app.py

import re
import gradio as gr
from youtube_utils import get_youtube_captions, summarize_large_text_with_bart

def extract_video_id(url):
    """
    Extract video ID from YouTube URLs using regular expressions.
    """
    patterns = [
        r'(?:v=|\/)([0-9A-Za-z_-]{11}).*',  # Standard and shortened URLs
        r'(?:embed\/)([0-9A-Za-z_-]{11})',   # Embed URLs
        r'(?:youtu\.be\/)([0-9A-Za-z_-]{11})'  # Shortened URLs
    ]
    for pattern in patterns:
        match = re.search(pattern, url)
        if match:
            return match.group(1)
    return None

def summarize_youtube_video(video_url):
    """
    Summarize YouTube video by extracting captions and applying summarization.
    """
    try:
        # Extract video ID
        video_id = extract_video_id(video_url)
        if not video_id:
            return "Invalid YouTube URL. Please try again.", None
        
        # Fetch captions
        captions = get_youtube_captions(video_id)
        if not captions:
            return "Unable to fetch captions for the video. Ensure the video has subtitles.", None
        
        # Generate summary
        summary = summarize_large_text_with_bart(captions)
        return summary, f"https://www.youtube.com/watch?v={video_id}"
    
    except Exception as e:
        return f"An error occurred: {str(e)}", None

# Gradio Interface
def create_gradio_interface():
    """
    Create and return the Gradio Blocks interface.
    """
    with gr.Blocks(title="YouTube Video Summarizer") as interface:
        gr.Markdown("# 🎥 YouTube Video Summarizer")
        gr.Markdown(
            "Provide a YouTube video URL, and this tool will extract captions and summarize the content using a BART model."
        )
        
        with gr.Row():
            video_url_input = gr.Textbox(
                label="YouTube Video URL", 
                placeholder="Enter the URL of the YouTube video"
            )
            summarize_button = gr.Button("Summarize")
        
        with gr.Row():
            summary_output = gr.Textbox(label="Summary", lines=10, interactive=False)
            video_link_output = gr.Textbox(label="YouTube Video Link", interactive=False)

        summarize_button.click(
            fn=summarize_youtube_video,
            inputs=[video_url_input],
            outputs=[summary_output, video_link_output]
        )

    return interface

# Launch the interface
if __name__ == "__main__":
    interface = create_gradio_interface()
    interface.launch()