Merge pull request #988 from matrix-org/erikj/ignore_comments_preview

Don't include html comments in description

1 files changed, 2 insertions, 1 deletions

diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py

index 4060593f7f..bdd0e60c5b 100644
--- a/synapse/rest/media/v1/preview_url_resource.py
+++ b/synapse/rest/media/v1/preview_url_resource.py
@@ -345,7 +345,8 @@ class PreviewUrlResource(Resource):
                 # lines)
                 text_nodes = (
                     re.sub(r'\s+', '\n', el.text).strip()
-                    for el in cloned_tree.iter() if el.text
+                    for el in cloned_tree.iter()
+                    if el.text and isinstance(el.tag, basestring)  # Removes comments
                 )
                 og['og:description'] = summarize_paragraphs(text_nodes)