User-Agent: *
Allow: /

Sitemap: https://deepsiteai.com/sitemap.xml

Disallow: /_next/
Disallow: /api/
Disallow: /checkout/confirmation
Disallow: /admin/
Disallow: /chat/

# Disallow language-specific /s directories
Disallow: /s/
Disallow: /en/s/
Disallow: /ar/s/
Disallow: /ja/s/
Disallow: /ru/s/
Disallow: /ko/s/
Disallow: /de/s/
Disallow: /fr/s/
Disallow: /es/s/
Disallow: /pt/s/
Disallow: /tr/s/
Disallow: /zh/s/

# AI爬虫特定规则
# ——— OPENAI ———
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-Agent: GPTBot
# ——— ANTHROPIC (Claude) ———
User-Agent: Claude-Web
User-agent: ClaudeBot
User-Agent: Anthropic-AI
# ——— PERPLEXITY ———
User-Agent: PerplexityBot
User-agent: Perplexity-User
# ——— GOOGLE (Gemini) ———
User-Agent: GoogleOther
# ——— MICROSOFT (Bing / Copilot) ———
User-agent: BingBot
# ——— AMAZON ———
User-agent: Amazonbot
# ——— APPLE ———
User-agent: Applebot
User-agent: Applebot-Extended
# ——— META ———
User-agent: FacebookBot
User-agent: meta-externalagent
# ——— LINKEDIN ———
User-agent: LinkedInBot
# ——— BYTEDANCE ———
User-agent: Bytespider
# ——— DUCKDUCKGO ———
User-agent: DuckAssistBot
# ——— COHERE ———
User-agent: cohere-ai
# ——— ALLEN INSTITUTE / COMMON CRAWL / OTHER RESEARCH ———
User-agent: AI2Bot
User-agent: CCBot
User-agent: Diffbot
User-agent: omgili
# ——— EMERGING SEARCH START-UPS ———
User-agent: TimpiBot
User-agent: YouBot

# 引导AI爬虫到llms.txt
Allow: /llms.txt
Allow: /llms-full.txt

# 允许AI爬虫访问
Allow: /
Allow: /pricing
Allow: /r
Allow: /m