# Content Signals (EU Directive 2019/790 Art. 4 rights reservation) # REVIEW: ai-train=yes means you consent to AI model training on your content. # Change to ai-train=no if you only want search/retrieval, not training. Content-Signal: search=yes, ai-train=yes, ai-input=yes # ============================================================================= # BLOCKED CRAWLERS # ============================================================================= # Yandex - blocked entirely User-agent: Yandex Disallow: / User-agent: YandexBot Disallow: / User-agent: YandexBot/3.0 Disallow: / # Bytespider (ByteDance) - blocked entirely # Note: ignores robots.txt — enforce via WAF/AI Crawl Control edge block User-agent: Bytespider Disallow: / # CCBot (Common Crawl) - blocked entirely User-agent: CCBot Disallow: / # ============================================================================= # ALLOWED AI CRAWLERS — Training / Indexing # Crawl-delay applied to training crawlers to protect origin resources. # Anthropic and OpenAI respect Crawl-delay. Perplexity compliance unverified. # ============================================================================= # --- Anthropic --- # ClaudeBot: AI training data collection User-agent: ClaudeBot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # Claude-SearchBot: search indexing for Claude search User-agent: Claude-SearchBot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 3 # --- OpenAI --- # GPTBot: training data collection for OpenAI models User-agent: GPTBot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # OAI-SearchBot: OpenAI search indexing User-agent: OAI-SearchBot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 3 # --- Perplexity --- # WARNING: Cloudflare delisted Perplexity as verified bot (Jan 2026). # Known to rotate ASNs and spoof UAs. Enforce via WAF, not just robots.txt. User-agent: PerplexityBot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # --- Google --- # Google-Extended: controls Google AI training (Gemini/Bard) on your content # This is a training opt-in/out token, not a separate crawler. # Allowing = consenting to Google using your content for AI model training. User-agent: Google-Extended Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ # ============================================================================= # ALLOWED AI AGENTS — Real-time user-initiated browsing # No Crawl-delay: these are on-demand, single-page fetches triggered by users. # Crawl-delay would degrade the user experience with no benefit. # ============================================================================= # Claude-User: when a Claude user asks it to visit a URL User-agent: Claude-User Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ # ChatGPT-User: when a ChatGPT user asks it to browse User-agent: ChatGPT-User Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ # Perplexity-User: when a Perplexity user triggers a fetch User-agent: Perplexity-User Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ # ============================================================================= # SEARCH ENGINE CRAWLERS # ============================================================================= User-agent: Applebot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # --- Meta --- # Meta-ExternalAgent: AI training data collection for Meta AI (Llama models) User-agent: Meta-ExternalAgent Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # FacebookExternalAgent: Meta link previews and shared-content fetching User-agent: facebookexternalagent Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 3 # Amazonbot: Amazon search, indexing, and service-improvement crawler User-agent: Amazonbot Allow: /wp/wp-admin/admin-ajax.php Allow: / Disallow: /wp/wp-admin/ Crawl-delay: 5 # ============================================================================= # DEFAULT RULES — All other crawlers # ============================================================================= User-agent: * Disallow: /wp/wp-admin/ Allow: /wp/wp-admin/admin-ajax.php Sitemap: https://www.ipxo.com/sitemap_index.xml