1"""
  2Módulo main.py
  3==============
  4
  5[PT-BR]
  6Ponto de entrada para o sistema de captura de dados Pokémon.
  7
  8Fluxo principal:
  91. Carrega variáveis de configuração do arquivo ``.env`` (START_PAGE, OUTPUT_FILE).
 102. Configura sistema de logging.
 113. Descobre todas as páginas de listagem de Pokémon a partir da página inicial.
 124. Faz o *crawl* de cada página, parseia as tabelas e cria objetos ``Pokemon``.
 135. Exporta o conjunto consolidado para um CSV.
 146. Executa uma análise opcional do CSV gerado.
 15
 16Variáveis de ambiente esperadas (definidas em ``.env``):
 17    START_PAGE   URL da página inicial a ser rastreada.
 18    OUTPUT_FILE  Caminho do arquivo CSV de saída.
 19
 20[EN]
 21Entry point for the Pokémon data capture system.
 22
 23Main flow:
 241. Loads configuration variables from the ``.env`` file (START_PAGE, OUTPUT_FILE).
 252. Sets up the logging system.
 263. Discovers all Pokémon listing pages starting from the initial one.
 274. Crawls each page, parses the tables, and creates ``Pokemon`` objects.
 285. Exports the consolidated data to a CSV file.
 296. Optionally runs an analysis of the generated CSV.
 30
 31Expected environment variables (defined in ``.env``):
 32    START_PAGE   Initial page URL to be crawled.
 33    OUTPUT_FILE  Output CSV file path.
 34
 35Usage:
 36    $ python main.py
 37"""
 38import os
 39import logging
 40from pathlib import Path
 41from dotenv import load_dotenv  # type: ignore
 42
 43from services.pokemon_crawler import PokemonCrawler
 44from services.quests import QuestPokemon
 45from services.logging import setup_logging
 46from services.csv_writer import write_pokemon_csv  # type: ignore
 47from services.csv_analyzer import PokemonCSVAnalyzer
 48
 49# ----------------------------------------------------------------------------
 50# [PT-BR] Carregamento de variáveis de ambiente e preparação de pastas
 51# [EN]   Load environment variables and prepare folders
 52# ----------------------------------------------------------------------------
 53
 54load_dotenv()
 55START_PAGE: str = os.getenv(
 56    "START_PAGE", "https://pokemythology.net/conteudo/pokemon/lista01.htm"
 57)
 58OUTPUT_FILE: str = os.getenv("OUTPUT_FILE", "output/pokemons.csv")
 59Path(OUTPUT_FILE).parent.mkdir(parents=True, exist_ok=True)
 60
 61
 62# ----------------------------------------------------------------------------
 63# [PT-BR] Descobre todas as páginas a partir da página inicial
 64# [EN]   Discover all listing pages from the start page
 65# ----------------------------------------------------------------------------
 66def discover_urls(start_url: str) -> list[str]:
 67    urls = PokemonCrawler.discover_pages(start_url)
 68    if start_url not in urls:
 69        urls.insert(0, start_url)
 70    return urls
 71
 72
 73# ----------------------------------------------------------------------------
 74# [PT-BR] Realiza o crawling de todas as páginas e retorna a lista consolidada
 75# [EN]   Crawls all discovered pages and returns the consolidated list
 76# ----------------------------------------------------------------------------
 77def crawl_all_pages(urls: list[str]) -> list[dict]:
 78    all_pokemons = []
 79    for url in urls:
 80        logging.info("Crawling Pokémon from: %s", url)
 81        print(print(QuestPokemon(url).to_text()))
 82
 83        try:
 84            pokemons = PokemonCrawler(url).crawl()
 85            all_pokemons.extend(pokemons)
 86            print(f"  + {len(pokemons)} Pokémon captured on this page.\n")
 87            logging.info("  + %d Pokémon captured on this page.", len(pokemons))
 88        except Exception:
 89            logging.error("Failed to process %s", url, exc_info=True)
 90    return all_pokemons
 91
 92
 93# ----------------------------------------------------------------------------
 94# [PT-BR] Função principal
 95# [EN]   Main function
 96# ----------------------------------------------------------------------------
 97def main() -> None:
 98    setup_logging()
 99    urls = discover_urls(START_PAGE)
100    print(f"{len(urls)} pages found. Starting capture…")
101
102    all_pokemons = crawl_all_pages(urls)
103
104    if not all_pokemons:
105        logging.warning("No Pokémon captured.")
106        return
107
108    written = write_pokemon_csv(all_pokemons, OUTPUT_FILE)
109    print(f"\n{written} Pokémon exported to '{OUTPUT_FILE}'.")
110
111    PokemonCSVAnalyzer(OUTPUT_FILE).run_full_report()
112
113
114# ----------------------------------------------------------------------------
115# [PT-BR] Execução direta
116# [EN]   Direct execution
117# ----------------------------------------------------------------------------
118if __name__ == "__main__":
119    main()