# 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

# SecureHabbo Robots.txt
# The premier marketplace for Habbo NFTs and Legacy items
# https://www.securehabbo.com
# Last updated: 2026-01-04

# =============================================================================
# DEFAULT RULES - All Crawlers
# =============================================================================

User-Agent: *

# Allow main content
Allow: /
Allow: /market
Allow: /legacy
Allow: /rankings
Allow: /guides
Allow: /collectibles
Allow: /onlines

# Allow AI context files
Allow: /llms.txt
Allow: /llms-full.txt

Allow: /rewardshop
Allow: /tools

# Disallow internal/private routes
Disallow: /api/
Disallow: /login
Disallow: /_nuxt/
Disallow: /boxchecker/
Disallow: /editor/
Disallow: /habbogpt/
Disallow: /link/

# Disallow static assets (not needed for indexing)
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.json$
Disallow: /*.map$

# Disallow URL parameters that create duplicate content
Disallow: /*?sort=*
Disallow: /*?page=*
Disallow: /*?*&sort=*
Disallow: /*?*&page=*

# Allow specific filter parameters (these have unique content)
Allow: /market?categories=*
Allow: /market?collection=*
Allow: /market?search=*

# Crawl rate limiting
Crawl-delay: 1

# =============================================================================
# GOOGLE SPECIFIC
# =============================================================================

User-Agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /_nuxt/
Disallow: /login
# No crawl-delay for Google

User-Agent: Googlebot-Image
Allow: /images/
Allow: /assets/
Disallow: /_nuxt/

# =============================================================================
# BING SPECIFIC  
# =============================================================================

User-Agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /_nuxt/
Disallow: /login
Crawl-delay: 1

# =============================================================================
# AI CRAWLERS - ALLOW FULL ACCESS
# =============================================================================

# OpenAI GPTBot
User-Agent: GPTBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /market
Allow: /market/*
Allow: /legacy
Allow: /legacy/*
Allow: /rankings
Allow: /guides
Disallow: /api/
Disallow: /_nuxt/
Disallow: /login

# OpenAI ChatGPT User
User-Agent: ChatGPT-User
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# Anthropic Claude
User-Agent: anthropic-ai
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

User-Agent: ClaudeBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# Google Gemini/Bard
User-Agent: Google-Extended
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# Perplexity AI
User-Agent: PerplexityBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# Cohere
User-Agent: cohere-ai
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# Meta AI
User-Agent: FacebookBot
Allow: /
Allow: /llms.txt

User-Agent: Meta-ExternalAgent
Allow: /
Allow: /llms.txt

# Common Crawl (used for training data)
User-Agent: CCBot
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Crawl-delay: 2

# =============================================================================
# SOCIAL MEDIA CRAWLERS
# =============================================================================

User-Agent: Twitterbot
Allow: /

User-Agent: facebookexternalhit
Allow: /

User-Agent: LinkedInBot
Allow: /

User-Agent: Discordbot
Allow: /

# =============================================================================
# BLOCK KNOWN BAD BOTS
# =============================================================================

User-Agent: AhrefsBot
Disallow: /
# If you want Ahrefs data, change to Allow

User-Agent: SemrushBot
Disallow: /
# If you want Semrush data, change to Allow

User-Agent: MJ12bot
Disallow: /

User-Agent: DotBot
Disallow: /

User-Agent: BLEXBot
Disallow: /

# =============================================================================
# SITEMAPS
# =============================================================================

Sitemap: https://www.securehabbo.com/sitemap.xml
Sitemap: https://www.securehabbo.com/sitemap-items.xml

# =============================================================================
# HOST
# =============================================================================

Host: https://www.securehabbo.com