# =============================================
# AI Search / Answer Engine Crawlers — ALLOW
# These crawlers surface content in AI-powered search results
# =============================================

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: YouBot
Allow: /

# =============================================
# AI Training Crawlers — BLOCK (protect IP)
# These crawlers scrape content for model training, not search
# =============================================

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# =============================================
# Default Crawl Policy (Google, Bing, etc.)
# =============================================

User-agent: *
Allow: /

# Block sensitive WordPress areas
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /cgi-bin/
Disallow: /xmlrpc.php
Disallow: /wp-login.php
Disallow: /wp-register.php

# Block low-value pages from crawl budget
Disallow: /?s=
Disallow: /search/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /trackback/
Disallow: /tag/
Disallow: /author/
Disallow: /?replytocom=

# =============================================
# Sitemap
# =============================================
Sitemap: https://www.vrvisiongroup.com/sitemap_index.xml