# ==============================================================================
# MyPR.co.za - Robots.txt
# Search Engine & AI-Friendly Crawling Rules
# ==============================================================================

User-agent: *
# Allow public content, releases, and media
Allow: /
Allow: /wp-content/uploads/
Allow: /international/

# Block WordPress administrative, plugin, & dynamic utility endpoints
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /readme.html
Disallow: /license.txt

# Block registration, account management, and internal utility routes
Disallow: /login-3/
Disallow: /register/
Disallow: /?mypr_svc=*

# Standard search query blocking (prevents duplicate index bloat)
Disallow: /?s=
Disallow: /search/

# ------------------------------------------------------------------------------
# Explicitly Allow Major AI Crawlers & LLM Indexers
# ------------------------------------------------------------------------------
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: AnthropicAI
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: Cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

User-agent: YouBot
Allow: /

# ------------------------------------------------------------------------------
# Sitemaps & Machine-Readable AI Files
# ------------------------------------------------------------------------------
Sitemap: https://mypr.co.za/sitemap_index.xml

# Reference LLMs.txt index if available
Allow: /llms.txt