User-agent: * Disallow: /wp/wp-content/uploads/wc-logs/ Disallow: /wp/wp-content/uploads/woocommerce_transient_files/ Disallow: /wp/wp-content/uploads/woocommerce_uploads/ Disallow: /*?add-to-cart= Disallow: /*?*add-to-cart= Disallow: /wp/wp-admin/ Allow: /wp/wp-admin/admin-ajax.php Sitemap: https://dcrand.org/wp-sitemap.xml ############################################# # randonneur.app Network - robots.txt # Site: dcrand.org # Generated dynamically # Last updated: January 2026 ############################################# ############################################# # MAJOR SEARCH ENGINES (Welcome!) ############################################# # Google - Primary search User-agent: Googlebot User-agent: Googlebot-Image User-agent: Googlebot-News User-agent: Googlebot-Video Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /login/ Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /forums/ Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /pre-register/ Disallow: /register/ Disallow: /confirm-device/ Disallow: /?s= Disallow: /search/ Disallow: /*?add-to-cart=* Disallow: /*?replytocom=* Disallow: /wp-json/ Disallow: /feed/ Disallow: /comments/feed/ Crawl-delay: 1 # Bing - Microsoft search User-agent: Bingbot User-agent: MSNBot User-agent: MSNBot-Media Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /login/ Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /forums/ Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /pre-register/ Disallow: /register/ Disallow: /confirm-device/ Disallow: /?s= Disallow: /search/ Disallow: /*?add-to-cart=* Crawl-delay: 1 # DuckDuckGo - Privacy-focused search User-agent: DuckDuckBot Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /login/ Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /forums/ Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /pre-register/ Disallow: /register/ Disallow: /confirm-device/ Disallow: /?s= Disallow: /search/ # Yahoo (uses Bing infrastructure) User-agent: Slurp Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /login/ Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /forums/ Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /pre-register/ Disallow: /register/ Disallow: /confirm-device/ Crawl-delay: 1 # Apple - Siri and Spotlight User-agent: Applebot Allow: / Disallow: /wp-admin/ Disallow: /wp-login.php Disallow: /login/ Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ # Yandex - Russian search (some US users) User-agent: Yandex User-agent: YandexBot User-agent: YandexImages Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ Disallow: /cart/ Disallow: /checkout/ Crawl-delay: 2 # Brave Search User-agent: Brave Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ Disallow: /cart/ Disallow: /checkout/ ############################################# # AI CRAWLERS - BLOCK TRAINING # These scrape content for AI model training # Block to protect member content and IP ############################################# # OpenAI - GPT model training User-agent: GPTBot Disallow: / # Google - Gemini/Bard AI training (separate from search) User-agent: Google-Extended Disallow: / # Common Crawl - Dataset used by many AI companies User-agent: CCBot Disallow: / # Anthropic - Claude AI training User-agent: anthropic-ai User-agent: ClaudeBot Disallow: / # Meta - Facebook/Instagram AI training User-agent: FacebookBot User-agent: Meta-ExternalAgent User-agent: Meta-ExternalFetcher Disallow: / # ByteDance - TikTok AI User-agent: Bytespider Disallow: / # Amazon - Alexa and AWS AI User-agent: Amazonbot Disallow: / # Cohere - Enterprise AI User-agent: cohere-ai Disallow: / # Diffbot - Web scraping AI User-agent: Diffbot Disallow: / # AI2 - Allen Institute User-agent: AI2Bot Disallow: / # Hugging Face User-agent: HuggingFaceBot Disallow: / # Writer.com User-agent: WriterBot Disallow: / # Webz.io data collector User-agent: Webzio User-agent: webzio-extended Disallow: / # Siri suggestions (training, not search) User-agent: Applebot-Extended Disallow: / ############################################# # AI CRAWLERS - ALLOW SEARCH/BROWSING # These provide real-time answers citing sources # Allow so randonneuring info appears in AI search ############################################# # ChatGPT browsing - Real-time lookups when users ask questions User-agent: ChatGPT-User Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ Disallow: /cart/ Disallow: /checkout/ Disallow: /pre-register/ Disallow: /register/ # Perplexity AI - AI-powered search engine User-agent: PerplexityBot Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ Disallow: /cart/ Disallow: /checkout/ Disallow: /pre-register/ Disallow: /register/ # You.com - AI search User-agent: YouBot Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ Disallow: /cart/ Disallow: /checkout/ # Neeva (now part of Snowflake, but bot may still exist) User-agent: NeevaBot Allow: / Disallow: /wp-admin/ Disallow: /members/ Disallow: /my-account/ ############################################# # SEO TOOL BOTS - BLOCK # Competitor intelligence tools # No benefit, wastes bandwidth ############################################# User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: PetalBot Disallow: / User-agent: SeznamBot Disallow: / User-agent: Sogou Disallow: / User-agent: Exabot Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: BomboraBot Disallow: / ############################################# # AGGRESSIVE/MALICIOUS CRAWLERS - BLOCK ############################################# User-agent: MegaIndex Disallow: / User-agent: MauiBot Disallow: / User-agent: SeekportBot Disallow: / User-agent: Riddler Disallow: / User-agent: TurnitinBot Disallow: / User-agent: Linguee Disallow: / User-agent: DataForSeoBot Disallow: / ############################################# # DEFAULT RULES (All other crawlers) ############################################# User-agent: * Allow: / # WordPress core - protect admin Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp-login.php Disallow: /xmlrpc.php Allow: /wp-admin/admin-ajax.php # Authentication & user flows Disallow: /login/ Disallow: /logout/ Disallow: /register/ Disallow: /pre-register/ Disallow: /confirm-device/ Disallow: /password-reset/ Disallow: /activate/ # BuddyBoss member areas - private content Disallow: /members/ Disallow: /groups/ Disallow: /activity/ Disallow: /forums/ Disallow: /notifications/ Disallow: /messages/ Disallow: /settings/ # WooCommerce - transactional pages Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ Disallow: /order-received/ Disallow: /*?add-to-cart=* Disallow: /*?removed_item=* # Event Tickets - personal ticket pages Disallow: /*?ical=* Disallow: /tickets/ Disallow: /ticket/ # Cycling Club Manager - ride management Disallow: /completed-rides/ Disallow: /my-rides/ # Search & dynamic content Disallow: /?s= Disallow: /search/ Disallow: /*?replytocom=* Disallow: /*?p=* # Pagination - reduce duplicate content Disallow: /page/ # Feeds - prevent duplicate content indexing Disallow: /feed/ Disallow: /comments/feed/ Disallow: /*/feed/ # Trackbacks - spam vector Disallow: /trackback/ Disallow: /*/trackback/ # Caching/optimization artifacts Disallow: /wp-content/cache/ Disallow: /wp-content/uploads/cache/ Disallow: /wp-content/litespeed/ # Misc WordPress Disallow: /readme.html Disallow: /license.txt Disallow: /wp-config.php ############################################# # CRAWL RATE # Be gentle - volunteer-run infrastructure ############################################# Crawl-delay: 2