top500albums/scripts/download_album_covers.py

#!/usr/bin/env python3
"""
Download album cover images for Top 500 Albums using iTunes Search API
"""

import requests
import csv
import os
import re
import time
import json
from urllib.parse import quote
from urllib.request import urlretrieve

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 = "https://itunes.apple.com/search"
    params = {
        'term': search_term,
        'media': 'music',
        'entity': 'album',
        'limit': 5
    }
    
    try:
        response = requests.get(url, params=params, timeout=10)
        response.raise_for_status()
        data = response.json()
        
        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_album_covers():
    """Main function to download all album covers"""
    
    # Create covers directory
    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_downloaded = 0
    
    # Keep track of what we've processed
    log_file = 'download_log.json'
    processed_albums = {}
    
    # Load existing log if it exists
    if os.path.exists(log_file):
        with open(log_file, 'r') as f:
            processed_albums = json.load(f)
    
    with open(csv_file, 'r', encoding='utf-8') as file:
        csv_reader = csv.DictReader(file)
        
        for row in csv_reader:
            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:03d}_{safe_artist}_{safe_album}.jpg"
            filepath = os.path.join(covers_dir, filename)
            
            # Skip if already downloaded
            if os.path.exists(filepath):
                print(f"✓ Already exists: {rank}. {artist} - {album}")
                albums_downloaded += 1
                continue
            
            # Skip if we've already tried and failed
            album_key = f"{artist}_{album}"
            if album_key in processed_albums and not processed_albums[album_key]:
                print(f"⚠ Previously failed: {rank}. {artist} - {album}")
                continue
            
            print(f"Searching: {rank}. {artist} - {album}")
            
            # Search for artwork
            artwork_url = search_itunes(artist, album)
            
            if artwork_url:
                try:
                    print(f"  Downloading from: {artwork_url}")
                    urlretrieve(artwork_url, filepath)
                    print(f"  ✓ Downloaded: {filename}")
                    albums_found += 1
                    albums_downloaded += 1
                    processed_albums[album_key] = True
                    
                except Exception as e:
                    print(f"  ✗ Download failed: {e}")
                    processed_albums[album_key] = False
            else:
                print(f"  ✗ No artwork found")
                processed_albums[album_key] = False
            
            # Save progress
            with open(log_file, 'w') as f:
                json.dump(processed_albums, f, indent=2)
            
            # Be nice to the API
            time.sleep(0.5)
            
            # Progress update
            if albums_processed % 25 == 0:
                print(f"\nProgress: {albums_processed}/500 processed, {albums_found} found, {albums_downloaded} downloaded\n")
    
    print(f"\nFinal Results:")
    print(f"Albums processed: {albums_processed}")
    print(f"Artwork found: {albums_found}")
    print(f"Total downloaded: {albums_downloaded}")
    print(f"Success rate: {albums_found/albums_processed*100:.1f}%")

def create_missing_report():
    """Create a report of albums without covers"""
    covers_dir = 'covers'
    missing_albums = []
    
    with open('top_500_albums_2023.csv', 'r', encoding='utf-8') as file:
        csv_reader = csv.DictReader(file)
        
        for row in csv_reader:
            rank = row.get('Rank', '').strip()
            artist = row.get('Artist', '').strip()
            album = row.get('Album', '').strip()
            
            safe_artist = sanitize_filename(artist)
            safe_album = sanitize_filename(album)
            filename = f"rank_{rank:03d}_{safe_artist}_{safe_album}.jpg"
            filepath = os.path.join(covers_dir, filename)
            
            if not os.path.exists(filepath):
                missing_albums.append({
                    'rank': rank,
                    'artist': artist,
                    'album': album,
                    'filename': filename
                })
    
    print(f"\nMissing covers: {len(missing_albums)}")
    
    if missing_albums:
        with open('missing_covers.csv', 'w', newline='', encoding='utf-8') as file:
            writer = csv.DictWriter(file, fieldnames=['rank', 'artist', 'album', 'filename'])
            writer.writeheader()
            writer.writerows(missing_albums)
        print("Created missing_covers.csv with list of albums without artwork")

if __name__ == "__main__":
    print("Top 500 Albums Cover Art Downloader")
    print("===================================")
    
    choice = input("Choose option:\n1. Download covers\n2. Create missing report\n3. Both\nEnter choice (1-3): ")
    
    if choice in ['1', '3']:
        download_album_covers()
    
    if choice in ['2', '3']:
        create_missing_report()
    
    print("\nDone!")