# robots.txt — Nhà Cô Thảo
# Allow major search engines, block AI training crawlers.

User-agent: *
Allow: /
Disallow: /go/

# === AI training crawlers — block (Helpful Content + privacy) ===

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

# Note: FacebookBot/meta-externalagent là crawler của Meta (Facebook/Instagram)
# dùng cho Open Graph + Sharing Debugger — KHÔNG phải AI training.
# Allow để OG image preview hoạt động khi share link.
# Meta-ExternalAgent crawler riêng cho training — cả 2 cần allow root,
# nếu muốn block AI training của Meta thì dùng disallow path cụ thể.

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# === Sitemap ===

Sitemap: https://nhacothao.com/sitemap-index.xml