diff --git a/engines/misc/src/main/java/org/alfresco/transform/misc/transformers/HtmlParserContentTransformer.java b/engines/misc/src/main/java/org/alfresco/transform/misc/transformers/HtmlParserContentTransformer.java
index 46bee139..970670a5 100644
--- a/engines/misc/src/main/java/org/alfresco/transform/misc/transformers/HtmlParserContentTransformer.java
+++ b/engines/misc/src/main/java/org/alfresco/transform/misc/transformers/HtmlParserContentTransformer.java
@@ -101,7 +101,7 @@ public class HtmlParserContentTransformer implements CustomTransformerFileAdapto
 
         // Create the extractor
         EncodingAwareStringBean extractor = new EncodingAwareStringBean();
-        extractor.setCollapse(false);
+        extractor.setCollapse(true);
         extractor.setLinks(false);
         extractor.setReplaceNonBreakingSpaces(false);
         extractor.setURL(sourceFile, sourceEncoding);