# AboutMyHotel robots.txt
#
# Maintained on the origin, NOT by Cloudflare ("Manage your robots.txt" is set to
# "Disable robots.txt configuration"). Policy: search engines and AI retrieval are
# welcome, AI training is not.
#
# The same policy is enforced at network level by Cloudflare AI Crawl Control,
# where the training crawlers listed below are blocked outright and answered with
# a 403. This file is the polite declaration of that policy; the block list is
# what actually stops a crawler that ignores it.

# As a condition of accessing this website, you agree to abide by the following
# content signals:
#
# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.
#
# The content signals and their meanings are:
#
# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does
#           not include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content
#           for generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# AI training crawlers: not permitted.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

# Crawlers with no audience for this site, also blocked at network level.
User-agent: PetalBot
Disallow: /

User-agent: arquivo-web-crawler
Disallow: /

# Deliberately NOT listed above, and therefore allowed:
#
# - Google-Extended: lets Google AI Overviews and Gemini ground their answers on
#   this site. Allowing it is the point of ai-input=yes above.
# - OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot,
#   Perplexity-User, DuckAssistBot, MistralAI-User, Meta-ExternalFetcher: these
#   fetch pages to answer a user's question and cite the source, which is exactly
#   what use=reference permits.

Sitemap: https://www.aboutmyhotel.com/sitemap_index.xml

# AI-oriented site index, curated summary of this site for LLMs:
# https://www.aboutmyhotel.com/llms.txt