# FrancescaTabor.com robots.txt
# Canonical version hosted via GitHub Pages
# Optimized for Search Engine + AI Crawler Visibility
# Created November 2025

# --- AI Crawlers (explicitly allowed) ---
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: CCBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

# --- Search Engines (standard SEO visibility) ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# --- Default rules for all other crawlers ---
User-agent: *
Disallow: /config
Disallow: /search
Disallow: /account$
Disallow: /account/
Disallow: /commerce/digital-download/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?author=*
Disallow: /*&author=*
Disallow: /*?tag=*
Disallow: /*&tag=*
Disallow: /*?month=*
Disallow: /*&month=*
Disallow: /*?view=*
Disallow: /*&view=*
Disallow: /*?format=*
Disallow: /*&format=*
Disallow: /*?reversePaginate=*
Disallow: /*&reversePaginate=*
Allow: /

# --- Sitemap reference ---
Sitemap: https://www.francescatabor.com/sitemap.xml

# --- Canonical host declaration ---
Host: www.francescatabor.com