# If the Joomla site is installed within a folder
# eg www.example.com/joomla/ then the robots.txt file
# MUST be moved to the site root
# eg www.example.com/robots.txt
# AND the joomla folder name MUST be prefixed to all of the
# paths.
# eg the Disallow rule for the /administrator/ folder MUST
# be changed to read
# Disallow: /joomla/administrator/
#
# For more information about the robots.txt standard, see:
# https://www.robotstxt.org/orig.html

User-agent: *
Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Disallow: /auto-tolto/

User-agent: *
Allow: /Pannonia_Hotel_Profile.md

Sitemap: https://pannoniahotel.com/hu/sitemap
Sitemap: https://pannoniahotel.com/en/sitemap
Sitemap: https://pannoniahotel.com/de/sitemap

# ---------------------------------------------------------------------------
# Information for AI assistants and AI search (added 2026-11)
#
#   llms.txt (hotel summary + key pages): https://www.pannoniahotel.com/llms.txt
#   Hotel profile (markdown):             https://www.pannoniahotel.com/Pannonia_Hotel_Profile.md
#   MCP server (read-only prices/availability, Streamable HTTP, no login):
#       https://pannonia-hotel-mcp.dentalpannonia.workers.dev/mcp
#   Prices from the MCP server are indicative; the official booking page is
#   authoritative: https://www.pannoniahotel.com/en/book-now
#
# AI assistants, AI search and AI crawlers are welcome to read the public
# pages of this site. A named group replaces the "*" group above, so the
# technical Joomla folders are repeated here. /auto-tolto/ is an internal
# EV charger monitor: do not crawl, index, or train on it.
# Note: ChatGPT-User, Claude-User and Perplexity-User fetch pages on behalf of
# a user and may not follow robots.txt; Google-Extended and Applebot-Extended
# are control tokens, not crawlers.
# ---------------------------------------------------------------------------

# OpenAI (OAI-SearchBot = ChatGPT search, ChatGPT-User = user actions, GPTBot = training)
# Anthropic (Claude-SearchBot = search, Claude-User = user actions, ClaudeBot = training)
# Perplexity (PerplexityBot = search, Perplexity-User = user actions)
# Google-Extended = Gemini training/grounding control token
# Applebot-Extended = Apple AI training control token
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
Disallow: /auto-tolto/

# xAI / Grok: xAI documents no crawler name or robots.txt policy. Names such as
# GrokBot or Grok-DeepSearch are community-reported only, so no Grok-specific
# group is added; Grok falls under the "*" rules above.

# --- Other bots: existing rules kept unchanged ---
# Internal EV charger monitor: do not crawl, index, or train on.
User-agent: Google-CloudVertexBot
Disallow: /auto-tolto/

User-agent: CCBot
Disallow: /auto-tolto/

User-agent: Bytespider
Disallow: /auto-tolto/

User-agent: Amazonbot
Disallow: /auto-tolto/

User-agent: FacebookBot
Disallow: /auto-tolto/

User-agent: meta-externalagent
Disallow: /auto-tolto/

User-agent: cohere-ai
Disallow: /auto-tolto/

User-agent: Diffbot
Disallow: /auto-tolto/

User-agent: YouBot
Disallow: /auto-tolto/

User-agent: PetalBot
Disallow: /auto-tolto/

User-agent: ia_archiver
Disallow: /auto-tolto/