# # 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.md Disallow: /composer/Metapackage/README.txt Disallow: /composer/Plugin/ProjectMessage/README.md Disallow: /composer/Plugin/Scaffold/README.md Disallow: /composer/Plugin/VendorHardening/README.txt Disallow: /composer/Template/README.txt Disallow: /modules/README.txt Disallow: /sites/README.txt Disallow: /themes/README.txt # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips Disallow: /node/add/ Disallow: /search/ Disallow: /user/register Disallow: /user/password Disallow: /user/login Disallow: /user/logout Disallow: /media/oembed Disallow: /*/media/oembed # Paths (no clean URLs) Disallow: /index.php/admin/ Disallow: /index.php/comment/reply/ Disallow: /index.php/filter/tips Disallow: /index.php/node/add/ Disallow: /index.php/search/ Disallow: /index.php/user/password Disallow: /index.php/user/register Disallow: /index.php/user/login Disallow: /index.php/user/logout Disallow: /index.php/media/oembed Disallow: /index.php/*/media/oembed #Block Drupal Plan Uploads Disallow: /sites/default/files/webform/ Disallow: /sites/default/files/plan_uploaded/ Disallow: /sites/default/files/business/ # ============================================================================= # MAJOR SEARCH ENGINES - Explicitly Allow Everything # ============================================================================= # These explicit allows ensure no ambiguity after the indexing incident User-agent: Googlebot Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password User-agent: Googlebot-Mobile Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password User-agent: Googlebot-Image Allow: / User-agent: Bingbot Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password User-agent: Slurp Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password User-agent: DuckDuckBot Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password User-agent: Applebot Allow: / Disallow: /user/login Disallow: /user/register Disallow: /user/password # ============================================================================= # AI CRAWLERS - DECISION REQUIRED # ============================================================================= # # OPTION A: ALLOW AI Crawlers (RECOMMENDED for visibility in AI search) # MyCareSpace is a directory service - being discoverable in AI assistants # (ChatGPT, Claude, Perplexity, etc.) is likely BENEFICIAL for traffic. # # OPTION B: BLOCK AI Crawlers (if you don't want content used for AI training) # Note: This may reduce visibility in AI-powered search results # # Current recommendation: ALLOW (Option A) # ============================================================================= # Option A: Allow AI crawlers User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / User-agent: ClaudeBot Allow: / User-agent: Claude-Web Allow: / User-agent: Amazonbot Allow: / User-agent: anthropic-ai Allow: / User-agent: CCBot Allow: / User-agent: Google-Extended Allow: / User-agent: PerplexityBot Allow: / User-agent: YouBot Allow: / User-agent: cohere-ai Allow: / # ============================================================================= # SEO TOOL CRAWLERS - Block to save crawl budget # ============================================================================= # These tools consume server resources without providing direct SEO benefit. # Block them and use their official integrations instead. User-agent: SemrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: rogerbot Disallow: / User-agent: BLEXBot Disallow: / # ============================================================================= # MALICIOUS/SPAM BOTS - Block # ============================================================================= User-agent: Exabot Disallow: / User-agent: Gigabot Disallow: / User-agent: BlackWidow Disallow: / User-agent: HTTrack Disallow: / User-agent: Wget Disallow: / User-agent: WebCopier Disallow: / User-agent: WebZIP Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Zeus Disallow: / # ============================================================================= # SITEMAP # ============================================================================= Sitemap: https://mycarespace.com.au/sitemap.xml