app.py

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

# Load the summarization model
text_summary = pipeline("summarization", model="Falconsai/text_summarization")

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

def get_youtube_transcript(video_url):
    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)
        return text_transcript
    except Exception as e:
        return f"An error occurred: {e}"

def summarize_youtube_video(url):
    transcript = get_youtube_transcript(url)
    if "An error occurred" in transcript:
        return transcript
    summary = text_summary(transcript, min_length=10, max_length=1000, do_sample=False)
    return summary[0]['summary_text']

# Define the Gradio interface
iface = gr.Interface(
    fn=summarize_youtube_video,
    inputs=gr.Textbox(label="Enter YouTube Video URL", placeholder="e.g. https://www.youtube.com/watch?v=abcdef12345"),
    outputs=gr.Textbox(label="Video Summary"),
    title="YouTube Video Summarizer",
    description="Enter the URL of a YouTube video to get a summary of its transcript."
)

if __name__ == "__main__":
    iface.launch()