# celltech robots.txt
# GEO-Optimised: Allow AI citation bots, block training scrapers
# Updated: January 2026

# ============================================
# ALLOW: Search Engines
# ============================================
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Applebot
Allow: /

# ============================================
# ALLOW: AI Citation & Retrieval Bots (GEO)
# These bots cite your content in AI answers
# Viola Eva: "LLM traffic converts at 0.7-2.3%"
# ============================================

# OpenAI search indexing (cites your content in answers)
User-agent: OAI-SearchBot
Allow: /

# ChatGPT browsing mode (users asking ChatGPT to visit your site)
User-agent: ChatGPT-User
Allow: /

# Google AI Overviews (appears in AI-generated search results)
User-agent: Google-Extended
Allow: /

# Perplexity AI (cites sources in answers)
User-agent: PerplexityBot
Allow: /

# Perplexity user-directed retrieval
User-agent: Perplexity-User
Allow: /

# Anthropic search indexing and user-directed retrieval
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Legacy Anthropic web retrieval
User-agent: Claude-Web
Allow: /

# Microsoft Copilot
User-agent: Copilot
Allow: /

# ============================================
# BLOCK: AI Training Scrapers
# These scrape content for model training, not citation
# ============================================

# Common Crawl (training dataset)
User-agent: CCBot
Disallow: /

# OpenAI model training
User-agent: GPTBot
Disallow: /

# Anthropic model training
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Apple foundation-model training (Apple search remains allowed above)
User-agent: Applebot-Extended
Disallow: /

# ByteDance/TikTok scraper
User-agent: Bytespider
Disallow: /

# Diffbot (content extraction)
User-agent: Diffbot
Disallow: /

# Omgili (content aggregator)
User-agent: Omgilibot
Disallow: /

# Meta/Facebook training
User-agent: FacebookBot
Disallow: /

# ============================================
# BLOCK: SEO Tool Scrapers
# Competitors use these to analyse your site
# ============================================

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: serpstatbot
Disallow: /

# ============================================
# BLOCK: Tech Stack Detection
# ============================================

User-agent: BuiltWith
Disallow: /

User-agent: Wappalyzer
Disallow: /

# ============================================
# DEFAULT: Allow with restrictions
# ============================================
User-agent: *
Allow: /
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /account/
Disallow: /checkout/
Disallow: /settings/
Disallow: /dev/
Disallow: /track/

# ============================================
# Sitemaps (Segmented for better GSC monitoring)
# ============================================
# Main sitemap (Next.js auto-generated, Google auto-discovers)
# URLs use non-www to match GSC property (non-www 301→www during crawl)
Sitemap: https://celltechmobilerepairs.co.uk/sitemap.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemap-index.xml

# Individual sitemaps (for direct submission to GSC)
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/pages.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/services.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-iphone.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-ipad.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-macbook.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-samsung.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-gaming.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/repair-other.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/blog.xml
Sitemap: https://celltechmobilerepairs.co.uk/sitemaps/legal.xml