top500albums/download_missing_covers.py

#!/usr/bin/env python3
"""
Download album covers for albums that don't have covers yet
"""

import urllib.request
import urllib.parse
import json
import csv
import os
import re
import time

def sanitize_filename(text):
    """Remove or replace characters that aren't valid in filenames"""
    # Remove/replace problematic characters
    text = re.sub(r'[<>:"/\\|?*]', '', text)
    text = re.sub(r'[^\w\s\-_\.]', '', text)
    text = re.sub(r'\s+', '_', text.strip())
    return text[:100]  # Limit length

def search_itunes(artist, album):
    """Search iTunes API for album artwork"""
    # Clean up search terms
    search_term = f"{artist} {album}".strip()
    search_term = re.sub(r'\([^)]*\)', '', search_term)  # Remove parentheses content
    search_term = re.sub(r'\s+', ' ', search_term).strip()
    
    # URL encode the search term
    encoded_term = urllib.parse.quote(search_term)
    url = f"https://itunes.apple.com/search?term={encoded_term}&media=music&entity=album&limit=5"
    
    try:
        with urllib.request.urlopen(url, timeout=15) as response:
            data = json.loads(response.read().decode())
        
        if data['resultCount'] > 0:
            # Try to find the best match
            for result in data['results']:
                result_artist = result.get('artistName', '').lower()
                result_album = result.get('collectionName', '').lower()
                
                # Simple matching - check if artist and album names are similar
                if (artist.lower() in result_artist or result_artist in artist.lower()) and \
                   (album.lower() in result_album or result_album in album.lower()):
                    artwork_url = result.get('artworkUrl100', '').replace('100x100', '600x600')
                    return artwork_url
            
            # If no exact match, return the first result
            first_result = data['results'][0]
            artwork_url = first_result.get('artworkUrl100', '').replace('100x100', '600x600')
            return artwork_url
            
    except Exception as e:
        print(f"Error searching for {artist} - {album}: {e}")
        return None
    
    return None

def download_missing_covers():
    """Download covers for albums that don't have covers yet"""
    
    # Create covers directory if it doesn't exist
    covers_dir = 'covers'
    if not os.path.exists(covers_dir):
        os.makedirs(covers_dir)
    
    # Read the CSV file
    csv_file = 'top_500_albums_2023.csv'
    if not os.path.exists(csv_file):
        print(f"Error: {csv_file} not found!")
        return
    
    albums_processed = 0
    albums_found = 0
    albums_skipped = 0
    failed_albums = []
    
    print("Downloading covers for albums without covers...")
    print("This will take a while to be respectful to the iTunes API...\\n")
    
    with open(csv_file, 'r', encoding='utf-8') as file:
        csv_reader = csv.DictReader(file)
        
        # Convert to list and sort by rank
        rows = list(csv_reader)
        rows.sort(key=lambda x: int(x.get('Rank', 999)))
        
        for i, row in enumerate(rows):
            rank = row.get('Rank', '').strip()
            artist = row.get('Artist', '').strip()
            album = row.get('Album', '').strip()
            
            if not artist or not album:
                continue
            
            albums_processed += 1
            
            # Create filename
            safe_artist = sanitize_filename(artist)
            safe_album = sanitize_filename(album)
            filename = f"rank_{rank.zfill(3)}_{safe_artist}_{safe_album}.jpg"
            filepath = os.path.join(covers_dir, filename)
            
            # Skip if already exists
            if os.path.exists(filepath):
                albums_skipped += 1
                continue
            
            print(f"Searching [{albums_processed - albums_skipped}/500]: {rank}. {artist} - {album}")
            
            # Search for artwork
            artwork_url = search_itunes(artist, album)
            
            if artwork_url:
                try:
                    print(f"  Downloading from: {artwork_url}")
                    urllib.request.urlretrieve(artwork_url, filepath)
                    print(f"  ✓ Downloaded: {filename}")
                    albums_found += 1
                    
                except Exception as e:
                    print(f"  ✗ Download failed: {e}")
                    failed_albums.append(f"{rank}. {artist} - {album}")
            else:
                print(f"  ✗ No artwork found")
                failed_albums.append(f"{rank}. {artist} - {album}")
            
            # Be nice to the API
            time.sleep(1.2)
            
            # Progress update every 25 new downloads
            if albums_found % 25 == 0 and albums_found > 0:
                print(f"\\n--- Progress Update ---")
                print(f"New downloads: {albums_found}")
                print(f"Already existed: {albums_skipped}")
                print(f"Failed: {len(failed_albums)}")
                print("----------------------\\n")
    
    print(f"\\n🎉 FINAL RESULTS:")
    print(f"Albums processed: {albums_processed}")
    print(f"Already existed: {albums_skipped}")
    print(f"New downloads: {albums_found}")
    print(f"Failed to find: {len(failed_albums)}")
    print(f"Total covers available: {albums_found + albums_skipped}")
    print(f"Overall success rate: {(albums_found + albums_skipped)/albums_processed*100:.1f}%")
    
    if failed_albums:
        print(f"\\n❌ Failed albums ({len(failed_albums)}):")
        for album in failed_albums[:10]:  # Show first 10
            print(f"  {album}")
        if len(failed_albums) > 10:
            print(f"  ... and {len(failed_albums) - 10} more")
        
        # Save failed albums to file
        with open('failed_downloads.txt', 'w') as f:
            for album in failed_albums:
                f.write(f"{album}\\n")
        print(f"\\nFull list saved to failed_downloads.txt")

if __name__ == "__main__":
    download_missing_covers()