# 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: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Allow search engines and AI search to index public content, but protect sensitive data

User-agent: *
# Allow all regular indexing
Disallow:

# Block all crawlers from API endpoints (protects database and user data)
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Allow AI search crawlers to index public content but block sensitive data
# OpenAI crawlers - allow public content indexing
User-agent: GPTBot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

User-agent: ChatGPT-User
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Anthropic crawlers - allow public content indexing
User-agent: ClaudeBot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

User-agent: Claude-Web
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Google AI crawlers - allow public content indexing
User-agent: Google-Extended
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

User-agent: GoogleOther
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

User-agent: GoogleOther-Image
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Perplexity - allow public content indexing
User-agent: PerplexityBot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Common Crawl - allow public content indexing (used for AI training)
User-agent: CCBot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Apple AI crawler - allow public content indexing
User-agent: Applebot-Extended
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Amazon crawler - allow public content indexing
User-agent: Amazonbot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# ByteDance crawler - allow public content indexing
User-agent: Bytespider
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# You.com crawler - allow public content indexing
User-agent: YouBot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Omgili crawlers - allow public content indexing
User-agent: omgilibot
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

User-agent: Omgili
Disallow: /api/
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /setup-password
Disallow: /reset-password

# Additional protections
# Block access to sensitive user areas
Disallow: /home
Disallow: /user-dashboard
Disallow: /profile
Disallow: /my-plan
Disallow: /application
Disallow: /enrollment
Disallow: /checkout
Disallow: /social
Disallow: /marketplace
Disallow: /strategy
Disallow: /college-search
Disallow: /essayiq
Disallow: /meeting-logs
Disallow: /brag-sheets
Disallow: /accepted-library

# Sitemap reference for search engines
Sitemap: https://acceptedx.com/sitemap.xml