# # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/robotstxt.html User-agent: * # CSS, JS, Images Allow: /core/*.css$ Allow: /core/*.css? Allow: /core/*.js$ Allow: /core/*.js? Allow: /core/*.gif Allow: /core/*.jpg Allow: /core/*.jpeg Allow: /core/*.png Allow: /core/*.svg Allow: /profiles/*.css$ Allow: /profiles/*.css? Allow: /profiles/*.js$ Allow: /profiles/*.js? Allow: /profiles/*.gif Allow: /profiles/*.jpg Allow: /profiles/*.jpeg Allow: /profiles/*.png Allow: /profiles/*.svg # Directories Disallow: /core/ Disallow: /profiles/ # Files Disallow: /README.txt Disallow: /web.config # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips/ Disallow: /node/add/ Disallow: /search/ # Paths (no clean URLs) Disallow: /job/sendMail Disallow: /job/sendMail/* Disallow: /private_message/create Disallow: /*?dest=*&id=* Disallow: /*?jtype=*&jtype=*&jtype=* Disallow: /*?jtype=*&jtype=*&more=* Disallow: /*?jtype=*&more=* Disallow: /*?more=*?more=* Disallow: /*?more=*&more=*&more=* Disallow: /*?more=* Disallow: /desgin-437873621dhjKa21k/ Disallow: /desgin-437873621dhjKa21k/* Disallow: /heading1 Disallow: /heading2 Disallow: /heading3 Disallow: /about-curam Disallow: /carer-profile/ # Block all URLs with a question mark (any parameter) Disallow: /*? Sitemap: https://www.curamcare.com/sitemap.xml Sitemap: https://www.curamcare.com/location-sitemap.xml Sitemap: https://www.curamcare.com/location-caretype-sitemap.xml # ========================================== # AI SEARCH & AGENTS (High Referral Value) # These bots drive traffic and citations. # ========================================== # OpenAI Search (ChatGPT Search) User-agent: OAI-SearchBot Allow: /llms.txt Allow: /all-locations*.txt # Google Gemini & AI Search # Google-Extended is the specific token for Gemini and Vertex AI. User-agent: Google-Extended Allow: /llms.txt Allow: /all-locations*.txt # Perplexity AI Search User-agent: PerplexityBot Allow: /llms.txt Allow: /all-locations*.txt # Anthropic Claude Search/Agents User-agent: Claude-Web Allow: /llms.txt Allow: /all-locations*.txt # ========================================== # AI TRAINING BOTS (Bulk Data Ingestion) # These bots crawl for model training. # ========================================== # OpenAI GPT Models User-agent: GPTBot Allow: /llms.txt Allow: /all-locations*.txt # Anthropic Claude Training User-agent: ClaudeBot Allow: /llms.txt Allow: /all-locations*.txt # Apple Intelligence User-agent: Applebot-Extended Allow: /llms.txt Allow: /all-locations*.txt # Common Crawl (Used by many smaller AI models) User-agent: CCBot Allow: /llms.txt Allow: /all-locations*.txt