app.py

import re
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import TextFormatter
import torch
import gradio as gr
from transformers import pipeline

# Initialize the model for summarization
text_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", torch_dtype=torch.bfloat16)

# Function to summarize text
def summary(input_text):
    output = text_summary(input_text)
    return output[0]['summary_text']

# Function to extract YouTube video ID from URL
def extract_video_id(url):
    regex = r"(?:youtube\.com\/(?:[^\/\n\s]+\/\S+\/|(?:v|e(?:mbed)?)\/|\S*?[?&]v=)|youtu\.be\/)([a-zA-Z0-9_-]{11})"
    match = re.search(regex, url)
    if match:
        return match.group(1)
    return None

# Function to get YouTube transcript and summary
def get_youtube_transcript(video_url, summarize=True):
    video_id = extract_video_id(video_url)
    if not video_id:
        return "Video ID could not be extracted."

    try:
        transcript = YouTubeTranscriptApi.get_transcript(video_id)

        formatter = TextFormatter()
        text_transcript = formatter.format_transcript(transcript)

        if summarize:
            return summary(text_transcript)
        else:
            return text_transcript

    except Exception as e:
        return f"An error occurred: {e}"

# Define the Gradio interface with customization
def create_gradio_interface():
    with gr.Blocks() as demo:
        gr.Markdown("# YouTube Script Summarizer 🤖")
        gr.Markdown("""
        Enter the video URL, and choose whether you'd like the full Script or just the summary.
        ### Credits:
        Created by **Taizun** – Providing a simple solution for video summarization!
        """)

        # Input for YouTube URL
        video_url_input = gr.Textbox(label="Input YouTube URL", lines=1)

        # Radio button for choosing output type (summary or full transcript)
        output_type = gr.Radio(choices=["Summary", "Full Transcript"], label="Choose Output Type", value="Summary")

        # Output for summarized or full transcript text
        output_text = gr.Textbox(label="Result", lines=6)

        # Submit button
        submit_button = gr.Button("Generate", variant="primary")

        # Define the action for the button press
        submit_button.click(fn=get_youtube_transcript,
                            inputs=[video_url_input, output_type],
                            outputs=[output_text])

    return demo

# Launch the interface with user credit
demo = create_gradio_interface()
demo.launch(share=True)