From: Antonio Ospite <ao2@ao2.it>
Date: Wed, 1 Jul 2015 11:35:56 +0000 (+0200)
Subject: tweeper.php: strip the leading "www." from hosts
X-Git-Tag: v0.4~22
X-Git-Url: https://git.ao2.it/tweeper.git/commitdiff_plain/032dc6cebadb1bc3e1647dff131a1e99c53019ff

tweeper.php: strip the leading "www." from hosts

This makes tweeper more forgiving when it is passed URLs either with or
without the "www" subdomain for the same host.
---

diff --git a/tweeper.php b/tweeper.php
index 178176d..2444a39 100644
--- a/tweeper.php
+++ b/tweeper.php
@@ -244,7 +244,10 @@ class Tweeper {
       return NULL;
     }
 
-    $xsltProcessor = $this->load_stylesheet($url["host"]);
+    // Strip the leading www. to be more forgiving on input URLs
+    $host = preg_replace('/^www\./', '', $url["host"]);
+
+    $xsltProcessor = $this->load_stylesheet($host);
     if (NULL === $xsltProcessor) {
       return NULL;
     }
@@ -254,7 +257,7 @@ class Tweeper {
       return NULL;
     }
 
-    $xmlDoc = $this->html_to_xml($html, $url["host"]);
+    $xmlDoc = $this->html_to_xml($html, $host);
     if (NULL === $xmlDoc) {
       return NULL;
     }