# robots.txt
# NOTE: robots.txt groups do not inherit rules from other groups — a crawler
# matches exactly one User-agent block (its own, or "*" if none matches) and
# only follows the Allow/Disallow rules in that block. All crawlers below are
# intentionally allowed the same access, so they share a single "*" group
# rather than separate named blocks (a separate named block with only
# "Allow: /" would bypass every Disallow rule below for that bot).
User-agent: *
Allow: /

# Sitemap
Sitemap: https://webuyanyvegashouse.com/sitemap.xml

# Disallow admin and API routes
Disallow: /api/

# Block WordPress artifacts (legacy crawl cleanup)
Disallow: /wp-content/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-json/
Disallow: /xmlrpc.php
Disallow: /*/feed/
Disallow: /feed/
Disallow: /faq-items/
Disallow: /faq_category/
Disallow: /author/
Disallow: /category/
Disallow: /tag/
Disallow: /?s=

# Search engine crawlers (Googlebot, Bingbot) — no bot-specific overrides,
# so they use the "*" group above (Allow: / plus the Disallows).

# LLM crawlers — OpenAI (GPTBot, ChatGPT-User, OAI-SearchBot) — allowed,
# use the "*" group above.

# LLM crawlers — Anthropic (ClaudeBot, Claude-Web legacy alias, anthropic-ai)
# — allowed, use the "*" group above.

# LLM crawlers — Perplexity (PerplexityBot, Perplexity-User) — allowed,
# use the "*" group above.

# LLM crawlers — Google (Google-Extended, Gemini / AI Overviews opt-in)
# — allowed, use the "*" group above.

# LLM crawlers — Apple Intelligence (Applebot-Extended) — allowed, use the
# "*" group above.

# LLM crawlers — Other (CCBot, cohere-ai, Bytespider) — allowed, use the
# "*" group above.