# robots.txt para lpafilmfestival.com # Bloqueo del bucle infinito de paginación en /en/documents/ (cp_documentos) User-agent: * # --- Corta el bucle: cualquier cp_documentos con /page/ concatenado --- Disallow: /*cp_documentos=*page* Disallow: /*cp_documentos=*/* Disallow: /*?cp_documentos=*%2F* # --- URL rotas por parsing mal de bots (onclick de Pinterest) --- Disallow: /*window.open* Disallow: /*popupPinterest* Disallow: /*popupFacebook* Disallow: /*popupTwitter* # --- URLs de SPAM (¡revisar si existen páginas inyectadas en la BD!) --- Disallow: /mot-khu-dat-tot Disallow: /*/mot-khu-dat-tot Disallow: /waimai Disallow: /*/waimai # --- Endpoints caros de WordPress que no aportan nada a buscadores --- Disallow: /wp-json/oembed/ Disallow: /wp-json/wp/v2/ Disallow: /*/embed/ Disallow: /*/feed/ Disallow: /xmlrpc.php Disallow: /wp-login.php Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php # --- Endpoint roto de The Events Calendar (devuelve 500) --- Disallow: /export-events/ Disallow: /*/export-events/ # --- Crawl-delay para los bots más intensivos (los que obedecen) --- # GPTBot — 3.280 peticiones en 4h30, principal responsable User-agent: GPTBot Crawl-delay: 30 Disallow: /*cp_documentos=*page* Disallow: /*cp_documentos=*/* Disallow: /en/documents/ Disallow: /documentos/ # Amazonbot — 827 peticiones User-agent: Amazonbot Crawl-delay: 30 Disallow: /*cp_documentos=*page* Disallow: /en/documents/ Disallow: /documentos/ # Bytespider (TikTok) — ignora robots a menudo, añádelo también a nginx User-agent: Bytespider Crawl-delay: 60 Disallow: /*cp_documentos=*page* Disallow: /en/documents/ Disallow: /documentos/ # Applebot User-agent: Applebot Crawl-delay: 20 Disallow: /*cp_documentos=*page* # ClaudeBot (sí, el mío) User-agent: ClaudeBot Crawl-delay: 30 Disallow: /*cp_documentos=*page* # Baiduspider — abusa del endpoint oembed User-agent: Baiduspider Crawl-delay: 30 Disallow: /wp-json/ Disallow: /*cp_documentos=*page* # Sogou User-agent: Sogou web spider Crawl-delay: 60 Disallow: /wp-json/ # PetalBot (Huawei) — frecuentemente abusivo User-agent: PetalBot Crawl-delay: 60 # MJ12bot User-agent: MJ12bot Crawl-delay: 60 # DotBot User-agent: DotBot Crawl-delay: 60 # --- Sitemap (ajusta si es otro) --- Sitemap: https://www.lpafilmfestival.com/sitemap.xml Sitemap: https://www.lpafilmfestival.com/sitemap_index.xml