Add pyquery path setting.

docs/settings.rst

@@ -51,4 +51,14 @@ The password to use when connecting to the Read the Docs API. Used for hitting t
 INDEX_ONLY_LATEST
 -----------------
 
+Default: `False`
+
 In search, only index the `latest` version of a Project. 
+
+DOCUMENT_PYQUERY_PATH
+---------------------
+
+Default: `div.document`
+
+The Pyquery path to an HTML element that is the root of your document. 
+This is used for making sure we are only searching the main content of a document.

readthedocs/projects/search_indexes.py

@@ -72,6 +72,7 @@ class ImportedFileIndex(indexes.SearchIndex, indexes.Indexable):
             log.info('Unable to index file: %s, error :%s' % (file_path, e))
             return
         log.debug('Indexing %s:%s' % (obj.project, obj.path))
+        DOCUMENT_PYQUERY_PATH = getattr(settings, 'DOCUMENT_PYQUERY_PATH', 'div.document')
         try:
             to_index = strip_tags(PyQuery(content)("div.document").html()).replace(u'¶', '')
         except ValueError: