From 782ea61998ebce34e10028ba7b80f1ebd1c19785 Mon Sep 17 00:00:00 2001
From: bookfere <bookfere@gmail.com>
Date: Sat, 11 Nov 2023 15:47:55 +0800
Subject: [PATCH] fix: Identify pages by their type rather than a simple
 keyword. #169

---
 lib/element.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/element.py b/lib/element.py
index 6005561..67618a3 100644
--- a/lib/element.py
+++ b/lib/element.py
@@ -199,7 +199,7 @@ def load_element_patterns(self):
 
     def get_sorted_pages(self):
         return sorted(
-            [page for page in self.pages if 'html' in page.media_type],
+            [p for p in self.pages if isinstance(p.data, etree._Element)],
             key=lambda page: sorted_mixed_keys(page.href))
 
     def get_elements(self):