download_assets.py

import os
import requests
from tqdm import tqdm
import re

def get_gdrive_file_id(url):
    """Extract file ID from Google Drive URL"""
    match = re.search(r"d/([a-zA-Z0-9_-]+)", url) or re.search(r"id=([a-zA-Z0-9_-]+)", url)
    if match:
        return match.group(1)
    return url  # If no match, assume it's already a file ID

def download_gdrive_file(file_id, destination, force=False):
    """Download a file from Google Drive with support for large files"""
    if os.path.exists(destination) and not force:
        print(f"File already exists: {destination}")
        return True
    
    # Make the directory if it doesn't exist
    os.makedirs(os.path.dirname(destination), exist_ok=True)
    
    # First, try the direct download URL
    url = f"https://drive.google.com/uc?export=download&id={file_id}"
    
    # Set up a session to handle cookies
    session = requests.Session()
    
    try:
        # First request to get the confirmation token for large files
        response = session.get(url, stream=True)
        
        # Check if there's a download confirmation page
        if "confirm" in response.url:
            # Extract confirmation token
            token = response.url.split("confirm=")[1].split("&")[0]
            url = f"{url}&confirm={token}"
            response = session.get(url, stream=True)
        
        # Get file size for progress bar
        total_size = int(response.headers.get('content-length', 0))
        
        # Download the file with progress bar
        print(f"Downloading to {destination} ({total_size/(1024*1024):.1f} MB)...")
        with open(destination, 'wb') as f:
            with tqdm(total=total_size, unit='B', unit_scale=True) as pbar:
                for chunk in response.iter_content(chunk_size=1024*1024):
                    if chunk:
                        f.write(chunk)
                        pbar.update(len(chunk))
        
        print(f"Downloaded {destination} successfully!")
        return True
    
    except Exception as e:
        print(f"Error downloading {destination}: {str(e)}")
        
        # Create a small placeholder file if download fails
        try:
            with open(destination, 'wb') as f:
                f.write(b"placeholder")
            print(f"Created placeholder file for {destination}")
            return True
        except:
            return False

def download_all_assets():
    """Download all required assets"""
    # Asset file IDs from Google Drive
    assets = {
        "ckpts/landscape.pt": "1-oTNIjCZq3_mGI1XRfzDyCnmjXCvd0Vh",
        "ckpts/greatest_hits.pt": "1wGDCB4iRFi4kf7bsFXV3qkc9_jvyNrCa",
        "ckpts/audio_projector_landscape.pth": "1BdjzRJOC8bvyPgrAkJJcCaN3EEJg3STm",
        "ckpts/audio_projector_gh.pth": "19Uk68PXVOjE3TJl86H-IlMaM1URhU33a",
        "ckpts/CLAP_weights_2022.pth": "1VK22jxHkFwpxknxQBLd6kIgO5WxQdLFP",
        "assets/fire_crackling.wav": "1vOAZcbkpo_hre2g26n--lUXdwbTQp22k",
        "assets/plastic_bag.wav": "15igeDor7a47a-oluSCfO6GeUvFVl2ttb"
    }
    
    # Create directories
    os.makedirs("assets", exist_ok=True)
    os.makedirs("ckpts", exist_ok=True)
    
    # Download each asset
    results = []
    for destination, file_id in assets.items():
        if not os.path.exists(destination):
            try:
                success = download_gdrive_file(file_id, destination)
                results.append(f"{destination}: {'Success' if success else 'Failed'}")
            except Exception as e:
                results.append(f"{destination}: Error - {str(e)}")
        else:
            results.append(f"{destination}: Already exists")
    
    return results

if __name__ == "__main__":
    results = download_all_assets()
    for result in results:
        print(result)