# robots.txt — mayatravel.ai
# Updated: April 2026 | Platform: Webflow
# Strategy: Allow all search engines + all AI bots, protect crawl budget,
# keep every locale crawlable to preserve hreflang reciprocity.

# ─── SEARCH ENGINES ─────────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /cdn-cgi/
Disallow: /utility-pages/
Disallow: /style-guide
Disallow: /*?db65ccca_page=

User-agent: Googlebot-Image
Allow: /
Disallow: /cdn-cgi/
Disallow: /utility-pages/

User-agent: Bingbot
Allow: /
Disallow: /cdn-cgi/
Disallow: /utility-pages/
Disallow: /style-guide
Disallow: /*?db65ccca_page=

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

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

# ─── AI BOTS (allowed for GEO visibility) ───────────────────
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: CCBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: cohere-ai
Allow: /

# ─── SEO CRAWLERS (throttled / blocked) ─────────────────────
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# ─── DEFAULT (catch-all) ────────────────────────────────────
User-agent: *
Allow: /
Disallow: /cdn-cgi/
Disallow: /utility-pages/
Disallow: /style-guide
Disallow: /*?db65ccca_page=

# ─── SITEMAPS ───────────────────────────────────────────────
Sitemap: https://www.mayatravel.ai/sitemap.xml

Sitemap: https://www.mayatravel.ai/sitemap.xml