progress with the crawler

crawler/parse.php

@@ -0,0 +1,19 @@
+<?php
+
+require_once('../web/inc/helpers.php');
+
+//loop all files in results folder
+$files = scandir('tmp/results');
+foreach ($files as $file) {
+    if ($file == '.' || $file == '..' || !endsWith($file, '.pdf') || file_exists('tmp/csv/' . $file . '.csv'))
+        continue;
+    $csv = analyze('tmp/results/' . $file);
+    file_put_contents('tmp/csv/' . $file . '.csv', $csv);
+}
+
+
+function analyze($pdf) {
+    $cmd = "java -jar tabula-1.0.5-jar-with-dependencies.jar -f CSV $pdf";
+    $output = shell_exec($cmd);
+    return $output;
+}