Search

# CodeFormers robots.txt
# Strategy: allow search engines + AI/LLM citation bots, deny everything else.
# Goal: "cited in AI answers, not strip-mined by SEO scrapers."
# Note: misbehaved scrapers ignore robots.txt — real enforcement is on the Cloudflare WAF.

# ─── Search engines (organic search + AI Overviews / Copilot citations) ─────────
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Google-InspectionTool
User-agent: Storebot-Google
User-agent: AdsBot-Google
User-agent: Mediapartners-Google
User-agent: Bingbot
User-agent: msnbot
User-agent: msnbot-media
User-agent: BingPreview
User-agent: AdIdxBot
User-agent: DuckDuckBot
User-agent: DuckDuckGo-Favicons-Bot
User-agent: Applebot
User-agent: YandexBot
User-agent: YandexImages
Allow: /
Disallow: /api/
Disallow: /cfmetrics/
Disallow: /cdn-cgi/
Disallow: /*?_debug=

# ─── AI / LLM citation bots ─────────────────────────────────────────────────────
# OpenAI
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
# Anthropic
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Claude-SearchBot
User-agent: Claude-User
# Perplexity
User-agent: PerplexityBot
User-agent: Perplexity-User
# Google (AI training opt-in + general purpose Gemini)
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
# Apple Intelligence
User-agent: Applebot-Extended
# Microsoft Copilot
User-agent: MicrosoftPreview
# Amazon (Alexa / Amazon Nova AI answers)
User-agent: Amazonbot
# DuckDuckGo AI (DuckAssist)
User-agent: DuckAssistBot
# Meta AI (Llama citations)
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
# ByteDance / Doubao AI
User-agent: Bytespider
# Mistral
User-agent: Mistralai-User
User-agent: MistralAI-User
# Cohere
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
# DeepSeek
User-agent: DeepSeekBot
# Common training-data crawlers (used by many LLMs)
User-agent: CCBot
User-agent: omgilibot
User-agent: omgili
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: Webzio-Extended
User-agent: Diffbot
User-agent: PanguBot
# AI search engines (You/Phind/Kagi/Andi/Liner/Komo/iAsk)
User-agent: YouBot
User-agent: PhindBot
User-agent: Kagibot
User-agent: AndiBot
User-agent: LinerBot
User-agent: Liner-Bot
User-agent: KomoBot
User-agent: Komo-Bot
User-agent: iAsk-AI
User-agent: iAskAI
Allow: /
Disallow: /api/
Disallow: /cfmetrics/
Disallow: /cdn-cgi/
Disallow: /*?_debug=

# ─── SEO audit tools (own-site audits only) ─────────────────────────────────────
# Allowlisted because we run audits on codeformers.it from these tools.
# Note: AhrefsBot (general backlink crawler) intentionally NOT allowed — only the
# Site Audit user-agent, which is what we trigger ourselves from the dashboard.
User-agent: AhrefsSiteAudit
Allow: /
Disallow: /api/
Disallow: /cfmetrics/
Disallow: /cdn-cgi/
Disallow: /*?_debug=

# ─── Social preview bots (Open Graph / link unfurling) ──────────────────────────
User-agent: facebookexternalhit
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: Slackbot
User-agent: Slackbot-LinkExpanding
User-agent: TelegramBot
User-agent: WhatsApp
User-agent: Discordbot
User-agent: Pinterestbot
User-agent: Embedly
User-agent: SkypeUriPreview
Allow: /
Disallow: /api/
Disallow: /cfmetrics/
Disallow: /cdn-cgi/
Disallow: /*?_debug=

# ─── Default: everything else (SEO scrapers, data brokers, generic crawlers) ───
User-agent: *
Disallow: /

Sitemap: https://codeformers.it/sitemap-index.xml