# Robots.txt for The Library Dispensary # https://thelibrarynj.com/ # Business: The Library of New Jersey - Cannabis Dispensary # Last Updated: January 29, 2026 # Google Bot - FULL ACCESS GRANTED User-agent: Googlebot Allow: / Allow: /business.html Allow: /google-business-info.html Allow: /google-site-verification.html Allow: /*.js$ Allow: /*.css$ Allow: /*.html$ Allow: /images/ Allow: /public/ Crawl-delay: 0 # Google Business Bot User-agent: Googlebot-Business Allow: / # Google AdsBot User-agent: AdsBot-Google Allow: / # All other crawlers User-agent: * Allow: / Disallow: /test-* Disallow: /_next/ Disallow: /node_modules/ # Test pages (explicit blocks for safety) Disallow: /test-cookie-consent/ Disallow: /test-mobile-verification/ Disallow: /test-modal/ # (Removed 2026-05-05) Previous lines blocked /events/[slug] and /faq/[slug] — # robots.txt does not interpret [ and ] as templates so Google read them as # literal URLs and reported 404 in GSC. Real /events/* and /faq/* subpages # remain crawlable. Google will deindex the artifact URLs on next recrawl. # Bing Bot User-agent: Bingbot Allow: / Crawl-delay: 1 # AI Search Crawlers - FULL ACCESS GRANTED User-agent: GPTBot Allow: / User-agent: Google-Extended Allow: / User-agent: ChatGPT-User Allow: / User-agent: anthropic-ai Allow: / User-agent: Claude-Web Allow: / User-agent: PerplexityBot Allow: / User-agent: Bytespider Allow: / User-agent: CCBot Allow: / User-agent: Amazonbot Allow: / User-agent: meta-externalagent Allow: / # Important pages to crawl frequently Allow: /products/ Allow: /first-visit/ Allow: /location/ Allow: /about/ # LLMs.txt for AI assistants # See: https://thelibrarynj.com/llms.txt # Full: https://thelibrarynj.com/llms-full.txt # Sitemap location Sitemap: https://thelibrarynj.com/sitemap.xml # Host directive (for Yandex) Host: https://thelibrarynj.com