app.py

from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled
import re
import torch
import gradio as gr
from transformers import pipeline
#test
# Load the  summarization model
text_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", torch_dtype=torch.float32)

def summary(input_text):
    max_input_length = 1024
    if len(input_text) > max_input_length:
        input_text = input_text[:max_input_length]
    
    try:
        output = text_summary(input_text)
        return output[0]['summary_text']
    except IndexError as e:
        print(f"Error summarizing text: {e}")
        return "Error summarizing text."

# Function to extract video ID from YouTube URL
def get_video_id(url):
    video_id = re.search(r"(?<=v=)[^&#]+", url) or re.search(r"(?<=be/)[^&#]+", url)
    return video_id.group(0) if video_id else None

# Function to fetch transcript with error handling
def fetch_transcript(url):
    video_id = get_video_id(url)
    if not video_id:
        return "Invalid YouTube URL"
    
    try:
        # Fetch the transcript
        transcript = YouTubeTranscriptApi.get_transcript(video_id)
        transcript_text = "\n".join([entry['text'] for entry in transcript])
        return summary(transcript_text)
    except TranscriptsDisabled:
        return "Transcripts are disabled for this video."
    except Exception as e:
        print(f"Error: {e}")
        return "An error occurred while fetching the transcript."

# Close any existing Gradio instances
gr.close_all()

# Create Gradio interface
demo = gr.Interface(
    fn=fetch_transcript,
    inputs=[gr.Textbox(lines=2, label="Input YouTube URL to summarize")],
    outputs=[gr.Textbox(lines=7, label="Summarized Text")],
    title="YouTube Script Summarization",
    theme="soft",
    description="Summarize any YouTube video in seconds! "
)

# Launch app
demo.launch()