# START YOAST BLOCK # --------------------------- # Content usage signals (emerging standard) # ------------------------------------------------------------- # All other crawlers (search engines + unknown bots) # ------------------------------------------------------------- User-agent: * Content-Signal: ai-train=no, search=yes, ai-input=no Allow: / Disallow: /wp-admin/ Disallow: /cdn-cgi/ Disallow: /wp-admin/admin-ajax.php?r=* Disallow: /wp-json Allow: /wp-admin/admin-ajax.php # ------------------------------------------------------------- # AI INPUT / RAG crawlers — ALLOW (enforces ai-input=yes) # ------------------------------------------------------------- User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: PerplexityBot Allow: / User-agent: ClaudeBot Allow: / User-agent: Claude-Web Allow: / User-agent: Applebot-Extended Allow: / User-agent: YouBot Allow: / User-agent: Bingbot Allow: / # ------------------------------------------------------------- # AI TRAINING crawlers — DISALLOW (enforces ai-train=no) # ------------------------------------------------------------- User-agent: Google-Extended Disallow: / User-agent: CCBot Disallow: / User-agent: FacebookBot Disallow: / User-agent: Diffbot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: cohere-ai Disallow: / User-agent: omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: img2dataset Disallow: / User-agent: Microsoft-Extended Disallow: / # ----------------------------------------------- # CHINESE AI / CRAWLER BOTS — DISALLOW # ----------------------------------------------- # DeepSeek AI User-agent: DeepSeekBot Disallow: / # Bytedance / TikTok User-agent: TikTokBot Disallow: / # Baidu User-agent: Baiduspider Disallow: / User-agent: Baiduspider-render Disallow: / User-agent: AlibabaBot Disallow: / # Tencent User-agent: SogouSpider Disallow: / User-agent: Sogou+Spider Disallow: / # 360 Spider (Qihoo) User-agent: 360Spider Disallow: / User-agent: HaosouSpider Disallow: / # Huawei / PetalBot User-agent: PetalBot Disallow: / # Yandex (Russian — no Russian market) User-agent: YandexBot Disallow: / User-agent: YandexImages Disallow: / Sitemap: https://mylegalservices.co.uk/sitemap_index.xml Page Sitemap: https://mylegalservices.co.uk/page-sitemap.xml Page Sitemap - 2: https://mylegalservices.co.uk/page-sitemap2.xml Post Sitemap: https://mylegalservices.co.uk/post-sitemap.xml Category Sitemap: https://mylegalservices.co.uk/category-sitemap.xml Tag Sitemap: https://mylegalservices.co.uk/post_tag-sitemap.xml Tag Sitemap - 2: https://mylegalservices.co.uk/post_tag-sitemap2.xml # --------------------------- # END YOAST BLOCK