Web scraping publication from a google scholar profile via simplehtmldom PHP - php

Question

I'm trying to scrape publication from a google scholar profile,but i have no idea how to scrape every publication from a profile, i know the maximum publication the profile page can show is 100 per page from this question :
Google Scholar profile scrape PHP
I just want to know how to apply the url to my php code so that i can get every publication from a profile and insert them to a array
I am able to put every publication in a single page to a array with this code:
<?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);
?>
I just want to know how to apply this code to multiple pages to get all publication from a google scholar profile

Answer 1

I found a method that works, first, i create a loop that searches the web page for an indication that the page has no publication to show and inserts the url that contains the publication which i then loop to scrape the publication within the url.
This is the code that i used:
<?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);
?>