README.md

metadata

title: MSDSF25M004_ver2
emoji: 🎬
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 5.23.0
app_file: app.py
pinned: false

Version 2 — Website Scraper + YouTube Transcript Q&A Bot

This Gradio app has two tabs:

1. Tab 1: Website Scraper — Scrape bot-protected websites using Bright Data Web Unlocker and ask questions about the content
2. Tab 2: YouTube Transcript Q&A — Enter a YouTube Video ID to fetch its transcript and ask questions about the video

Features

• Bright Data Web Unlocker for CAPTCHA/bot-protected scraping
• YouTube Transcript API for fetching video transcripts
• Groq Cloud LLM for intelligent Q&A
• Tabbed Gradio interface for easy navigation

Setup

1. Set environment variables (or Secrets on HF Spaces):

   • GROQ_API_KEY — Your Groq Cloud API key
   • BRIGHT_DATA_USERNAME — Your Bright Data username
   • BRIGHT_DATA_PASSWORD — Your Bright Data password

2. Install and run:

   pip install -r requirements.txt
   python app.py