from __future__ import annotations import argparse import logging from .addons.nuvio_addon import run_nuvio_addon from .config import load_yaml from .crawlers import build_crawler from .database import MovieDatabase from .http import HttpClient from .jellyfin.scan_bot import JellyfinScanBot from .nfo_writer import NfoWriter from .playlist.cleaner import PlaylistCleaner from .playlist.playlist_server import run_playlist_server from .playlist_writer import PlaylistWriter from .remap import SlugRemapper from .strm_writer import StrmWriter from .tmdb_sync import TmdbSync from .utils import setup_logging def load_source_configs(app_config: dict) -> dict[str, dict]: result: dict[str, dict] = {} for item in app_config.get("sources", []): source_config = load_yaml(item["config"]) result[item["name"]] = source_config return result def has_playable_links(movie) -> bool: return any(episode.m3u8_url for server in movie.servers for episode in server.episodes) def crawl_once(config_path: str, only_source: str | None = None, only_slug: str | None = None) -> None: app_config = load_yaml(config_path) setup_logging(app_config.get("logging", {}).get("dir", "logs"), app_config.get("logging", {}).get("level", "INFO")) log = logging.getLogger("moviebot") http = HttpClient(**app_config.get("http", {})) db = MovieDatabase(app_config["database"]["path"]) cleaner = PlaylistCleaner(load_yaml(app_config["cleaner_config"])) db_mounts = app_config.get("db_mounts", {}) playlist_writer = PlaylistWriter(app_config["paths"]["playlists"], http, cleaner, db_mounts.get("playlists", "/m3u8")) strm_writer = StrmWriter(app_config["paths"]["libraries"], app_config["playlist_server"]["public_url"], db_mounts.get("libraries", "/strm")) nfo_writer = NfoWriter(app_config["paths"]["libraries"], db_mounts.get("libraries", "/strm")) max_pages = int(app_config.get("crawl", {}).get("max_pages", 1)) try: for source_name, source_config in load_source_configs(app_config).items(): if only_source and source_name != only_source: continue crawler = build_crawler(source_name, source_config, http) log.info("Crawling source=%s max_pages=%s", source_name, max_pages) slugs = [only_slug] if only_slug else crawler.list_slugs(max_pages) for slug in slugs: try: movie = crawler.fetch_movie(slug) if not has_playable_links(movie): log.info("Skipped movie without m3u8 links source=%s slug=%s title=%s", source_name, slug, movie.title) continue movie_id = db.upsert_movie(movie) movie = db.apply_canonical_movie(movie_id, movie) has_success_episode = False for server in movie.servers: server_id = db.upsert_server(movie_id, movie.source, server) for episode in server.episodes: episode_id = db.upsert_episode(movie_id, server_id, movie.source, episode) row = db.get_episode(episode_id) if row["crawl_status"] == "success" and row["origin_m3u8_url"] == episode.m3u8_url: has_success_episode = True if movie.media_type == "movie" and row["strm_path"]: nfo_writer.write_for_db_strm(movie, row["strm_path"]) log.info( "Skipped unchanged m3u8 source=%s slug=%s episode=%s", source_name, slug, episode.filename, ) continue try: playlist_result = playlist_writer.write(movie, episode.filename, episode.m3u8_url, row["access_key"]) strm_result = strm_writer.write( movie, episode.filename, playlist_result.db_path, row["access_key"], episode.season, episode.episode, ) db.update_episode_files(episode_id, playlist_result.db_path, strm_result.db_path, "success") if movie.media_type == "movie": nfo_writer.write_for_strm(movie, strm_result.file_path) has_success_episode = True except Exception as exc: db.update_episode_files(episode_id, None, None, "failed", str(exc)) log.exception("Episode write failed source=%s slug=%s episode=%s", source_name, slug, episode.filename) if has_success_episode and movie.media_type == "tv": nfo_writer.write(movie) log.info("Crawled movie source=%s slug=%s title=%s", source_name, slug, movie.title) except Exception as exc: db.mark_source_failed(source_name, slug, str(exc)) log.exception("Movie crawl failed source=%s slug=%s", source_name, slug) if app_config.get("jellyfin", {}).get("scan_after_crawl", False): JellyfinScanBot(app_config.get("jellyfin", {}), http).scan() finally: db.close() def main() -> None: parser = argparse.ArgumentParser(description="Modular movie crawler bot") parser.add_argument("command", choices=["crawl", "serve-playlists", "serve-nuvio-addon", "remap-slugs", "sync-tmdb"]) parser.add_argument("--config", default="app.yaml") parser.add_argument("--source") parser.add_argument("--slug") parser.add_argument("--tmdb-id") args = parser.parse_args() if args.command == "crawl": crawl_once(args.config, args.source, args.slug) elif args.command == "serve-playlists": app_config = load_yaml(args.config) setup_logging(app_config.get("logging", {}).get("dir", "logs"), app_config.get("logging", {}).get("level", "INFO")) server = app_config["playlist_server"] run_playlist_server( app_config["paths"].get("content_root", "."), server.get("host", "0.0.0.0"), int(server.get("port", 8000)), app_config["database"]["path"], ) elif args.command == "serve-nuvio-addon": app_config = load_yaml(args.config) setup_logging(app_config.get("logging", {}).get("dir", "logs"), app_config.get("logging", {}).get("level", "INFO")) addon_config = app_config.get("nuvio_addon", {}).copy() addon_config.setdefault("db_path", app_config["database"]["path"]) addon_config.setdefault("content_root", app_config["paths"].get("content_root", ".")) addon_config.setdefault("playlist_mount", app_config.get("db_mounts", {}).get("playlists", "/m3u8")) run_nuvio_addon(addon_config) elif args.command == "remap-slugs": app_config = load_yaml(args.config) setup_logging(app_config.get("logging", {}).get("dir", "logs"), app_config.get("logging", {}).get("level", "INFO")) slug_maps = app_config.get("slug_maps", {}) http = HttpClient(**app_config.get("http", {})) SlugRemapper(app_config, http).run( slug_maps.get("movies", "slug_map_movies.yaml"), slug_maps.get("tvshows", "slug_map_tvshows.yaml"), args.slug, ) elif args.command == "sync-tmdb": app_config = load_yaml(args.config) setup_logging(app_config.get("logging", {}).get("dir", "logs"), app_config.get("logging", {}).get("level", "INFO")) http = HttpClient(**app_config.get("http", {})) TmdbSync(app_config, http).run(args.tmdb_id) if __name__ == "__main__": main()