# 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.

# 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.

# BEGIN Cloudflare Managed content

User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Robots.txt for Endless Adventure
# See https://www.robotstxt.org/robotstxt.html for documentation

# Allow all search engines to crawl public content
User-agent: *

# Allow access to main public pages and localized content
Allow: /
Allow: /en/
Allow: /es/
Allow: /fr/
Allow: /de/
Allow: /it/
Allow: /pt/
Allow: /pt-BR/
Allow: /nl/
Allow: /pl/
Allow: /cs/
Allow: /hu/
Allow: /ro/
Allow: /ru/
Allow: /uk/
Allow: /ar/
Allow: /he/
Allow: /tr/
Allow: /hi/
Allow: /th/
Allow: /vi/
Allow: /id/
Allow: /ms/
Allow: /ko/
Allow: /ja/
Allow: /zh-CN/
Allow: /sv/
Allow: /no/
Allow: /da/
Allow: /fi/
Allow: /el/
Allow: /fa/

# Allow access to static assets for proper page rendering
Allow: /assets/
Allow: /*.css
Allow: /*.js
Allow: /*.png
Allow: /*.jpg
Allow: /*.jpeg
Allow: /*.gif
Allow: /*.svg
Allow: /*.webp
Allow: /*.ico

# Block admin areas
Disallow: /admin/
Disallow: /admin/*

# Block API endpoints (not meant for search indexing)
Disallow: /api/
Disallow: /api/*

# Block Rails-specific paths
Disallow: /rails/
Disallow: /rails/*

# Block transaction and purchase endpoints
Disallow: /purchases/
Disallow: /purchases/*

# Block health check endpoint
Disallow: /up

# Block account deletion page (sensitive/private)
Disallow: /*/account-deletion
Disallow: /account-deletion

# Block error pages (they shouldn't be indexed)
Disallow: /400
Disallow: /404
Disallow: /406
Disallow: /422
Disallow: /500

# Block any temporary or cache files
Disallow: /tmp/
Disallow: /cache/
Disallow: /.well-known/

# Crawl delay (be respectful to server resources)
Crawl-delay: 1

# Sitemap location (update this URL to your actual domain)
Sitemap: https://magicbookshelf.ai/sitemap.xml

# Specific rules for major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /