# =================================== # COMPREHENSIVE ROBOTS.TXT # Last Updated: July 2025 # # Configuration: # - Major AI Assistants (GPT, Claude, Gemini): 2-second delay # - Other AI/LLM Bots: 10-second delay # - All bots (including Google): Blocked from parameterized URLs # =================================== # =================================== # MAJOR AI ASSISTANTS – ALLOWED WITH LIGHT DELAY # =================================== # OpenAI Bots User-agent: GPTBot Allow: / Crawl-delay: 2 User-agent: ChatGPT-User Allow: / Crawl-delay: 2 User-agent: OAI-SearchBot Allow: / Crawl-delay: 2 # Anthropic/Claude Bots User-agent: anthropic-ai Allow: / Crawl-delay: 2 User-agent: ClaudeBot Allow: / Crawl-delay: 2 User-agent: Claude-Web Allow: / Crawl-delay: 2 User-agent: Claude-SearchBot Allow: / Crawl-delay: 2 User-agent: Claude-User Allow: / Crawl-delay: 2 # Google AI/Gemini (not search) User-agent: Google-Extended Allow: / Crawl-delay: 2 User-agent: Google-CloudVertexBot Allow: / Crawl-delay: 2 User-agent: GoogleOther Allow: / Crawl-delay: 2 User-agent: GoogleOther-Image Allow: / Crawl-delay: 2 User-agent: GoogleOther-Video Allow: / Crawl-delay: 2 # =================================== # OTHER LLM/AI BOTS – ALLOWED WITH HEAVY DELAY # =================================== # Common Crawl User-agent: CCBot Allow: / Crawl-delay: 10 # ByteDance/TikTok User-agent: Bytespider Allow: / Crawl-delay: 10 # Perplexity User-agent: PerplexityBot Allow: / Crawl-delay: 10 # Amazon User-agent: Amazonbot Allow: / Crawl-delay: 10 # Apple AI User-agent: Applebot-Extended Allow: / Crawl-delay: 10 # Meta/Facebook AI User-agent: FacebookBot Allow: / Crawl-delay: 10 User-agent: Meta-ExternalAgent Allow: / Crawl-delay: 10 User-agent: Meta-ExternalFetcher Allow: / Crawl-delay: 10 User-agent: meta-externalagent Allow: / Crawl-delay: 10 # Cohere AI User-agent: cohere-ai Allow: / Crawl-delay: 10 User-agent: cohere-training-data-crawler Allow: / Crawl-delay: 10 # Other AI/LLM Bots User-agent: AI2Bot Allow: / Crawl-delay: 10 User-agent: Ai2Bot-Dolma Allow: / Crawl-delay: 10 User-agent: aiHitBot Allow: / Crawl-delay: 10 User-agent: Brightbot 1.0 Allow: / Crawl-delay: 10 User-agent: Crawlspace Allow: / Crawl-delay: 10 User-agent: Diffbot Allow: / Crawl-delay: 10 User-agent: DuckAssistBot Allow: / Crawl-delay: 10 User-agent: Factset_spyderbot Allow: / Crawl-delay: 10 User-agent: FirecrawlAgent Allow: / Crawl-delay: 10 User-agent: FriendlyCrawler Allow: / Crawl-delay: 10 User-agent: iaskspider/2.0 Allow: / Crawl-delay: 10 User-agent: ICC-Crawler Allow: / Crawl-delay: 10 User-agent: ImagesiftBot Allow: / Crawl-delay: 10 User-agent: img2dataset Allow: / Crawl-delay: 10 User-agent: imgproxy Allow: / Crawl-delay: 10 User-agent: ISSCyberRiskCrawler Allow: / Crawl-delay: 10 User-agent: Kangaroo Bot Allow: / Crawl-delay: 10 User-agent: Meltwater Allow: / Crawl-delay: 10 User-agent: Omgili Allow: / Crawl-delay: 10 User-agent: Omgilibot Allow: / Crawl-delay: 10 User-agent: PanguBot Allow: / Crawl-delay: 10 User-agent: Seekr Allow: / Crawl-delay: 10 User-agent: Timpibot Allow: / Crawl-delay: 10 User-agent: webzio-extended Allow: / Crawl-delay: 10 User-agent: Webzio-Extended Allow: / Crawl-delay: 10 User-agent: YouBot Allow: / Crawl-delay: 10 # =================================== # BING – SUPPORTS CRAWL DELAY # =================================== User-agent: bingbot Allow: / Crawl-delay: 0 User-agent: Slurp Allow: / Crawl-delay: 0 # =================================== # DEFAULT RULES FOR ALL BOTS # Including: Googlebot, Googlebot-Image, Googlebot-Video, # Googlebot-News, AdsBot-Google, AdsBot-Google-Mobile, # DuckDuckBot, YandexBot, Baiduspider, and others # =================================== User-agent: * Allow: / Disallow: /wp-admin/ Disallow: /old-site Disallow: /wp-content/uploads/2024/03/signature-img.png Allow: /wp-admin/admin-ajax.php # Disallow faceted navigation and parameterized URLs for ALL bots Disallow: /*?add-to-cart= Disallow: /*?added-to-cart=true Disallow: /*?min_price= Disallow: /*?max_price= Disallow: /*?paged= Disallow: /*?product_count= Disallow: /*&add-to-cart= Disallow: /*&min_price= Disallow: /*&max_price= Disallow: /*&paged= Disallow: /*&product_count= # =================================== # SITEMAP # =================================== Sitemap: https://bwmachinery.com.au/sitemap_index.xml