sometimes extract_text can't get text

2012-05-16 14:36:01 -04:00 · 2012-05-16 14:36:01 -04:00 · dfb556a49f
commit dfb556a49f
parent 1d441a8f86
1 changed files with 3 additions and 0 deletions
--- a/oyster/ext/elasticsearch.py
+++ b/oyster/ext/elasticsearch.py
@ -18,6 +18,9 @@ class ElasticSearchPush(Task):

        try:
            text = kernel.extract_text(doc)
+            if not text:
+                self.log.info('no text for %s', doc_id,
+                              extra={'doc_class':doc['doc_class']})

            self.log.info('tracked %s', doc_id,
                          extra={'doc_class':doc['doc_class']})