# 2023/05/10 # robots.txt para canaln.pe # # no entry # === INDEXACIÓN GENERAL PARA BUSCADORES === User-agent: * Disallow: /llms.txt # === BING: Permitir indexación y uso en IA === User-agent: bingbot Allow: / User-agent: msnbot Allow: / # Microsoft aún no tiene un equivalente público a "Google-Extended". # Pero permitir "bingbot" garantiza visibilidad en Bing Search y Copilot IA. # === OPENAI: Permitir indexación en GPTBot y respuestas en ChatGPT === User-agent: GPTBot Allow: / User-agent: ChatGPT-User Allow: / # === PERPLEXITY AI === User-agent: PerplexityBot Allow: / # === CLAUDE (Anthropic) === User-agent: ClaudeBot Allow: / User-agent: anthropic-ai Allow: / User-agent: Claude-Web Allow: / # === DUCKDUCKGO AI === User-agent: duckduckgo-ai Allow: / # === BLOQUEO DE BOTS DE IA NO DESEADOS === User-agent: CCBot Disallow: / User-agent: FacebookBot Disallow: / User-agent: Amazonbot Disallow: / User-agent: cohere-ai Disallow: / User-agent: youBot Disallow: / User-agent: UbiCrawler Disallow: / User-agent: DOC Disallow: / User-agent: Zao Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: Zealbot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: SiteSnagger Disallow: / User-agent: WebStripper Disallow: / User-agent: WebCopier Disallow: / User-agent: Fetch Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Teleport Disallow: / User-agent: TeleportPro Disallow: / User-agent: WebZIP Disallow: / User-agent: linko Disallow: / User-agent: HTTrack Disallow: / User-agent: Microsoft.URL.Control Disallow: / User-agent: Xenu Disallow: / User-agent: larbin Disallow: / User-agent: libwww Disallow: / User-agent: ZyBORG Disallow: / User-agent: Download Ninja Disallow: / # # la mayoria de veces causa problemas # User-agent: wget Disallow: / User-agent: grub-client Disallow: / User-agent: k2spider Disallow: / User-agent: NPBot Disallow: / User-agent: WebReaper Disallow: / User-agent: Googlebot Disallow: User-agent: Googlebot-News Disallow: User-agent: Googlebot-Image Disallow: User-agent: Google-Extended Disallow: User-agent: Applebot-Extended Disallow: / User-agent: Bytespider Disallow: / User-agent: facebookexternalhit Allow: / User-agent: meta-externalagent Allow: / User-agent: meta-externalagent/1.1 Allow: / # # Guia # User-agent: * Disallow: /buscar$ Disallow: /cdn-cgi/ Sitemap: https://canaln.pe/sitemap