# =====================================================================
# robots.txt — ligadoscampeoes.com
# Estratégia:
#   - Crawlers de busca tradicional: acesso total, crawl-delay sensato.
#   - AI scrapers (treino + RAG): bloqueados por defeito. Política
#     editorial: o conteúdo é nosso, não pasto para LLMs.
#   - Excepção: AI search engines com link-back (Perplexity, Applebot)
#     têm acesso para indexação real-time, mas não para treino.
# =====================================================================

# --- Default: tudo aberto ---
User-agent: *
Allow: /
Disallow: /api/
Disallow: /og/
Disallow: /apostas
Disallow: /notificacoes
Disallow: /favoritos
Disallow: /pesquisa
Disallow: /comparador
Disallow: /confronto-directo/

# --- Crawl-rate sane para os principais ---
User-agent: Googlebot
Crawl-delay: 1

User-agent: Bingbot
Crawl-delay: 1

User-agent: DuckDuckBot
Crawl-delay: 1

User-agent: YandexBot
Crawl-delay: 2

# --- AI scrapers de TREINO: bloqueados ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Bardeen
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

# --- AI search engines com link-back: PERMITIDOS (search real-time) ---
# Perplexity faz "answer engine" com citações. Vale a indexação.
User-agent: PerplexityBot
Allow: /
Disallow: /api/
Disallow: /og/
Crawl-delay: 2

# Apple Search & Spotlight (separado do "Extended" de treino, esse continua bloqueado)
User-agent: Applebot
Allow: /
Disallow: /api/
Disallow: /og/

# --- Sitemaps ---
# /sitemap.xml é o índice master (agrega static + articles + matches/SSR)
Sitemap: https://ligadoscampeoes.com/sitemap.xml
# Sub-sitemaps directos (defesa: para crawlers que não seguem o índice)
Sitemap: https://ligadoscampeoes.com/sitemap-0.xml
Sitemap: https://ligadoscampeoes.com/sitemap-articles.xml
Sitemap: https://ligadoscampeoes.com/sitemap-matches.xml