[dev] [commit] r980 - wwwbase/Crawler

automailer at dexonline.ro automailer at dexonline.ro
Mon Sep 9 09:11:56 EEST 2013


Author: alinu
Date: Mon Sep  9 09:11:56 2013
New Revision: 980

Log:


Modified:
   wwwbase/Crawler/Crawler.php

Modified: wwwbase/Crawler/Crawler.php
==============================================================================
--- wwwbase/Crawler/Crawler.php	Sun Sep  8 23:31:54 2013	(r979)
+++ wwwbase/Crawler/Crawler.php	Mon Sep  9 09:11:56 2013	(r980)
@@ -114,16 +114,24 @@
 		$multipleLinesComment = false;
 
 		foreach($this->domainsList as $startUrl) {
+			
+			$startUrl = trim($startUrl);
+
 			//comentarii pe mai multe linii
-			if (substr($startUrl, 0, 3) == '###')
-				$multipleLinesComment ^= $multipleLinesComment;
 
-			if ($multipleLinesComment)
-				continue;
-			//comentarii pe o singura linie
-			if (substr($startUrl,0,1) == '#')
+			if (substr($startUrl, 0, 3) == '###') {
+				//flip bit
+				$multipleLinesComment ^= 1;
+			}
+			
+			//comentarii sau linii goale
+			if ($multipleLinesComment || substr($startUrl,0,1) == '#'
+				|| !$startUrl)
 				continue;
 
+
+			
+
 			//curatam url-ul
 			$this->currentUrl = $this->urlPadding($startUrl);
 			//impartim url-ul pe componente


More information about the Dev mailing list