# Allow AdMob crawler to find app-ads.txt specifically
User-agent: Google-adstxt
Disallow:

User-agent: Mediapartners-Google
Disallow:

# Googlebot: only index static pages, not the Flutter SPA
User-agent: Googlebot
Allow: /$
Allow: /blog/
Allow: /legal/
Allow: /about/
Allow: /contacto/
Allow: /jugadores/
Allow: /propietarios/
Allow: /administradores/
Allow: /ios/
Allow: /en/$
Allow: /en/blog/
Allow: /en/legal/
Allow: /en/about/
Allow: /en/contact/
Allow: /en/players/
Allow: /en/residents/
Allow: /en/managers/
Allow: /en/ios/
# __US_ALLOW_START__
Allow: /en/athletics-tracks/
Allow: /en/badminton-courts/
Allow: /en/basketball-courts/
Allow: /en/bowling-alleys/
Allow: /en/climbing-gyms/
Allow: /en/community-sports-spaces/
Allow: /en/football-pitches/
Allow: /en/fronton-courts/
Allow: /en/gyms/
Allow: /en/handball-courts/
Allow: /en/hockey-venues/
Allow: /en/leisure-centres/
Allow: /en/martial-arts-gyms/
Allow: /en/padel-courts/
Allow: /en/petanque-courts/
Allow: /en/pickleball-courts/
Allow: /en/shooting-ranges/
Allow: /en/skateparks/
Allow: /en/soccer-fields/
Allow: /en/sports-centers/
Allow: /en/squash-courts/
Allow: /en/swimming-pools/
Allow: /en/table-tennis-venues/
Allow: /en/tennis-courts/
Allow: /en/volleyball-courts/
Allow: /en/water-sports-centers/
Allow: /en/water-sports-centres/
Allow: /sitemap-cities-us.xml
Allow: /sitemap-cities-us/
Allow: /sitemap-venues-us.xml
Allow: /sitemap-venues-us/
Allow: /sitemap-cities-gb.xml
Allow: /sitemap-cities-gb/
Allow: /sitemap-venues-gb.xml
Allow: /sitemap-venues-gb/
Allow: /sitemap-cities-ie.xml
Allow: /sitemap-cities-ie/
Allow: /sitemap-venues-ie.xml
Allow: /sitemap-venues-ie/
# __US_ALLOW_END__
# Carril B2B (venta a gestores: verticales /software-gestion-* y funciones
# /funciones/*, con sus equivalentes /en/ y /fr/). Las líneas entre los
# marcadores las GENERA build-blog.mjs desde workers/seo-worker/src/b2b/registry.js,
# que es la misma fuente de la que salen las páginas y el sitemap: una página
# nueva en el registro se declara aquí sola, y una BLOQUEADA (declarada pero sin
# producto, hoy la piscina) no aparece — anunciar una URL que cae al fallback de
# la SPA es invitar a rastrear un noindex. No editar a mano entre los marcadores.
# __B2B_ALLOW_START__
Allow: /en/features/access-control
Allow: /en/features/classes-and-capacity
Allow: /en/features/club-website
Allow: /en/features/integrations
Allow: /en/features/memberships
Allow: /en/features/online-booking
Allow: /en/features/payments
Allow: /en/gym-management-software
Allow: /en/leisure-centre-management-software
Allow: /en/padel-club-management-software
Allow: /en/sports-academy-management-software
Allow: /en/tennis-club-management-software
Allow: /fr/fonctionnalites/adhesions
Allow: /fr/fonctionnalites/controle-acces
Allow: /fr/fonctionnalites/cours-et-jauge
Allow: /fr/fonctionnalites/integrations
Allow: /fr/fonctionnalites/paiements
Allow: /fr/fonctionnalites/reservations
Allow: /fr/fonctionnalites/site-du-club
Allow: /fr/logiciel-gestion-centre-sportif
Allow: /fr/logiciel-gestion-club-padel
Allow: /fr/logiciel-gestion-club-tennis
Allow: /fr/logiciel-gestion-ecole-de-sport
Allow: /fr/logiciel-gestion-salle-de-sport
Allow: /funciones/clases-y-aforo
Allow: /funciones/cobros
Allow: /funciones/control-de-acceso
Allow: /funciones/integraciones
Allow: /funciones/reservas
Allow: /funciones/socios-y-cuotas
Allow: /funciones/web-del-club
Allow: /software-gestion-club-padel
Allow: /software-gestion-club-tenis
Allow: /software-gestion-escuela-deportiva
Allow: /software-gestion-gimnasio
Allow: /software-gestion-polideportivo
# __B2B_ALLOW_END__
Allow: /sitemap.xml
Allow: /sitemap-pages.xml
Allow: /sitemap-cities.xml
Allow: /sitemap-matches.xml
Allow: /sitemap-venues.xml
Allow: /sitemap-venues/
Allow: /sitemap-clubs.xml
Allow: /og/
Allow: /ads.txt
Allow: /app-ads.txt
# SSR public pages — match/venue/club/hyper-local directory.
Allow: /m/
Allow: /v/
Allow: /c/
Allow: /pistas-padel/
Allow: /pistas-tenis/
Allow: /pistas-baloncesto/
Allow: /pistas-futbol/
Allow: /pistas-voleibol/
Allow: /salas-comunitarias/
Allow: /gimnasios/
Allow: /piscinas/
Allow: /polideportivos/
Allow: /frontones/
Allow: /tenis-de-mesa/
Allow: /pistas-petanca/
Allow: /rocodromos/
Allow: /pistas-atletismo/
Allow: /pistas-squash/
# France (/fr/) tree — static pages + verticals + sitemaps. The lines below the
# marker are GENERATED at build time by build-blog.mjs from the SAME
# shared/sports.json vertical list that feeds the Caddy handles (SEO-FR-A3 /
# CD-1), so a vertical can never get a Caddy handle without its robots Allow.
# Do not hand-edit between the markers.
# __FR_ALLOW_START__
Allow: /fr/$
Allow: /fr/legal/
Allow: /fr/about/
Allow: /fr/contact/
Allow: /fr/joueurs/
Allow: /fr/proprietaires/
Allow: /fr/gestionnaires/
Allow: /fr/ressources/
Allow: /fr/ios/
Allow: /fr/recherche
Allow: /fr/bases-nautiques/
Allow: /fr/bowlings/
Allow: /fr/complexes-sportifs/
Allow: /fr/courts-de-squash/
Allow: /fr/courts-de-tennis/
Allow: /fr/frontons/
Allow: /fr/piscines/
Allow: /fr/pistes-d-athletisme/
Allow: /fr/salles-communautaires/
Allow: /fr/salles-d-escalade/
Allow: /fr/salles-de-sport/
Allow: /fr/salles-de-sports-de-combat/
Allow: /fr/skateparks/
Allow: /fr/stands-de-tir/
Allow: /fr/tennis-de-table/
Allow: /fr/terrains-de-badminton/
Allow: /fr/terrains-de-basket/
Allow: /fr/terrains-de-football/
Allow: /fr/terrains-de-handball/
Allow: /fr/terrains-de-hockey/
Allow: /fr/terrains-de-padel/
Allow: /fr/terrains-de-petanque/
Allow: /fr/terrains-de-volley/
Allow: /sitemap-cities-fr.xml
Allow: /sitemap-cities-fr/
Allow: /sitemap-venues-fr.xml
Allow: /sitemap-venues-fr/
# __FR_ALLOW_END__
Disallow: /home
Disallow: /settings
Disallow: /bookings
Disallow: /courts
Disallow: /clubs
Disallow: /tournaments
Disallow: /league
Disallow: /play
Disallow: /notifications
Disallow: /profile
Disallow: /venues
# /instalaciones-publicas NO se bloquea A PROPOSITO: es una ruta retirada que el
# origen responde con 301 (a /search o al centro concreto). Un Disallow impide la
# descarga, asi que Google no llegaria a VER ese 301 y las ~14K URLs indexadas se
# quedarian congeladas en "Bloqueada por robots.txt" en vez de consolidarse. Para
# sacar una URL del indice hay que PERMITIR su rastreo y darle la redireccion.
Disallow: /messages
Disallow: /login
Disallow: /register

# AI crawlers (training & AI search): WELCOME — we want to be cited. But please
# pace yourselves. Crawl-delay is advisory; we ALSO enforce ~30 req/min per
# (crawler, subnet) at the origin and answer 429 + Retry-After when you exceed
# it (we honor backoff in return — see https://bookrgo.app/bot). No paths
# blocked for the crawlers in THIS group.
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot-Extended
User-agent: Google-Extended
User-agent: CCBot
Crawl-delay: 2

# Crawlers we do NOT serve. Measured over 30 days (Aug-2026): these three cost
# 2.4M origin requests and returned ZERO sessions — no citations, no clicks, no
# referrals. The group above stays welcome precisely because it does send
# people back (ChatGPT, Perplexity). This is a cost decision, not a licensing
# one: ask us at hola@bookrgo.app if that changes on your side.
#
# The origin also answers 403 to these User-Agents (bot_rules), so honoring
# this group is strictly cheaper for you than ignoring it. Bytespider was
# already blocked at the origin — listing it here just makes robots.txt tell
# the truth about it.
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: Bytespider
Disallow: /

# Same decision, four more (Aug-2026). Measured on 16-Aug: these were the
# heaviest clients hitting this origin that day, and none of them is a search
# engine that sends us readers or an AI that cites its sources. Over the whole
# life of the site, exactly one external host has ever produced a registered
# user: google.com. So the trade we make with the group above — you crawl, you
# send people back — has no counterpart here.
#
# Two neighbours we deliberately did NOT include:
#   - facebookexternalhit is NOT blocked. It builds the link previews when
#     someone shares a venue on Facebook, Instagram or WhatsApp, and that is a
#     person sharing, not a crawler harvesting.
#   - Amazonbot is in the group above; Amzn-SearchBot is a different UA and is
#     listed here on its own merits.
#
# probe-image-size is not a crawler at all: it reads the header of an image to
# learn its dimensions and then aborts the connection. Our aerial photos are
# generated on demand, so every one of those cost us the full render and got
# thrown away — 18,867 requests in a single day against ~1,000 the days before.
#
# The origin also answers 403 to these User-Agents (bot_rules).
User-agent: meta-webindexer
User-agent: Amzn-SearchBot
User-agent: SleepBot
User-agent: probe-image-size
Disallow: /

# Everyone else: no paths blocked, but please pace yourselves.
#
# This group is where every crawler we haven't met yet lands, and in practice
# that is most of the traffic: on 16-Aug-2026 the three heaviest clients on this
# origin were all here, none of them named above. So the pacing rule belongs in
# THIS group, not only in the AI one — a rate limit that only the crawlers we
# already listed can see is a rate limit for the well-behaved.
#
# Crawl-delay is advisory and Googlebot ignores it (Googlebot has its own group
# above and is not affected by this one; use Search Console to adjust its rate).
# Bing, Yandex and most smaller crawlers do honor it. Independently of what you
# do with this line, the origin enforces ~30 req/min per (crawler, subnet) and
# answers 429 + Retry-After — see https://bookrgo.app/bot. Honoring the delay is
# strictly cheaper for you than collecting 429s.
User-agent: *
Crawl-delay: 5
Disallow:

Sitemap: https://bookrgo.app/sitemap.xml