fix: LinkContentFetcher - when no content retrieved (i.e. request blocked), default to snippet text (#5656)

* When no content retrieved (i.e. request blocked), default to snippet

* Add release note

haystack/nodes/retriever/link_content.py

@@ -200,8 +200,10 @@ class LinkContentFetcher(BaseComponent):
                 logger.debug("%s handler extracted content from %s", handler, url)
 
             extracted_doc["content"] = content
-            document = Document.from_dict(extracted_doc)
-            fetched_documents = self.processor.process(documents=[document]) if self.processor else [document]
+        else:
+            extracted_doc["content"] = extracted_doc.get("snippet_text", "")  # fallback to snippet_text
+        document = Document.from_dict(extracted_doc)
+        fetched_documents = self.processor.process(documents=[document]) if self.processor else [document]
 
         return fetched_documents
 

releasenotes/notes/link-content-include-snippet-if-blocked-53b0e3108f010315.yaml

@@ -0,0 +1,5 @@
+---
+enhancements:
+  - |
+    If LinkContentFetcher encounters a block or receives any response code other than HTTPStatus.OK, return the search
+    engine snippet as content, if it's available.

test/nodes/test_link_content_fetcher.py

@@ -279,7 +279,9 @@ def test_handle_various_response_errors(caplog, mocked_requests, error_code: int
     docs = r.fetch(url=url)
 
     assert f"Couldn't retrieve content from {url}" in caplog.text
-    assert docs == []
+    assert len(docs) == 1
+    assert isinstance(docs[0], Document)
+    assert docs[0].content == ""
 
 
 @pytest.mark.unit