# ---------------------------
# CLOUD Flare Managed Section
# ---------------------------
User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: meta-externalagent
Disallow: /

# ---------------------------
# GLOBAL RULES
# ---------------------------
User-agent: *
Disallow: /search/
Disallow: /?s=
Disallow: /wp-admin/
Disallow: /*?live-news-*
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-content/litespeed/

# ---------------------------
# GOOGLE FAMILY FULL ACCESS with search URL prevention retained
# ---------------------------
User-agent: Googlebot
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: GoogleOther
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: Google-SMART
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: Google-NotebookLM
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: AdsBot-Google
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: AdsBot-Google-Mobile
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: Googlebot-Image
Disallow: /search/
Disallow: /?s=
Allow: /

User-agent: Googlebot-Video
Disallow: /search/
Disallow: /?s=
Allow: /

# ---------------------------
# BING
# ---------------------------
User-agent: Bingbot
Allow: /

# ---------------------------
# APPROVED AI-ASSISTED CRAWLERS (limited safely)
# ---------------------------
User-agent: GPTBot
Disallow: /search/
Disallow: /?s=
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: ClaudeBot
Disallow: /search/
Disallow: /?s=
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ---------------------------
# BLOCK ALL OTHER AI SCRAPERS
# ---------------------------
User-agent: Amazonbot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Google-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Diffbot
User-agent: VelenPublicWebCrawler
User-agent: omgili
User-agent: omgilibot
User-agent: TikTokBot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Sogou
User-agent: PetalBot
User-agent: PerplexityBot
Disallow: /

# ---------------------------
# BLOCK SEO SPAM BOT CRAWLERS
# ---------------------------
User-agent: SemrushBot
User-agent: Majestic
User-agent: MJ12bot
User-agent: SerpstatBot
User-agent: Dotbot
User-agent: DataForSeoBot
Disallow: /

# ---------------------------
# BLOCK SHIELD CRAWLS FROM GOOGLE
# ---------------------------
Disallow: /wp-json/shield/v1/ 

# ---------------------------
# SITEMAP
# ---------------------------
Sitemap: https://www.boston.ac.za/sitemap_index.xml
Sitemap: https://www.boston.ac.za/ai-sitemap.xml