예제 #1
0
                     foreach ($curlList as $outfile => $curlEl) {
                         //	exec("mkdir \"".dirname($outfile)."\\\"");
                         file_put_contents($outfile, curl_multi_getcontent($curlEl));
                         curl_multi_remove_handle($curlHandle, $curlEl);
                     }
                     curl_multi_close($curlHandle);
                     $n = 0;
                     $curlList = array();
                 }
             }
             echo "\n";
             flush();
         }
         // the last call
         if ($curlList) {
             Crawler::execHandle($curlHandle);
             foreach ($curlList as $outfile => $curlEl) {
                 //	exec("mkdir \"".dirname($outfile)."\\\"");
                 file_put_contents($outfile, curl_multi_getcontent($curlEl));
                 curl_multi_remove_handle($curlHandle, $curlEl);
             }
             curl_multi_close($curlHandle);
         }
     }
     break;
 case 'phase4':
     // folder yg -original$ dan -reprint$ digabung jdai satu
     // filenamenya diprefix ^original- dan ^reprint-
     $dirname = 'Carl Barks';
     $subdirs = scandir($dirname);
     $n = count($subdirs);
예제 #2
0
 /**
  * Mendownload $size buah link sekaligus, lalu diproses oleh fungsi $function
  * @param integer $size jumlah thread yg diinginkan
  * @param array   $pages_url array of full url
  * @param string  $function nama fungsi yang dipanggil untuk memproses 1 halaman,
  *                  fungsinya punya 2 parameter (resource $fil, string $url)
  * @param array   $params parameter tambahan ke fungsi
  */
 public static function multiProcess($size, $pages_url, $function, $params = false)
 {
     $n = 0;
     $curlHandle = null;
     $curlList = array();
     foreach ($pages_url as $aurl) {
         if ($n == 0) {
             $curlHandle = curl_multi_init();
         }
         $curlList[$aurl] = Crawler::addHandle($curlHandle, $aurl);
         $n++;
         if ($n >= $size) {
             Crawler::execHandle($curlHandle);
             foreach ($curlList as $theurl => $curlEl) {
                 $html = curl_multi_getcontent($curlEl);
                 // Ada kemungkinan gagal retrieve
                 if (trim($html)) {
                     $fil = tmpfile();
                     fwrite($fil, $html);
                 } else {
                     $fil = $theurl;
                 }
                 if ($params) {
                     call_user_func_array($function, array_merge(array($fil, $theurl), $params));
                 } else {
                     $function($fil, $theurl);
                 }
                 curl_multi_remove_handle($curlHandle, $curlEl);
             }
             curl_multi_close($curlHandle);
             $n = 0;
             $curlList = array();
         }
     }
     if ($curlList) {
         Crawler::execHandle($curlHandle);
         foreach ($curlList as $theurl => $curlEl) {
             $html = curl_multi_getcontent($curlEl);
             // Ada kemungkinan gagal retrieve
             if (trim($html)) {
                 $fil = tmpfile();
                 fwrite($fil, $html);
             } else {
                 $fil = $theurl;
             }
             if ($params) {
                 call_user_func_array($function, array_merge(array($fil, $theurl), $params));
             } else {
                 $function($fil, $theurl);
             }
             curl_multi_remove_handle($curlHandle, $curlEl);
         }
         curl_multi_close($curlHandle);
     }
 }