From 1b5b4823e97e2ce72ade7054606932755e9d702b Mon Sep 17 00:00:00 2001 From: joshua stein Date: Tue, 3 Dec 2013 16:14:35 -0600 Subject: [PATCH] prevent diffbot from trying to read pdf links --- extras/story_cacher.rb | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/extras/story_cacher.rb b/extras/story_cacher.rb index a546d07..844ca0f 100644 --- a/extras/story_cacher.rb +++ b/extras/story_cacher.rb @@ -11,6 +11,11 @@ class StoryCacher return end + # XXX: diffbot tries to read pdfs as text, so disable for now + if url.to_s.match(/\.pdf$/i) + return nil + end + db_url = "#{DIFFBOT_API_URL}?token=#{@@DIFFBOT_API_KEY}&url=" << CGI.escape(url)