main.py

from typing import Union
import re
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import TextFormatter
from transformers import pipeline
from fastapi import FastAPI, Query
from fastapi.staticfiles import StaticFiles
from fastapi.responses import FileResponse

app = FastAPI()

text_summary = pipeline("summarization", model="Falconsai/text_summarization", max_length=12000)


def extract_video_id(url: str) -> Union[str, None]:
    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: str) -> Union[str, None]:
    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_text(text: str) -> str:
    summarized_text = text_summary(text)
    return summarized_text[0]['summary_text']

# Get the input from the frontend
@app.get("/getdata")
def get_data(input: str = Query(..., title="YouTube Video URL")) -> dict:
    
    transcript = get_youtube_transcript(input)
    if transcript:
        summary = summarize_text(transcript)
        return {"summary": summary}
    else:
        return {"error": "Failed to get transcript from the YouTube video."}



app.mount('/', StaticFiles(directory="static", html=True), name="static")


@app.get('/')
def index() -> FileResponse:
    return FileResponse('/app/static/index.html', media_type="text/html")