Merge branch 'main' of https://huggingface.co/spaces/Badro/clip-engine

app.py

@@ -1,133 +1,5 @@
+# Your detailed YouTube analysis app.py content
 import gradio as gr
 from pytube import YouTube
-from textblob import TextBlob
-from transformers import pipeline
-import logging
-import os
-
-# Configure basic logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-
-# Initialize sentiment analysis pipeline (once, to save resources)
-# Using a specific model for potentially better results or if default is too large/slow
-# You might need to adjust the model based on availability and performance on HF Spaces free tier
-SENTIMENT_MODEL_NAME = "distilbert-base-uncased-finetuned-sst-2-english"
-sentiment_analyzer = None
-try:
-    logging.info(f"Attempting to load sentiment analysis pipeline: {SENTIMENT_MODEL_NAME}...")
-    # Specify a cache directory within the Space's writable area if needed
-    # cache_dir = "/data/.cache/huggingface/transformers" # Example for some HF environments
-    # os.makedirs(cache_dir, exist_ok=True)
-    sentiment_analyzer = pipeline("sentiment-analysis", model=SENTIMENT_MODEL_NAME) #, cache_dir=cache_dir)
-    logging.info(f"Sentiment analysis pipeline '{SENTIMENT_MODEL_NAME}' loaded successfully.")
-except Exception as e:
-    logging.warning(f"Failed to load {SENTIMENT_MODEL_NAME}: {e}. Falling back to default sentiment model.")
-    try:
-        sentiment_analyzer = pipeline("sentiment-analysis") #, cache_dir=cache_dir)
-        logging.info("Default sentiment analysis pipeline loaded successfully.")
-    except Exception as e_default:
-        logging.error(f"Failed to load default sentiment analysis pipeline: {e_default}")
-        # sentiment_analyzer will remain None
-
-
-def analyze_youtube_content(youtube_url: str = "", transcript_text: str = "") -> dict:
-    """
-    Analyzes YouTube video content.
-    If a YouTube URL is provided, it attempts to fetch video information (e.g., title, views, length).
-    If transcript text is provided, it performs sentiment analysis on the text using
-    TextBlob and a Hugging Face transformer model.
-
-    Args:
-        youtube_url (str, optional): The URL of the YouTube video. Defaults to "".
-        transcript_text (str, optional): The transcript text of the video. Defaults to "".
-
-    Returns:
-        dict: A dictionary containing analysis results.
-              Includes 'video_info' if URL is processed and 'sentiment_analysis' if transcript is processed.
-    """
-    results = {}
-    logging.info(f"Tool 'analyze_youtube_content' called with URL: '{youtube_url}', Transcript provided: {bool(transcript_text)}")
-
-    if not youtube_url and not transcript_text:
-        logging.warning("No YouTube URL or transcript text provided.")
-        return {"error": "No YouTube URL or transcript text provided for analysis."}
-
-    if youtube_url:
-        try:
-            yt = YouTube(youtube_url)
-            results["video_info"] = {
-                "title": yt.title,
-                "views": yt.views,
-                "length_seconds": yt.length,
-                "publish_date": yt.publish_date.strftime('%Y-%m-%d') if yt.publish_date else None,
-                "status": "success"
-            }
-            logging.info(f"Successfully fetched info for video: {yt.title}")
-        except Exception as e:
-            logging.error(f"Error fetching video info from URL '{youtube_url}': {e}")
-            results["video_info"] = {
-                "status": "error",
-                "message": f"Could not fetch video info: {str(e)}"
-            }
-
-    if transcript_text:
-        analysis_data = {}
-        # TextBlob sentiment
-        try:
-            blob = TextBlob(transcript_text)
-            tb_sentiment = blob.sentiment
-            analysis_data["textblob"] = {
-                "polarity": round(tb_sentiment.polarity, 3),
-                "subjectivity": round(tb_sentiment.subjectivity, 3),
-                "assessment": "positive" if tb_sentiment.polarity > 0.05 else "negative" if tb_sentiment.polarity < -0.05 else "neutral"
-            }
-            logging.info("TextBlob sentiment analysis complete.")
-        except Exception as e:
-            logging.error(f"Error during TextBlob sentiment analysis: {e}")
-            analysis_data["textblob"] = {"error": str(e)}
-
-        # Hugging Face sentiment
-        if sentiment_analyzer:
-            try:
-                # Truncate for performance and model limits (default for many models is 512 tokens)
-                max_length_chars = 1000 # Heuristic, actual token limit is what matters
-                truncated_text = transcript_text[:max_length_chars]
-                hf_result = sentiment_analyzer(truncated_text)[0]
-                analysis_data["huggingface_transformer"] = {
-                    "label": hf_result["label"],
-                    "score": round(hf_result["score"], 3)
-                }
-                if len(transcript_text) > max_length_chars:
-                    analysis_data["huggingface_transformer"]["note"] = f"Analyzed approximately the first {max_length_chars} characters of the transcript."
-                logging.info("Hugging Face transformer sentiment analysis complete.")
-            except Exception as e:
-                logging.error(f"Error during Hugging Face sentiment analysis: {e}")
-                analysis_data["huggingface_transformer"] = {"error": str(e)}
-        else:
-            analysis_data["huggingface_transformer"] = {"error": "Hugging Face sentiment analyzer not loaded."}
-            logging.warning("Hugging Face sentiment analyzer was not available for analysis.")
-
-        results["sentiment_analysis"] = analysis_data
-
-    if not results:
-         return {"status": "No analysis performed, though input was provided. Check logs."}
-
-    return results
-
-# Create Gradio interface for the tool.
-youtube_tool_interface = gr.Interface(
-    fn=analyze_youtube_content,
-    inputs=[
-        gr.Textbox(label="YouTube Video URL (Optional)", placeholder="Enter YouTube video URL..."),
-        gr.Textbox(label="Video Transcript Text (Optional)", placeholder="Paste video transcript here...", lines=5)
-    ],
-    outputs=gr.JSON(label="Analysis Result"),
-    title="YouTube Content Analyzer Tool",
-    description="Provides information and sentiment analysis for a YouTube video URL or its transcript. (For Agent Use via MCP)"
-)
-
-# Launch the Gradio app with the MCP server enabled.
-if __name__ == "__main__":
-    logging.info("Launching Gradio app with MCP server enabled for the YouTube Content Analyzer Tool...")
-    # The `mcp_server=True` flag is crucial for the agent to connect and use the tool.
-    youtube_tool_interface.launch(mcp_server=True)
+# ... more of your code ...
+youtube_tool_interface.launch(mcp_server=True)