,status,tipePublikasi,periode,tahun,citedCount) VALUES ';
$response = array();


while (!$finalPage) {
    $offset = ($page - 1)* 100;
    $cStart = 0+$offset;
    $profile = 'https://scholar.google.com/citations?user='.$scholarID.'&hl=en&cstart='.$cStart.'&view_op=list_works&pagesize=100';
    $html = file_get_html($profile);
    if(is_object($html)){
        $empty = $html->find('td.gsc_a_e',0);
        if($empty){
            $finalPage = true;
            unset($html);
        }
        else{
            $urlArray[] = $profile;
            $page++;
        }
    }
    else{
        $response['success'] = 0;
        $response['message'] = "URL tidak valid ";
    }

}

if($finalPage){
    foreach ($urlArray as $urlPublikasi) {
        $html = file_get_html($urlPublikasi);
        $table = $html->find('#gsc_a_t',0);
        $rowData = array();
        if($table){
            foreach($table->find('tr.gsc_a_tr') as $row){
                $paper['kodeDosen'] = $kodeDosen;
                $paperjudul  = $row->find('td.gsc_a_t a', 0)->plaintext;
                $paper['judul'] = $paperjudul;
                $cited   = $row->find('td.gsc_a_c', 0)->plaintext;
                if($cited === ''){
                    $cited = 0;
                }
                $cited = preg_replace('/[\*]+/', '', $cited);
                $paper['citedBy'] = trim($cited);
                $paper['jenis'] = 'Scholar';
                $paper['namaJurnal']    = $row->find('td.gsc_a_t .gs_gray', 1)->plaintext;
                if($paper['namaJurnal'] === ''){
                    $paper['namaJurnal'] = 'n/a';
                }
                $paper['periode'] = 'n/a';
                $paper['tahun']   = $row->find('td.gsc_a_y', 0)->plaintext;
                if($paper['tahun'] === ' '){
                    $paper['tahun'] = '0000';
                }
                $paper['tipePublikasi'] = 'Scholar'; 
                $paper['status'] = 'Published';
                $rowData[] = $paper;
            }

            foreach ($rowData as $paperValue) {
                $judul = $paperValue['judul'];
                $jenis = $paperValue['jenis'];
                $citedCount = $paperValue['citedBy'];
                $namaJurnal = $paperValue['namaJurnal'];
                $periode = $paperValue['periode'];
                $tahun = $paperValue['tahun'];
                $status = $paperValue['status'];
                $tipePublikasi = $paperValue['tipePublikasi'];
                $sqlTest .= "('".$kodeDosen."','".$jenis."','".$namaJurnal."','".$judul."','".$status."','".$tipePublikasi."','".$periode."','".trim($tahun)."','".$citedCount."'),";

            }
            $query = rtrim($sqlTest, ',');
            $query .= "ON DUPLICATE KEY UPDATE idPublikasi=LAST_INSERT_ID(idPublikasi), kodeDosen = VALUES(kodeDosen), jenis = VALUES(jenis), 
            namaJurnal=VALUES(namaJurnal),status=VALUES(status),
            tipePublikasi = VALUES(tipePublikasi),periode=VALUES(periode),tahun = VALUES(tahun),citedCount = VALUES(citedCount)";
        }
        else{
            $response['success'] = 0;
            $response['message'] = "Tabel Publikasi tidak ditemukan ";
        }

    }



     if (mysqli_query($conn, $query)) {
        $response['success'] = 1;
        $response['message'] = "Array Uploaded Successfully";
     } 
     else {
        $response['success'] = 0;
        $response['message'] = "Array Upload Failed, Alasan : ".mysqli_error($conn);
     }


}
else{
    $response['success'] = 0;
    $response['message'] = "Gagal ditemukan ";
}

echo json_encode($response);




?>

通过simplehtmldom PHP从Google学者个人资料中进行网络抓取发布

1 个答案: