feat: enhance YouTubeTranscripts component with Data output support (#6113)

* 📝 (youtube_transcripts.py): update description of YouTubeTranscriptsComponent to be more concise and accurate
✨ (youtube_transcripts.py): add new output option 'data_output' to provide transcript along with the source video URL
🔧 (youtube_transcripts.py): add method 'get_data_output' to handle the new 'data_output' output option and return a Data object with transcript, video URL, and error message

* [autofix.ci] apply automated fixes

* 📝 (youtube_transcripts.py): improve documentation for get_data_output method to provide a clear description of the returned data object and its contents
🐛 (youtube_transcripts.py): handle specific exceptions from the youtube_transcript_api library to provide more informative error messages and improve error handling in the get_data_output method

* [autofix.ci] apply automated fixes

* 🐛 (youtube_transcripts.py): handle case where no transcripts are found by updating the error message and returning a default data object
🔧 (youtube_transcripts.py): refactor get_data_output method to use a default data object and combine all transcript parts into a single continuous text

* [autofix.ci] apply automated fixes

* ✨ (test_youtube_transcript_component.py): Add unit tests for YouTubeTranscriptsComponent to test various functionalities such as component initialization, output generation, error handling, and setting translation languages.

* [autofix.ci] apply automated fixes

* ✅ (test_youtube_transcript_component.py): update file_names_mapping fixture to return a non-empty list to properly test different versions of file names mapping in the YouTube transcripts component

* [autofix.ci] apply automated fixes

* 📝 (test_youtube_transcript_component.py): Add docstrings and improve variable names for better readability and maintainability
🔧 (test_youtube_transcript_component.py): Refactor error handling in test methods to use descriptive error messages and improve code readability

* [autofix.ci] apply automated fixes

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

src/backend/base/langflow/components/youtube/youtube_transcripts.py

@@ -5,7 +5,7 @@ from langchain_community.document_loaders.youtube import TranscriptFormat
 
 from langflow.custom import Component
 from langflow.inputs import DropdownInput, IntInput, MultilineInput
-from langflow.schema import DataFrame, Message
+from langflow.schema import Data, DataFrame, Message
 from langflow.template import Output
 
 
@@ -13,7 +13,7 @@ class YouTubeTranscriptsComponent(Component):
     """A component that extracts spoken content from YouTube videos as transcripts."""
 
     display_name: str = "YouTube Transcripts"
-    description: str = "Extracts spoken content from YouTube videos with both DataFrame and text output options."
+    description: str = "Extracts spoken content from YouTube videos with multiple output options."
     icon: str = "YouTube"
     name = "YouTubeTranscripts"
 
@@ -43,6 +43,7 @@ class YouTubeTranscriptsComponent(Component):
     outputs = [
         Output(name="dataframe", display_name="Chunks", method="get_dataframe_output"),
         Output(name="message", display_name="Transcript", method="get_message_output"),
+        Output(name="data_output", display_name="Transcript + Source", method="get_data_output"),
     ]
 
     def _load_transcripts(self, *, as_chunks: bool = True):
@@ -68,6 +69,7 @@ class YouTubeTranscriptsComponent(Component):
                 start_seconds %= 60
                 timestamp = f"{start_minutes:02d}:{start_seconds:02d}"
                 data.append({"timestamp": timestamp, "text": doc.page_content})
+
             return DataFrame(pd.DataFrame(data))
 
         except (youtube_transcript_api.TranscriptsDisabled, youtube_transcript_api.NoTranscriptFound) as exc:
@@ -83,3 +85,32 @@ class YouTubeTranscriptsComponent(Component):
         except (youtube_transcript_api.TranscriptsDisabled, youtube_transcript_api.NoTranscriptFound) as exc:
             error_msg = f"Failed to get YouTube transcripts: {exc!s}"
             return Message(text=error_msg)
+
+    def get_data_output(self) -> Data:
+        """Creates a structured data object with transcript and metadata.
+
+        Returns a Data object containing transcript text, video URL, and any error
+        messages that occurred during processing. The object includes:
+        - 'transcript': continuous text from the entire video (concatenated if multiple parts)
+        - 'video_url': the input YouTube URL
+        - 'error': error message if an exception occurs
+        """
+        default_data = {"transcript": "", "video_url": self.url, "error": None}
+
+        try:
+            transcripts = self._load_transcripts(as_chunks=False)
+            if not transcripts:
+                default_data["error"] = "No transcripts found."
+                return Data(data=default_data)
+
+            # Combine all transcript parts
+            full_transcript = " ".join(doc.page_content for doc in transcripts)
+            return Data(data={"transcript": full_transcript, "video_url": self.url})
+
+        except (
+            youtube_transcript_api.TranscriptsDisabled,
+            youtube_transcript_api.NoTranscriptFound,
+            youtube_transcript_api.CouldNotRetrieveTranscript,
+        ) as exc:
+            default_data["error"] = str(exc)
+            return Data(data=default_data)

src/backend/tests/unit/components/bundles/youtube/test_youtube_transcript_component.py

@@ -0,0 +1,167 @@
+from unittest.mock import Mock, patch
+
+import pytest
+from langflow.components.youtube.youtube_transcripts import YouTubeTranscriptsComponent
+from langflow.schema import Data, DataFrame, Message
+from youtube_transcript_api import NoTranscriptFound, TranscriptsDisabled
+
+from tests.base import ComponentTestBaseWithoutClient
+
+
+class TestYouTubeTranscriptsComponent(ComponentTestBaseWithoutClient):
+    @pytest.fixture
+    def component_class(self):
+        """Return the component class to test."""
+        return YouTubeTranscriptsComponent
+
+    @pytest.fixture
+    def default_kwargs(self):
+        """Return the default kwargs for the component."""
+        return {
+            "url": "https://www.youtube.com/watch?v=test123",
+            "chunk_size_seconds": 60,
+            "translation": "",
+        }
+
+    @pytest.fixture
+    def file_names_mapping(self):
+        """Return the file names mapping for different versions."""
+        return []
+
+    @pytest.fixture
+    def mock_transcript_data(self):
+        """Return mock transcript data for testing."""
+        return [
+            Mock(page_content="First part of the transcript", metadata={"start_seconds": 0}),
+            Mock(page_content="Second part of the transcript", metadata={"start_seconds": 60}),
+        ]
+
+    def test_basic_setup(self, component_class, default_kwargs):
+        """Test basic component initialization."""
+        component = component_class()
+        component.set_attributes(default_kwargs)
+        assert component.url == default_kwargs["url"]
+        assert component.chunk_size_seconds == default_kwargs["chunk_size_seconds"]
+        assert component.translation == default_kwargs["translation"]
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_get_dataframe_output_success(self, mock_loader, component_class, default_kwargs, mock_transcript_data):
+        """Test successful DataFrame output generation."""
+        mock_loader.from_youtube_url.return_value.load.return_value = mock_transcript_data
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+        result = component.get_dataframe_output()
+
+        assert isinstance(result, DataFrame)
+        result_df = result  # More descriptive variable name
+        assert len(result_df) == 2
+        assert list(result_df.columns) == ["timestamp", "text"]
+        assert result_df.iloc[0]["timestamp"] == "00:00"
+        assert result_df.iloc[1]["timestamp"] == "01:00"
+        assert result_df.iloc[0]["text"] == "First part of the transcript"
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_get_message_output_success(self, mock_loader, component_class, default_kwargs, mock_transcript_data):
+        """Test successful Message output generation."""
+        mock_loader.from_youtube_url.return_value.load.return_value = mock_transcript_data
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+        result = component.get_message_output()
+
+        assert isinstance(result, Message)
+        assert result.text == "First part of the transcript"
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_get_data_output_success(self, mock_loader, component_class, default_kwargs, mock_transcript_data):
+        """Test successful Data output generation."""
+        mock_loader.from_youtube_url.return_value.load.return_value = mock_transcript_data
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+        result = component.get_data_output()
+
+        assert isinstance(result, Data)
+        assert result.data["video_url"] == default_kwargs["url"]
+        assert result.data["transcript"] == "First part of the transcript Second part of the transcript"
+        assert "error" not in result.data
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_transcript_disabled_error(self, mock_loader, component_class, default_kwargs):
+        """Test handling of TranscriptsDisabled error."""
+        error_message = "Transcripts are disabled for this video"
+
+        # Mock the load method to raise TranscriptsDisabled
+        def raise_error(*_):  # Use underscore to indicate unused arguments
+            raise TranscriptsDisabled(error_message)
+
+        mock_loader.from_youtube_url.return_value.load.side_effect = raise_error
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+
+        # Test DataFrame output
+        df_result = component.get_dataframe_output()
+        assert isinstance(df_result, DataFrame)
+        assert len(df_result) == 1  # One row for error message
+        assert "error" in df_result.columns
+        assert "Failed to get YouTube transcripts" in df_result["error"][0]
+
+        # Test Message output
+        msg_result = component.get_message_output()
+        assert isinstance(msg_result, Message)
+        assert "Failed to get YouTube transcripts" in msg_result.text
+
+        # Test Data output
+        data_result = component.get_data_output()
+        assert isinstance(data_result, Data)
+        assert "error" in data_result.data
+        assert data_result.data["transcript"] == ""
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_no_transcript_found_error(self, mock_loader, component_class, default_kwargs):
+        """Test handling of NoTranscriptFound error."""
+        video_id = "test123"
+        requested_langs = ["en"]
+        transcript_data = {"en": {"translationLanguages": []}}
+
+        # Mock the load method to raise NoTranscriptFound
+        def raise_error(*_):  # Use underscore to indicate unused arguments
+            raise NoTranscriptFound(video_id, requested_langs, transcript_data)
+
+        mock_loader.from_youtube_url.return_value.load.side_effect = raise_error
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+
+        data_result = component.get_data_output()
+        assert isinstance(data_result, Data)
+        assert "error" in data_result.data
+        assert data_result.data["transcript"] == ""
+
+    def test_translation_setting(self, component_class):
+        """Test setting different translation languages."""
+        component = component_class()
+        test_cases = ["en", "es", "fr", ""]
+
+        for lang in test_cases:
+            component.set_attributes({"url": "https://youtube.com/watch?v=test", "translation": lang})
+            assert component.translation == lang
+
+    @patch("langflow.components.youtube.youtube_transcripts.YoutubeLoader")
+    def test_empty_transcript_handling(self, mock_loader, component_class, default_kwargs):
+        """Test handling of empty transcript response."""
+        mock_loader.from_youtube_url.return_value.load.return_value = []
+
+        component = component_class()
+        component.set_attributes(default_kwargs)
+
+        # Test Data output with empty transcript
+        data_result = component.get_data_output()
+        assert data_result.data["error"] == "No transcripts found."
+        assert data_result.data["transcript"] == ""
+
+        # Test DataFrame output with empty transcript
+        df_result = component.get_dataframe_output()
+        assert len(df_result) == 0