User-agent: * # --- Bloqueos tecnicos WordPress --- Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /xmlrpc.php # --- Feeds, comentarios y trackbacks --- Disallow: /feed/ Disallow: /*/feed/ Disallow: /comments/feed/ Disallow: /comments/ Disallow: /trackback/ Disallow: /*/trackback/ # --- Archivos adjuntos y URLs generadas por WordPress --- Disallow: /?attachment_id= Disallow: /*?attachment_id= Disallow: /*/attachment/ Disallow: /attachment/ # --- Busquedas internas --- Disallow: /?s= Disallow: /*?s= Disallow: /search/ # --- Etiquetas del blog (no posicionan, detectadas en /blogimd/tag/) --- Disallow: /blogimd/tag/ Disallow: /tag/ # --- Parametro de tracking de Google Merchant Center (srsltid) --- # Detectado en el rastreo generando duplicados canonicalizados Disallow: /*?srsltid= Disallow: /*&srsltid= # --- Permitir recursos necesarios para el renderizado (Elementor + tema IMD-V2) --- Allow: /wp-content/uploads/ Allow: /wp-content/themes/ Allow: /wp-content/plugins/ Allow: /wp-includes/ # --- LBM --- Disallow: /lbm/ # ========================================================== # GOOGLE AI (Gemini / Grounding) # Permitir expresamente a Gemini la lectura en tiempo real # ========================================================== User-agent: Google-Extended Allow: / # ========================================================== # BOTS DE ENTRENAMIENTO IA (Bloqueados) # OAI-SearchBot, Claude-SearchBot y PerplexityBot siguen # permitidos a traves de User-agent: * # ========================================================== # OpenAI: bloquear entrenamiento masivo User-agent: GPTBot Disallow: / # Anthropic: bloquear entrenamiento masivo User-agent: ClaudeBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / # Apple: bloquear entrenamiento masivo User-agent: Applebot-Extended Disallow: / # Common Crawl (dataset publico de IA) User-agent: CCBot Disallow: / # Otros rastreadores de entrenamiento User-agent: cohere-ai Disallow: / User-agent: Bytespider Disallow: / # ========================================================== # SCRAPING / DESCARGA MASIVA # ========================================================== User-agent: HTTrack Disallow: / User-agent: WebCopier Disallow: / User-agent: WebStripper Disallow: / User-agent: SiteSnagger Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: wget Disallow: / User-agent: curl Disallow: / User-agent: libwww Disallow: / User-agent: Xenu Disallow: / # --- Sitemap --- Sitemap: https://imdermatologico.com/sitemap_index.xml