whisper/yt_dl_harari_lecture.py

#!/usr/bin/env python3
"""
Comprehensive Yuval Noah Harari Lecture Downloader with FFmpeg check
"""

import subprocess
import sys
import os
import platform
from pathlib import Path
import logging

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def check_ffmpeg_installed():
    """Check if ffmpeg is installed"""
    try:
        result = subprocess.run(["ffmpeg", "-version"], 
                              capture_output=True, text=True, timeout=10)
        return result.returncode == 0
    except (subprocess.TimeoutExpired, FileNotFoundError):
        return False

def install_ffmpeg():
    """Install ffmpeg using Homebrew"""
    logger.info("📦 Installing ffmpeg via Homebrew...")
    
    try:
        result = subprocess.run(["brew", "install", "ffmpeg"], 
                              capture_output=True, text=True, timeout=300)
        
        if result.returncode == 0:
            logger.info("✅ ffmpeg installed successfully")
            return True
        else:
            logger.error(f"❌ Failed to install ffmpeg: {result.stderr}")
            logger.info("💡 You can install ffmpeg manually: brew install ffmpeg")
            return False
            
    except (subprocess.TimeoutExpired, FileNotFoundError):
        logger.error("❌ Homebrew not found or installation timed out")
        logger.info("💡 Install Homebrew first: /bin/bash -c \"$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)\"")
        return False

def check_yt_dlp_installed():
    """Check if yt-dlp is already installed"""
    try:
        result = subprocess.run([sys.executable, "-m", "yt_dlp", "--version"], 
                              capture_output=True, text=True, timeout=10)
        return result.returncode == 0
    except (subprocess.TimeoutExpired, FileNotFoundError):
        return False

def install_yt_dlp():
    """Install yt-dlp using pip"""
    logger.info("📦 Installing yt-dlp...")
    
    try:
        result = subprocess.run([
            sys.executable, "-m", "pip", "install", "--upgrade", "yt-dlp"
        ], capture_output=True, text=True, timeout=300)
        
        if result.returncode == 0:
            logger.info("✅ yt-dlp installed successfully")
            return True
        else:
            logger.error(f"❌ Failed to install yt-dlp: {result.stderr}")
            return False
            
    except subprocess.TimeoutExpired:
        logger.error("❌ Installation timed out")
        return False

def download_lecture():
    """Download the Yuval Noah Harari lecture"""
    lecture_url = "https://www.youtube.com/watch?v=0BnZMeFtoAM"
    output_template = "yuval_harari_lecture.%(ext)s"
    
    logger.info("🎧 Downloading Yuval Noah Harari lecture...")
    logger.info(f"📺 URL: {lecture_url}")
    
    try:
        # Download as high-quality MP3
        result = subprocess.run([
            sys.executable, "-m", "yt_dlp",
            "-x",                      # Extract audio
            "--audio-format", "mp3",   # Convert to MP3
            "--audio-quality", "0",    # Best quality
            "--output", output_template,
            "--no-overwrites",         # Don't re-download if file exists
            lecture_url
        ], capture_output=True, text=True, timeout=3600)
        
        if result.returncode == 0:
            logger.info("✅ Download completed successfully!")
            
            # Check for the downloaded file
            if os.path.exists("yuval_harari_lecture.mp3"):
                size_mb = os.path.getsize("yuval_harari_lecture.mp3") / (1024 * 1024)
                logger.info(f"📁 File: yuval_harari_lecture.mp3")
                logger.info(f"📊 Size: {size_mb:.1f} MB")
            return True
        else:
            logger.error(f"❌ Download failed: {result.stderr}")
            return False
            
    except subprocess.TimeoutExpired:
        logger.error("❌ Download timed out")
        return False

def main():
    """Main function to orchestrate the download process"""
    logger.info("=" * 60)
    logger.info("🎓 Yuval Noah Harari Lecture Downloader")
    logger.info("=" * 60)
    
    # Check if ffmpeg is installed
    if not check_ffmpeg_installed():
        logger.warning("⚠️  ffmpeg not found - required for audio conversion")
        if not install_ffmpeg():
            logger.error("❌ Please install ffmpeg manually: brew install ffmpeg")
            return 1
    
    # Check if yt-dlp is installed
    if not check_yt_dlp_installed():
        logger.info("yt-dlp not found, installing...")
        if not install_yt_dlp():
            return 1
    else:
        logger.info("✅ yt-dlp is already installed")
    
    # Download the lecture
    if not download_lecture():
        return 1
    
    logger.info("=" * 60)
    logger.info("🎉 Download process completed!")
    logger.info("💡 You can now use the audio file for transcription with Whisper")
    logger.info("=" * 60)
    
    return 0

if __name__ == "__main__":
    try:
        exit(main())
    except KeyboardInterrupt:
        logger.info("\n⏹️  Operation cancelled by user")
        exit(1)