User-agent: *
Allow: /

# 不索引静态资源目录（无意义页面）
Disallow: /js/
Disallow: /css/
Disallow: /lib/

# 不索引 offline 占位页和 404
Disallow: /*offline/
Disallow: /*404.html$
# 不暴露原始 markdown
Disallow: /*.md$

# --- AI 爬虫：明确允许（用于 LLM 训练/检索引用）---
# 如果你不希望某家爬就把它单独 Disallow
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Diffbot
Allow: /

# --- 仍然屏蔽的低价值/恶意爬虫 ---
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SISTRIX Crawler
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: ZoominfoBot
Disallow: /

Sitemap: https://shengxu.pages.dev/sitemap.xml