# RexVet (Rex Vets Inc.) — robots.txt
# 501(c)(3) non-profit veterinary telehealth · rexvet.org

# Default: allow all standard crawlers
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/

# Explicit allow for AI / answer-engine crawlers.
# We WANT to appear in ChatGPT, Claude, Perplexity, and Google AI Overview
# citations — those drive measurable impressions and brand-search lift.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

# Explicit allow for Googlebot, Bingbot, YandexBot, DuckDuckBot —
# named ahead of wildcard so any future restrictive default we add to *
# won't cascade to these. Belt-and-suspenders.
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/

User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/

User-agent: YandexBot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/

User-agent: DuckDuckBot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/

# Sitemaps + feeds — every discovery surface declared
Sitemap: https://www.rexvet.org/sitemap-index.xml
Sitemap: https://www.rexvet.org/sitemap-blog.xml
Sitemap: https://www.rexvet.org/sitemap-images.xml
Sitemap: https://www.rexvet.org/news-sitemap.xml
# RSS feed (used by some crawlers as a freshness/discovery signal)
# https://www.rexvet.org/rss.xml

# Canonical host (Yandex uses this directive; ignored by other bots)
Host: www.rexvet.org