# Robots.txt for Hera Fertility # Unlisted clinic rules are generated dynamically from the database # Default rules for all crawlers User-agent: * Allow: / # Block development and test pages Disallow: /test-* Disallow: /viz-test Disallow: /theme-demo Disallow: /*-debug Disallow: /google-maps-* # Block API endpoints Disallow: /api/ # Block Cloudflare internal paths (email protection, etc.) Disallow: /cdn-cgi/ # Block clinic print and PDF pages Disallow: /clinic/*/print Disallow: /clinic/*/pdf # Block unlisted/closed clinic pages (auto-generated from is_listed=false) Disallow: /clinic/5 Disallow: /clinic/6 Disallow: /clinic/11 Disallow: /clinic/13 Disallow: /clinic/16 Disallow: /clinic/21 Disallow: /clinic/22 Disallow: /clinic/24 Disallow: /clinic/26 Disallow: /clinic/33 Disallow: /clinic/36 Disallow: /clinic/38 Disallow: /clinic/39 Disallow: /clinic/41 Disallow: /clinic/49 Disallow: /clinic/52 Disallow: /clinic/53 Disallow: /clinic/56 Disallow: /clinic/57 Disallow: /clinic/59 Disallow: /clinic/67 Disallow: /clinic/69 Disallow: /clinic/88 Disallow: /clinic/92 Disallow: /clinic/99 Disallow: /clinic/105 Disallow: /clinic/109 Disallow: /clinic/113 Disallow: /clinic/121 Disallow: /clinic/125 Disallow: /clinic/129 Disallow: /clinic/133 Disallow: /clinic/135 Disallow: /clinic/137 Disallow: /clinic/138 Disallow: /clinic/139 Disallow: /clinic/140 Disallow: /clinic/144 Disallow: /clinic/156 Disallow: /clinic/165 Disallow: /clinic/167 Disallow: /clinic/169 Disallow: /clinic/170 Disallow: /clinic/173 Disallow: /clinic/180 Disallow: /clinic/186 Disallow: /clinic/194 Disallow: /clinic/213 Disallow: /clinic/222 Disallow: /clinic/223 Disallow: /clinic/227 Disallow: /clinic/228 Disallow: /clinic/231 Disallow: /clinic/233 Disallow: /clinic/235 Disallow: /clinic/240 Disallow: /clinic/241 Disallow: /clinic/242 Disallow: /clinic/251 Disallow: /clinic/256 Disallow: /clinic/259 Disallow: /clinic/275 Disallow: /clinic/277 Disallow: /clinic/281 Disallow: /clinic/287 Disallow: /clinic/299 Disallow: /clinic/300 Disallow: /clinic/304 Disallow: /clinic/315 Disallow: /clinic/320 Disallow: /clinic/332 Disallow: /clinic/341 Disallow: /clinic/353 Disallow: /clinic/355 Disallow: /clinic/356 Disallow: /clinic/358 Disallow: /clinic/362 Disallow: /clinic/377 Disallow: /clinic/379 Disallow: /clinic/381 Disallow: /clinic/389 Disallow: /clinic/391 Disallow: /clinic/394 Disallow: /clinic/395 Disallow: /clinic/397 Disallow: /clinic/398 Disallow: /clinic/401 Disallow: /clinic/403 Disallow: /clinic/404 Disallow: /clinic/407 Disallow: /clinic/412 Disallow: /clinic/413 Disallow: /clinic/414 Disallow: /clinic/419 Disallow: /clinic/420 Disallow: /clinic/421 Disallow: /clinic/427 Disallow: /clinic/428 Disallow: /clinic/441 Disallow: /clinic/445 Disallow: /clinic/448 Disallow: /clinic/453 Disallow: /clinic/457 Disallow: /clinic/458 Disallow: /clinic/472 Disallow: /clinic/483 Disallow: /clinic/484 Disallow: /clinic/485 Disallow: /clinic/486 Disallow: /clinic/497 Disallow: /clinic/498 Disallow: /clinic/499 Disallow: /clinic/509 Disallow: /clinic/513 Disallow: /clinic/515 Disallow: /clinic/525 Disallow: /clinic/534 Disallow: /clinic/545 Disallow: /clinic/563 Disallow: /clinic/570 Disallow: /clinic/571 Disallow: /clinic/597 Disallow: /clinic/607 Disallow: /clinic/608 # Block authenticated areas (but allow login/signup) Disallow: /dashboard Disallow: /admin/ Disallow: /admin-tools Disallow: /clinic-portal/ Disallow: /profile/ Disallow: /messages Disallow: /analytics Disallow: /traffic-analytics # Note: /upload and /simple-upload are functional pages for authenticated users Disallow: /upload Disallow: /simple-upload # Block utility pages Disallow: /unsubscribe Disallow: /claim-account/ # Block direct access to success pages Disallow: /subscription/success Disallow: /starter-plan/success Disallow: /complete-plan/success # AI/LLM Crawlers - Priority access for AI citations User-agent: GPTBot Allow: / User-agent: Claude-Web Allow: / User-agent: ChatGPT-User Allow: / User-agent: CCBot Allow: / User-agent: PerplexityBot Allow: / User-agent: anthropic-ai Allow: / User-agent: Bytespider Allow: / # Search engine crawlers User-agent: Googlebot Allow: / # Google Ads crawlers - required for ad approval User-agent: AdsBot-Google Allow: / User-agent: AdsBot-Google-Mobile Allow: / User-agent: Google-AdWords-Express Allow: / User-agent: Mediapartners-Google Allow: / # Google specialized crawlers User-agent: Googlebot-Image Allow: / User-agent: Googlebot-Video Allow: / User-agent: Googlebot-News Allow: / User-agent: Storebot-Google Allow: / # Google AI/Gemini training crawler User-agent: Google-Extended Allow: / # Bing/Microsoft crawlers User-agent: Bingbot Allow: / User-agent: BingPreview Allow: / User-agent: msnbot Allow: / User-agent: adidxbot Allow: / # OpenAI Search (new search product) User-agent: OAI-SearchBot Allow: / # Apple AI crawler User-agent: Applebot Allow: / User-agent: Applebot-Extended Allow: / # Meta/Facebook AI User-agent: FacebookBot Allow: / User-agent: Meta-ExternalAgent Allow: / # Amazon/Alexa User-agent: Amazonbot Allow: / # Cohere AI User-agent: cohere-ai Allow: / # Other search engines User-agent: DuckDuckBot Allow: / User-agent: YandexBot Allow: / User-agent: Baiduspider Allow: / # SEO tools User-agent: AhrefsBot Allow: / User-agent: MJ12bot Allow: / User-agent: SemrushBot Allow: / # Sitemaps - Primary sitemap index for comprehensive crawling Sitemap: https://herafertility.co/sitemap.xml # Additional specialized sitemaps for faster discovery Sitemap: https://herafertility.co/sitemap-main.xml Sitemap: https://herafertility.co/sitemap-labs.xml Sitemap: https://herafertility.co/sitemap-blog.xml # LLM/AI Crawler Instructions # This file helps AI assistants understand our content structure and discover key resources # For AI-optimized content discovery and citation guidelines, see: # - https://herafertility.co/llm.txt (AI content directory - primary) # - https://herafertility.co/llms.txt (AI content directory - alternative) # - https://herafertility.co/sitemap.xml (comprehensive site structure) # # Key Content Areas for AI Crawlers: # - Fertility Education: /expert-interviews, /fertility-topics, /sperm-health-course # - Clinical Resources: /fertility-guide/, /fertility-testing/ # - Lab Directory: /find-labs, /labs/ # - Blog Content: /blogs/male-fertility, /blogs/resources # # Our content is intended to be crawled and cited by AI assistants to help # individuals understand male fertility testing and reproductive health.