# robots.txt for https://advisoranalyst.com
# Optimized for SEO, crawl efficiency, and controlled AI access

# ---------------------------------------------
# GLOBAL RULES
# ---------------------------------------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /wp-content/themes/
Disallow: /staging/
Disallow: /dev/
Disallow: /test/

# Avoid crawling duplicate, thin, or non-canonical content
Disallow: /?s=
Disallow: /search/
Disallow: /*?*
Disallow: /author/
Disallow: /tag/
Disallow: /category/
Disallow: /archive/
Disallow: /page/

# Optional: rate limit for heavy nonessential crawlers (ignored by Google)
Crawl-delay: 10

# ---------------------------------------------
# AI + SEARCH ENGINE CRAWLER EXCEPTIONS
# ---------------------------------------------

# ✅ Allow OpenAI crawlers (ChatGPT + GPTBot)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ✅ Allow Anthropic’s Claude crawler
User-agent: ClaudeBot
Allow: /

# ✅ Allow Google (including Googlebot, Google-Extended, and news/image/video bots)
User-agent: Googlebot
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Googlebot-News
Allow: /
User-agent: Googlebot-Image
Allow: /
User-agent: Googlebot-Video
Allow: /

# ✅ Allow Bing, Yahoo, Yandex, DuckDuckGo, etc.
User-agent: Bingbot
Allow: /
User-agent: Slurp
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Yandex
Allow: /

# ✅ Allow Facebook and social crawlers (for link previews and Open Graph)
User-agent: FacebookBot
Allow: /
User-agent: facebot
Allow: /
User-agent: Twitterbot
Allow: /
User-agent: LinkedInBot
Allow: /

# ---------------------------------------------
# BLOCK LOW-VALUE / UNKNOWN AI SCRAPERS
# ---------------------------------------------
User-agent: CCBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: omgili
Disallow: /
User-agent: MJ12bot
Disallow: /

# ---------------------------------------------
# SITEMAPS
# ---------------------------------------------
# (Update these with your actual SEO plugin sitemap URLs)
Sitemap: https://advisoranalyst.com/sitemap.xml
Sitemap: https://advisoranalyst.com/sitemap-posts.xml
Sitemap: https://advisoranalyst.com/sitemap-pages.xml