Aggiunta e documentata modalità debug

config.example.php

@@ -20,5 +20,8 @@ $allowedMimetypes = [
     'application/pdf' => 'pdf'
 ];
 
+// Specifica se visualizzare le URL scansionate
+$debug = true;
+
 // Directory dove salvare i file trovati
 $download_dir = __DIR__.'/pdf';

example/README.md

@@ -22,4 +22,6 @@ Inserendo negli `$start_url` l'indirizzo sopra e avviando lo script, dovreste tr
 [2] http://localhost/example/pagina2/sub2.3
 [3] http://localhost/example/pagina1/sub1.1/subsub1.1.1
 [3] http://localhost/example/pagina1/sub1.1/subsub1.1.2
+[3] http://localhost/example/pagina1/sub1.1/test.pdf
+[*] Downloading test.pdf
 ```

scrape.php

@@ -18,6 +18,7 @@ $scraper = new Scraper();
 // Configure object
 $scraper->allowedMimetypes = $allowedMimetypes;
 $scraper->link_rules = $link_rules;
+$scraper->debug = $debug;
 
 $scraper->scrape($start_urls, 0);
 

src/Scraping/Scraper.php

@@ -9,6 +9,7 @@ class Scraper
     public $results = [];
     public $allowedMimetypes;
     public $link_rules;
+    public $debug = false;
 
     /**
      * Scrapes specified URLs
@@ -24,8 +25,8 @@ class Scraper
         foreach ($urls as $url) {
             $crawler = $client->request('GET', $url);
 
-            if( $url == 'http://localhost/example/pagina1/sub1.1/test.pdf' ){
-                $a = 1;
+            if ($this->debug) {
+                print '['.$level.'] '.$url."\n";
             }
 
             $scraped_obj[$url]['content-type'] = $this->getContentType($client);