# 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

# Oraxia.online - Warframe Spider Queen Hub
# AI-optimized robots.txt for search engines and LLM crawlers

# General rules for all crawlers
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /static/
Disallow: /admin/
Disallow: /private/
Disallow: /404
Disallow: /500
Disallow: /*.json$

# AI Crawler specific rules - Allow access to LLM-optimized content
User-agent: GPTBot
User-agent: Claude-Web
User-agent: Anthropic-AI
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: GoogleOther
User-agent: DuckAssistBot
User-agent: ChatGPT-User
User-agent: GPT-4
User-agent: Claude
User-agent: Bard
User-agent: PaLM
User-agent: CCBot
User-agent: Applebot
User-agent: FacebookBot
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /
Allow: /abilities/
Allow: /builds/
Allow: /unlock-guide/
Allow: /showcase/
Allow: /community/
Allow: /blog/
Allow: /privacy-policy.html
Allow: /terms-of-service.html

# Search Engine Crawlers - Full Access
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /static/
Disallow: /404
Disallow: /500
Disallow: /*.json$

User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Baiduspider
User-agent: YandexBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /api/

# Social Media Crawlers
User-agent: facebookexternalhit
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: WhatsApp
User-agent: TelegramBot
Allow: /

# Block aggressive commercial crawlers
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: SiteAuditBot
Disallow: /

# Crawl delay for heavy crawlers
Crawl-delay: 1

# Sitemap locations
Sitemap: https://oraxia.online/sitemap.xml
Sitemap: https://oraxia.online/sitemap-images.xml
Sitemap: https://oraxia.online/sitemap-videos.xml

# Host directive
Host: https://oraxia.online