# Harley Street Institute - Robots.txt # https://www.harleystreetinstitute.com User-agent: * Allow: / # Sitemap locations Sitemap: https://www.harleystreetinstitute.com/sitemap.xml Sitemap: https://www.harleystreetinstitute.com/sitemap-courses.xml Sitemap: https://www.harleystreetinstitute.com/sitemap-pages.xml Sitemap: https://www.harleystreetinstitute.com/sitemap-journal.xml Sitemap: https://www.harleystreetinstitute.com/sitemap-aesthetic-talk.xml # Aesthetic Talk — explicitly allow chapter pages Allow: /aesthetic-talk/ # Journal — explicitly allow article HTML, PDFs and JATS exports Allow: /journal/ Allow: /functions/v1/journal-article-pdf Allow: /functions/v1/journal-issue-cover-pdf Allow: /functions/v1/journal-article-jats Allow: /functions/v1/journal-oai-pmh # Disallow admin and protected areas Disallow: /admin/ Disallow: /auth/ Disallow: /app/ Disallow: /media-manager/ Disallow: /page-management/ Disallow: /seo-evaluator/ Disallow: /seo-dashboard/ Disallow: /blog-management/ Disallow: /debug-blog-add/ Disallow: /user-management/ Disallow: /initialize-content/ Disallow: /journal/legacy-home/ Disallow: /polynucleotides-online-assessment/ Disallow: /coming-soon/ Disallow: /booking-success/ Disallow: /booking-cancelled/ Disallow: /contact-thank-you/ Disallow: /endolaser-models/ # Scratch / prototype routes (not for indexing; route cleanup pending) Disallow: /a2/ Disallow: /a3/ Disallow: /a4/ Disallow: /a5/ Disallow: /ab/ Disallow: /f2/ Disallow: /home6/ Disallow: /j2/ Disallow: /j3/ Disallow: /newhome1/ Disallow: /newhome2/ Disallow: /nt/ Disallow: /nt1/ Disallow: /test/ # Disallow all URLs with query parameters (prevents duplicate content) Disallow: /*?* # Disallow tag, category, and author pages (low SEO value, duplicate content) Disallow: /tag/ Disallow: /tags/ Disallow: /category/ Disallow: /categories/ Disallow: /author/ Disallow: /blog/author/ Disallow: /blog/tag/ Disallow: /blog/category/ # Note: Non-trailing slash URLs redirect to trailing slash versions via 301 # Canonical URLs always use trailing slashes (e.g., /course/ not /course) # This is enforced via: # 1. netlify.toml configuration # 2. _redirects file # 3. SEO component canonical tags # 4. Client-side redirect in SEO component # Set crawl delay to be respectful Crawl-delay: 1