# Robots.txt para blitznocode.com # Última actualización: Agosto 2025 # ============================================ # REGLAS GENERALES - BOTS LEGÍTIMOS # ============================================ # Permitir todos los bots legítimos por defecto User-agent: * Allow: / Crawl-delay: 1 # ============================================ # BOTS DE BÚSQUEDA PRINCIPALES # ============================================ # Google User-agent: Googlebot Allow: / Crawl-delay: 0 # Bing User-agent: Bingbot Allow: / Crawl-delay: 0 # ============================================ # BOTS DE LLM / AI TRAINING # ============================================ # OpenAI (GPT) User-agent: GPTBot Allow: / # OpenAI SearchBot User-agent: ChatGPT-User Allow: / # Anthropic (Claude) User-agent: anthropic-ai Allow: / User-agent: Claude-Web Allow: / # Google Bard/Gemini User-agent: Google-Extended Allow: / # Perplexity User-agent: PerplexityBot Allow: / # Common Crawl (usado por muchos LLMs) User-agent: CCBot Allow: / # Internet Archive User-agent: ia_archiver Allow: / # ============================================ # DIRECTORIOS Y ARCHIVOS A PROTEGER # ============================================ User-agent: * # Archivos de configuración y sistema Disallow: /.env Disallow: /.git/ Disallow: /.github/ Disallow: /node_modules/ Disallow: /.vscode/ Disallow: *.config.js Disallow: /package*.json Disallow: /.gitignore # Áreas administrativas (si existen) Disallow: /admin/ Disallow: /api/private/ Disallow: /dashboard/ Disallow: /login Disallow: /register Disallow: /reset-password # Archivos temporales y de desarrollo Disallow: /temp/ Disallow: /tmp/ Disallow: /test/ Disallow: /tests/ Disallow: /_next/ Disallow: /build/ Disallow: /dist/ # Páginas de búsqueda y filtros (evitar contenido duplicado) Disallow: /search? Disallow: /*?sort= Disallow: /*?filter= Disallow: /*?page= Disallow: /*& # Archivos sensibles por extensión Disallow: /*.sql$ Disallow: /*.log$ Disallow: /*.bak$ Disallow: /*.zip$ Disallow: /*.tar$ Disallow: /*.gz$ # ============================================ # SITEMAPS # ============================================ # Sitemap principal Sitemap: https://blitznocode.com/sitemap.xml # Si tienes sitemaps específicos (descomenta si los usas) # Sitemap: https://blitznocode.com/sitemap-pages.xml # Sitemap: https://blitznocode.com/sitemap-blog.xml # Sitemap: https://blitznocode.com/sitemap-products.xml # ============================================ # BOTS MALICIOSOS A BLOQUEAR # ============================================ # Scrapers agresivos conocidos User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: DotBot Disallow: / User-agent: MJ12bot Disallow: / # Bots de spam User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / # ============================================ # NOTAS IMPORTANTES # ============================================ # 1. Este archivo permite el acceso a bots de IA/LLM principales # 2. Protege directorios sensibles y archivos de configuración # 3. Incluye crawl-delay para evitar sobrecarga del servidor # 4. Bloquea bots maliciosos conocidos # 5. Recuerda actualizar los sitemaps según tu estructura Sitemap: https://www.blitznocode.com/sitemap.xml