import os import sys import shutil import logging from datetime import date import requests import markdown from jinja2 import Environment, FileSystemLoader # Assuming these are in the same directory or Python path from import_helpers import music_data, ExtensionAlbum, ExtensionSong, ExtensionReview from audio_downloader import process_html_files from markdown_extensions import AudioExtension # Constants specific to music generation CURRENT_DIR = os.path.dirname(os.path.abspath(__file__)) SOURCE_ASSETS_DIR = os.path.join(CURRENT_DIR, "assets") SOURCE_COVER_DIR = os.path.join(SOURCE_ASSETS_DIR, "album_covers") SOURCE_AUDIO_DIR = os.path.join(SOURCE_ASSETS_DIR, "audio") # The relative path used in HTML *remains* the same, pointing within assets OUTPUT_AUDIO_SUBDIR = "/assets/audio" TARGET_ALBUM_IDS = [ "OLAK5uy_nLmxB70YJBLEThZljF4v1xhhSJ2pwB6GA", # spelling "OLAK5uy_lvJG6wOQoiTe_vyGkre-RbZWnd4y5NtXM", # congratulations "OLAK5uy_kMVviQYyPZN-EUsk91z_hZJzCzu1804xg", # imaginal disk "OLAK5uy_kmzoSOa_tCizE-r4sweNz91d9qBv1UCVY", # brat "OLAK5uy_mgDUvSi1yFc9Sr-s1BmCGZKBFGravXSEc", # sinister grift "OLAK5uy_mlZk7kmAEKb8ZQWs-2sxnMmRrANtpXpzU", # 13" "OLAK5uy_mXoi-FuQb9Gw7Mguhdx5F4jltT0L1qOCw", # dsotm "OLAK5uy_mPI0_Yf-l12oLr5cbmu_HorkcRRDYPMfE", # vespertine # Add more album IDs here if needed ] MUSIC_INDEX_MD_PATH = os.path.join(CURRENT_DIR, "md/music_index.md") # --- Helper Functions --- def format_date(date_obj: date) -> str: """Formats a date object into 'Mon DD \'YY' format.""" if not date_obj: return "" return date_obj.strftime("%b '%y") def download_album_cover(album_id: str, album: ExtensionAlbum, cover_dir: str) -> str | None: """Downloads album cover if not already present, returns the local path.""" if not album or not album.thumbnail_url: logging.warning(f"Album {album_id} has no thumbnail URL. Skipping download.") return None local_image_filename = f"{album_id}.jpg" local_image_path = os.path.join(cover_dir, local_image_filename) if os.path.exists(local_image_path): logging.debug(f"Cover already exists for {album_id}: {local_image_path}") return local_image_path logging.info(f"Downloading cover for {album_id} from {album.thumbnail_url}...") try: response = requests.get(album.thumbnail_url, stream=True, timeout=10) response.raise_for_status() with open(local_image_path, 'wb') as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) logging.info(f"Successfully downloaded cover for {album_id} to {local_image_path}") return local_image_path except requests.exceptions.RequestException as e: logging.error(f"Error downloading image {album.thumbnail_url} for album {album_id}: {e}") if os.path.exists(local_image_path): os.remove(local_image_path) return None except Exception as e: logging.error(f"An unexpected error occurred during download for {album_id}: {e}") if os.path.exists(local_image_path): os.remove(local_image_path) return None def render_album_html(album: ExtensionAlbum, artist_str: str, album_reviews_data: list, songs_with_reviews_data: list, output_dir: str, env: Environment, cover_path: str | None) -> dict | None: """Renders the HTML for a single album using the template.""" try: template = env.get_template('templates/album_template.html') except Exception as e: logging.error(f"Error loading album_template.html: {e}") return None html_content = template.render( album=album, artist_str=artist_str, album_reviews=album_reviews_data, songs_with_reviews=songs_with_reviews_data, cover_path=cover_path ) filename = f"{album.id}.html" output_path = os.path.join(output_dir, filename) try: with open(output_path, "w", encoding="utf-8") as f: f.write(html_content) return { "filename": filename, "album_name": album.name, "artist_str": artist_str # Cover path is added later after checking download } except Exception as e: logging.error(f"Error writing HTML to {output_path} for album {album.id}: {e}") return None def generate_index_html(pages_info: list, site_description_html: str, output_dir: str, env: Environment): """Generates the index.html file linking to all album pages.""" # Load the main generic list page template template = env.get_template('templates/list_page_template.html') # Load the template for individual list items item_template = env.get_template('templates/list_templates/music_album_item.html') # Render each list item individually list_items_html = [] for page_data in pages_info: # Ensure cover_path exists, provide placeholder if not (handled in item template now) # page_data['cover_path'] = page_data.get('cover_path') # Or set placeholder here list_items_html.append(item_template.render(page=page_data)) # Render the main index page template with the list of item HTML html_content = template.render( page_title="WU - Music", # Set a specific title for this page site_description_html=site_description_html, list_items_html=list_items_html, # Pass the list of rendered HTML strings should_include_audio_player=True # Explicitly include audio player for music index ) output_path = os.path.join(output_dir, "index.html") try: with open(output_path, "w", encoding="utf-8") as f: f.write(html_content) logging.debug(f"Successfully generated music index.html -> {output_path}") except Exception as e: logging.error(f"Error writing music index.html to {output_path}: {e}") # --- Main Generation Function --- def generate_music_site(output_dir: str, templates_dir: str): """Generates the complete music website section.""" logging.info(f"Starting music site generation process for {len(TARGET_ALBUM_IDS)} target albums...") logging.info(f"Output directory set to: {output_dir}") # Create output directory if it doesn't exist os.makedirs(output_dir, exist_ok=True) # Create source asset directories needed before processing os.makedirs(SOURCE_COVER_DIR, exist_ok=True) os.makedirs(SOURCE_AUDIO_DIR, exist_ok=True) # Ensure this exists for downloads # Set up Jinja2 environment using the provided templates directory jinja_env = Environment(loader=FileSystemLoader(templates_dir)) # --- Data Storage --- albums_data = {} image_paths = {} for album_id in TARGET_ALBUM_IDS: album: ExtensionAlbum = music_data.all_albums.get(album_id) if album: albums_data[album_id] = album else: logging.warning(f"Album data not found for ID: {album_id}. Skipping.") active_album_ids = list(albums_data.keys()) logging.info(f"Found data for {len(active_album_ids)} albums to process.") # --- Step 1: Download Album Covers (if needed) --- logging.info("--- Music Step 1: Checking/Downloading Album Covers ---") for album_id in active_album_ids: album = albums_data[album_id] # Download to the *source* cover directory image_path = download_album_cover(album_id, album, SOURCE_COVER_DIR) image_paths[album_id] = image_path # Store path (or None if failed) # --- Step 2: Generate HTML for each album --- logging.info("--- Music Step 2: Generating Album HTML Pages ---") generated_pages_info = [] for album_id in active_album_ids: album = albums_data[album_id] artist_names = [music_data.artists.get(artist_id).name for artist_id in album.artists if music_data.artists.get(artist_id)] artist_str = ", ".join(artist_names) if artist_names else "Unknown Artist" album_reviews_data = [] album_md_parser = markdown.Markdown(extensions=[AudioExtension(fallback_song_id=None, relative_audio_path=OUTPUT_AUDIO_SUBDIR)]) for review in album.reviews: html_content = album_md_parser.convert(review.markdown) album_reviews_data.append({ "html_text": html_content, "formatted_date": format_date(review.addedOn) }) album_md_parser.reset() songs_with_reviews_data = [] for song_id in album.songIds: song: ExtensionSong = music_data.songs.get(song_id) if song and song.reviews: song_reviews_data = [] song_md_parser = markdown.Markdown(extensions=[AudioExtension(fallback_song_id=song_id, relative_audio_path=OUTPUT_AUDIO_SUBDIR)]) for review in song.reviews: html_content = song_md_parser.convert(review.markdown) song_reviews_data.append({ "html_text": html_content, "formatted_date": format_date(review.addedOn) }) song_md_parser.reset() if song_reviews_data: songs_with_reviews_data.append({ "id": song.id, "name": song.name, "reviews": song_reviews_data }) local_cover_path_relative_to_output = None full_image_path = image_paths.get(album_id) if full_image_path: image_filename = os.path.basename(full_image_path) # Path relative to the *output* directory where the HTML file will be # Assumes 'assets/album_covers' structure within the output dir local_cover_path_relative_to_output = os.path.join("/assets", "album_covers", image_filename) page_info = render_album_html( album=album, artist_str=artist_str, album_reviews_data=album_reviews_data, songs_with_reviews_data=songs_with_reviews_data, output_dir=output_dir, # Use the passed output_dir env=jinja_env, cover_path=local_cover_path_relative_to_output # Pass relative path for template ) if page_info: # Add the relative cover path needed for the index page rendering page_info["cover_path"] = local_cover_path_relative_to_output generated_pages_info.append(page_info) logging.debug(f"Successfully generated HTML for {album.name}") else: logging.error(f"Failed to generate HTML for {album.name} ({album_id})") # --- Step 3: Generate Music Index HTML --- logging.info("--- Music Step 3: Generating Music Index HTML ---") site_description_html = f"

Error: {MUSIC_INDEX_MD_PATH} not found or could not be read.

" if os.path.exists(MUSIC_INDEX_MD_PATH): try: with open(MUSIC_INDEX_MD_PATH, "r", encoding="utf-8") as f: index_md_content = f.read() index_md_parser = markdown.Markdown(extensions=[AudioExtension(fallback_song_id=None, relative_audio_path=OUTPUT_AUDIO_SUBDIR)]) site_description_html = index_md_parser.convert(index_md_content) logging.info(f"Successfully read and converted {MUSIC_INDEX_MD_PATH}") except Exception as e: logging.error(f"Error processing {MUSIC_INDEX_MD_PATH}: {e}") else: logging.warning(f"{MUSIC_INDEX_MD_PATH} not found. Using default description.") if generated_pages_info: generate_index_html(generated_pages_info, site_description_html, output_dir, jinja_env) else: logging.warning("No album pages were generated successfully for music. Index file not created.") # --- Step 4: Download Audio Segments --- logging.info("--- Music Step 4: Processing and Downloading Audio Segments ---") # process_html_files needs the directory containing the HTML files (output_dir) # and the *source* directory where audio should be downloaded. process_html_files(html_dir=output_dir, audio_output_dir=SOURCE_AUDIO_DIR) logging.info("Music site generation process finished.") # Example of how to call this from another script: # if __name__ == "__main__": # # Configure logging if running standalone # log_format = '%(asctime)s - %(name)s - %(levelname)s: %(message)s' # logging.basicConfig(level=logging.INFO, format=log_format, stream=sys.stdout) # logging.getLogger().setLevel(logging.INFO) # logging.getLogger("urllib3").setLevel(logging.WARNING) # # Define paths relative to the *calling* script or CWD # base_output_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "output") # music_output_dir = os.path.join(base_output_dir, "music") # templates_dir = os.path.dirname(os.path.abspath(__file__)) # Assuming templates are here # music_index_md_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "index.md") # Assuming index.md is here # generate_music_site(music_output_dir, templates_dir, music_index_md_path)