# IMO - Informed Market Opinions
# Robots.txt for search engine crawlers

# Allow all crawlers
User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/
# Empty SPA shell served by vercel.json's catch-all — never a real page.
Disallow: /_shell.html
Disallow: /uploads/
Disallow: /.env
Disallow: /node_modules
Disallow: /build
Disallow: /dist
Disallow: /.git

# LLM / AI crawlers — allow full access for AEO citations
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Gemini
Allow: /

User-agent: Bytespider
Allow: /

# Specific rules for Google
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# Specific rules for Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# Facebook crawler
User-agent: facebookexternalhit
Allow: /

# Twitter crawler
User-agent: Twitterbot
Allow: /

# LinkedIn crawler
User-agent: LinkedInBot
Allow: /

# Pinterest crawler
User-agent: Pinterestbot
Allow: /

# Sitemap
# One reference, on the canonical www host, pointing at the sitemap index
# (vercel.json rewrites /sitemap.xml to the backend's sitemap-index.xml).
# The three earlier entries here pointed at the api subdomain and at a
# non-www host that 301s — both make Google follow a redirect to reach the
# sitemap, and neither matches the host the URLs inside it use.
Sitemap: https://www.informedmarketopinions.com/sitemap.xml

# Rate limiting
Request-rate: 100/1h