# Hacé Cuentas — robots.txt
#
# Política 2026 (revisada 2026-05-01):
# Maximizar visibilidad en search ENGINES tradicionales + AI search
# (ChatGPT, Claude, Gemini, Perplexity, etc.). En 2026 el tráfico
# orgánico tradicional cae mientras AI search crece 10x — conviene
# permitir LLMs para ser citados como fuente.
#
# Bloqueamos solo scrapers comerciales sin valor SEO (Bytespider,
# Diffbot, Omgili, etc.) y rutas técnicas internas.

# ──────── Default (todos los bots) ────────
User-agent: *
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

# ──────── Search engines tradicionales ────────
User-agent: Googlebot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: Bingbot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: DuckDuckBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: Applebot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: YandexBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

# ──────── AI / LLM search bots — PERMITIDOS (cambio de política 2026-05-01) ────────
# Razón: aparecer en AI Overviews + ChatGPT + Claude + Perplexity respuestas.
# El tráfico desde AI search convierte 2-27x premium vs organic search.

# OpenAI: GPTBot (training), ChatGPT-User (live citations), OAI-SearchBot (search)
User-agent: GPTBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: ChatGPT-User
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

User-agent: OAI-SearchBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Anthropic: ClaudeBot (training), Claude-Web (research mode), anthropic-ai (legacy)
User-agent: ClaudeBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: Claude-Web
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

User-agent: anthropic-ai
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Google Gemini (separado de Googlebot — opt-in explícito para AI training)
User-agent: Google-Extended
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

# Perplexity (search engine basado en LLMs, alta conversión)
User-agent: PerplexityBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

User-agent: Perplexity-User
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Apple Intelligence (Siri, Apple Search)
User-agent: Applebot-Extended
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Common Crawl — base de training data de muchos LLMs públicos (Llama, Mistral, etc.)
User-agent: CCBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Meta (Llama models)
User-agent: Meta-ExternalAgent
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

User-agent: FacebookBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# You.com
User-agent: YouBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Amazon (Amazon Q + Alexa AI — ahora cita fuentes y manda tráfico,
# revisado 2026-05-13: mismo tratamiento que GPTBot / ClaudeBot)
User-agent: Amazonbot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/
Disallow: /embed/
Disallow: /embed.js
Disallow: /search-index.json

# ──────── Search engines regionales (LATAM-relevant via diaspora + viajes) ────────

# Naver (Corea — usa búsqueda propia, no Bing)
User-agent: Yeti
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Seznam.cz (Chequia — buscador propio top en CZ)
User-agent: SeznamBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Google adicional bots (AdsBot, Mobile, etc)
User-agent: GoogleOther
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Huawei Petal Search (mercados emergentes)
User-agent: PetalBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Mojeek (independent search engine, privacy-focused — usa crawler propio)
User-agent: MojeekBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Sogou (Tencent search — usuarios chinos en LATAM)
User-agent: Sogou web spider
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Exalead (Dassault Systèmes, used in France/EU)
User-agent: Exabot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# ──────── AI search emergentes 2026 ────────

# Yep (Ahrefs new search engine, 2024+)
User-agent: YepBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Phind (dev-focused AI search)
User-agent: PhindBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Andi (conversational AI search)
User-agent: Andibot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Komo AI
User-agent: KomoBot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Qwant (Francia — independent EU search)
User-agent: Qwantify
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Marginalia Search (independent, slow web)
User-agent: search.marginalia.nu
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# Stract (open source search engine)
User-agent: stractbot
Allow: /
Allow: /api/calcs-index.json
Allow: /api/calc/
Disallow: /admin
Disallow: /api/

# ──────── Bloqueados: scrapers comerciales sin valor SEO ────────
# Estos no traen tráfico ni mejoran AI visibility — solo consumen ancho de banda.

# Bytespider (TikTok/ByteDance scraper — no agrega tráfico, opaco)
User-agent: Bytespider
Disallow: /

# Diffbot (commercial data scraper)
User-agent: Diffbot
Disallow: /

# ImagesiftBot (image scraping comercial)
User-agent: ImagesiftBot
Disallow: /

# Omgili / Omgilibot (scraping for sale, no valor SEO)
User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

# Timpibot (AI scraper poco transparente)
User-agent: Timpibot
Disallow: /

# Cohere (no es buscador público, training-only)
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# Mistral (Le Chat — buscador IA público con citación). Permitido explícitamente
# (paridad con .well-known/llms-allowed.txt).
User-agent: MistralAI-User
Allow: /

# ──────── Sitemap ────────
# Index principal (Google sigue los sub-sitemaps automáticamente vía sitemap index).
Sitemap: https://hacecuentas.com/sitemap.xml
# Sitemap-fresh: URLs modificadas en últimos 14 días — Bing/Yandex freshness
Sitemap: https://hacecuentas.com/sitemap-fresh.xml
# RSS feed: discovery alternativo para Yandex/Seznam/Naver y AI engines (Claude/Perplexity)
# que parsean RSS para detectar contenido nuevo. Google lo ignora silenciosamente
# (acepta solo XML sitemaps válidos) — cero impacto en crawl budget de Google.
Sitemap: https://hacecuentas.com/rss.xml
# Sub-sitemaps geo + idioma declarados explícitamente: Bing y otros crawlers
# que no auto-procesan sitemap-index los descubren acá directo. Resuelve el
# warning "Important pages missing in sitemaps" de BWT (2026-05-25).
Sitemap: https://hacecuentas.com/sitemap-co.xml
Sitemap: https://hacecuentas.com/sitemap-cl.xml
Sitemap: https://hacecuentas.com/sitemap-mx.xml
Sitemap: https://hacecuentas.com/sitemap-es.xml
Sitemap: https://hacecuentas.com/sitemap-en.xml
Sitemap: https://hacecuentas.com/sitemap-pt.xml
Sitemap: https://hacecuentas.com/sitemap-argentina.xml
Sitemap: https://hacecuentas.com/sitemap-iibb.xml