# Robots.txt otimizado para SEO - Falcon Apps
# Última atualização: 2026-01-02

# === GOOGLE E BUSCADORES PRINCIPAIS ===
# Permitir acesso total para buscadores confiáveis
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-Mobile
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: YandexBot
Allow: /
Disallow: /api/
Disallow: /_next/static/
Disallow: /_next/image/
Crawl-delay: 0

# === BOTS DE ANÁLISE E SEO LEGÍTIMOS ===
# Permitir ferramentas de análise, mas com delay
User-agent: ia_archiver
User-agent: archive.org_bot
Allow: /
Crawl-delay: 2

# === BLOQUEAR BOTS MALICIOSOS E SCRAPERS ===
# Bots que consomem crawl budget sem valor
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: DotBot
User-agent: MJ12bot
User-agent: rogerbot
User-agent: Exabot
User-agent: Nutch
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: PetalBot
User-agent: ZoominfoBot
# === BOTS DE IA (PERMITIDOS) ===
# Permitir indexação por IAs para melhorar visibilidade no ChatGPT, Claude, Gemini, Perplexity, etc.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Applebot-Extended
Allow: /

# === REGRAS GERAIS PARA OUTROS BOTS ===
User-agent: *
Allow: /
# Bloquear diretórios sem valor SEO
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /private/
# Bloquear arquivos técnicos (URLs com query string são permitidas — ex.: UTM, ?q= no blog)
Disallow: /*.json$
Disallow: /search?
Disallow: /*_buildManifest.js$
Disallow: /*_middlewareManifest.js$
Disallow: /*_ssgManifest.js$
# Delay para bots desconhecidos
Crawl-delay: 1

# === PERMITIR RECURSOS ESSENCIAIS ===
# Garantir que CSS, JS e imagens sejam rastreáveis
Allow: /_next/static/css/
Allow: /_next/static/media/
Allow: /public/
Allow: /*.css$
Allow: /*.js$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.png$
Allow: /*.webp$
Allow: /*.svg$
Allow: /*.gif$
Allow: /*.txt$

# === SITEMAP E DOCUMENTAÇÃO PARA IA ===
Sitemap: https://falconapps.org/sitemap.xml

# LLM-friendly documentation (llms.txt standard)
# https://llmstxt.org
# llms.txt: https://falconapps.org/llms.txt
# llms-full.txt: https://falconapps.org/llms-full.txt