From 7097a8ad2ef040bc81a8c5f7ed7cc02e0073eaab Mon Sep 17 00:00:00 2001
From: Antonio Ospite <ao2@ao2.it>
Date: Wed, 1 Jul 2015 13:37:57 +0200
Subject: [PATCH] tweeper.php: support host-specific methods for preprocessing
 the HTML data

Some sites serve mangled HTML code, so a mechanism to clean it up before
loading it as XML is needed.

For instance, facebook.com puts come content inside HTML comments, and
these must be stripped in order to make the content available to the
HTML parser when loading the data into a DOMDocument.
---
 tweeper.php | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tweeper.php b/tweeper.php
index 2444a39..efc0fd6 100644
--- a/tweeper.php
+++ b/tweeper.php
@@ -257,6 +257,11 @@ class Tweeper {
       return NULL;
     }
 
+    $preprocess_html_host_method = 'preprocess_html_' . str_replace(".", "_", $host);
+    if (method_exists($this, $preprocess_html_host_method)) {
+      $html = call_user_func_array(array($this, $preprocess_html_host_method), array($html));
+    }
+
     $xmlDoc = $this->html_to_xml($html, $host);
     if (NULL === $xmlDoc) {
       return NULL;
-- 
2.1.4