Update to make sure we don't drop the html tag when ditching elements

mitechie · mitechie · commit f1a79fb8f87b · 2012-04-17T11:04:36.000-04:00
diff --git a/readability/readability.py b/readability/readability.py
@@ -350,8 +350,9 @@ def remove_unlikely_candidates(self):
             if len(s) < 2:
                 continue
             #self.debug(s)
-            if REGEXES['unlikelyCandidatesRe'].search(s) and (not REGEXES['okMaybeItsACandidateRe'].search(s)) and elem.tag != 'body':
+            if REGEXES['unlikelyCandidatesRe'].search(s) and (not REGEXES['okMaybeItsACandidateRe'].search(s)) and elem.tag not in ['html', 'body']:
                 self.debug("Removing unlikely candidate - %s" % describe(elem))
+                import ipdb; ipdb.set_trace()
                 elem.drop_tree()
 
     def transform_misused_divs_into_paragraphs(self):
