app.py

from youtube_transcript_api import YouTubeTranscriptApi
from urllib.parse import urlparse, parse_qs
from transformers import pipeline
import gradio as gr

# 1. Helper: extract ID
def get_video_id(url):
    parsed = urlparse(url)
    if parsed.hostname == "youtu.be":
        return parsed.path[1:]
    elif parsed.hostname in ["www.youtube.com", "youtube.com"]:
        if parsed.path == "/watch":
            return parse_qs(parsed.query)["v"][0]
        elif parsed.path.startswith("/embed/") or parsed.path.startswith("/v/"):
            return parsed.path.split("/")[2]
    raise ValueError("Invalid YouTube URL")

# 2. Helper: get transcript
def get_transcript(video_id, lang="en"):
    try:
        transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
        transcript = transcript_list.find_transcript([lang])
        lines = transcript.fetch()
        return " ".join([line.text for line in lines])
    except Exception as e:
        return f"Error: {e}"

# 3. Load model
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")

# 4. Summarize in chunks
def local_summarize_text(text, max_chunk_words=400):
    words = text.split()
    chunks = [words[i:i+max_chunk_words] for i in range(0, len(words), max_chunk_words)]
    summaries = []
    for chunk in chunks:
        chunk_text = " ".join(chunk)
        result = summarizer(
            chunk_text,
            max_length=min(130, int(len(chunk_text.split()) * 0.8)),
            min_length=20,
            do_sample=False
        )
        summaries.append(result[0]["summary_text"])
    return "\n\n".join(summaries)

# 5. Gradio interface function
def gradio_summarizer(youtube_url):
    try:
        video_id = get_video_id(youtube_url)
    except Exception as e:
        return f"❌ Error extracting video ID: {e}"

    transcript = get_transcript(video_id)
    if not transcript or transcript.startswith("Error"):
        return f"❌ Failed to fetch transcript. Reason: {transcript}"

    summary = local_summarize_text(transcript)
    return summary

# 6. Launch
iface = gr.Interface(
    fn=gradio_summarizer,
    inputs=gr.Textbox(label="YouTube Video URL"),
    outputs=gr.Textbox(label="Summary"),
    title="YouTube Video Summarizer",
    description="Enter a YouTube link (with subtitles). The app fetches and summarizes the transcript."
)

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