diff --git a/oml/media/pdf.py b/oml/media/pdf.py
index f32460b..f23f309 100644
--- a/oml/media/pdf.py
+++ b/oml/media/pdf.py
@@ -210,6 +210,8 @@ def info(pdf):
         data['date'] = '%s-%s-%s' % (d[:4], d[4:6], d[6:])
     if 'author' in data and isinstance(data['author'], str):
         data['author'] = [ox.normalize_name(data['author'])]
+    if 'description' in data:
+        data['description'] = ox.strip_tags(ox.decode_html(data['description'])).strip()
     return data
 
 '''