# https://www.robotstxt.org/robotstxt.html

# Default: cho phép search engine, chặn AI scraper
# Lưu ý: KHÔNG block /*?* vì sẽ chặn pagination /collections/...?page=2 và /search?q=...
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /search
Disallow: /profile
Disallow: /*.json$

# Search engines — Crawl-delay chỉ Bing/Yandex tuân; Google dùng Search Console
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 5

# Chặn toàn bộ AI training bot
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-webindexer
Disallow: /

# Chặn SEO scraper
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SeznamBot
Disallow: /

# Sitemaps
Sitemap: https://tomau.ai/sitemap_index.xml
Sitemap: https://tomau.ai/sitemaps/locale-vi.xml
Sitemap: https://tomau.ai/sitemaps/locale-en.xml
Sitemap: https://tomau.ai/sitemaps/locale-th.xml
Sitemap: https://tomau.ai/sitemaps/locale-id.xml
Sitemap: https://tomau.ai/sitemaps/locale-pt.xml
Sitemap: https://tomau.ai/sitemaps/locale-cs.xml
Sitemap: https://tomau.ai/sitemaps/locale-ja.xml
Sitemap: https://tomau.ai/sitemaps/locale-es.xml
Sitemap: https://tomau.ai/sitemaps/locale-tr.xml
Sitemap: https://tomau.ai/sitemaps/locale-ko.xml