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)