# robots.txt for no8.io
# Last updated: 2026-04-22

# --- Default rules for all crawlers ---

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

# --- AI Crawlers (GEO / Generative Engine Optimization) ---
# Explicitly allowing AI engines to crawl and cite our content.

# OpenAI — ChatGPT training + browsing + SearchGPT

User-agent: GPTBot
Allow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ChatGPT-User
Allow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: OAI-SearchBot
Allow: /

# Anthropic — Claude
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ClaudeBot
Allow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Claude-Web
Allow: /

# Perplexity — crawl + real-time user queries
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: PerplexityBot
Allow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Perplexity-User
Allow: /

# Google — Bard / Gemini / AI Overview training data
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Google-Extended
Allow: /

# Apple — Apple Intelligence
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Applebot-Extended
Allow: /

# Meta — Meta AI
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: meta-externalagent
Allow: /

# Amazon — Alexa / Rufus
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Amazonbot
Allow: /

# ByteDance — Doubao (亞洲 AI 重要引擎)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Bytespider
Allow: /

# Common Crawl — 間接訓練多個 LLM 的基礎資料集
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: CCBot
Allow: /

# --- Sitemap ---
Sitemap: https://no8.io/sitemap.xml
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*