# ============================================================= # robots.txt — www.latabledelise.mc # Dernière mise à jour : 22/08/2026 # ============================================================= # --- Règles générales --- # Les moteurs de recherche (Google, Bing, Qwant, DuckDuckGo, Apple) et # les agents IA de recherche (OAI-SearchBot, ChatGPT-User, PerplexityBot, # Claude-SearchBot) relèvent de ce groupe : ils sont autorisés partout # sauf sur les chemins listés ci-dessous. User-agent: * # Coeur WordPress Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php Disallow: /wp-login.php Disallow: /wp-signup.php Disallow: /xmlrpc.php Disallow: /readme.html Disallow: /license.txt Disallow: /wp-json/ Disallow: /*?rest_route= # /wp-includes/, /wp-content/plugins/ et /wp-content/cache/ restent # accessibles : nécessaires au rendu des pages par les moteurs. # Recherche interne — piège à crawl infini Disallow: /*?s= Disallow: /*&s= Disallow: /search/ Disallow: /*/search/ # Flux, commentaires, trackbacks Disallow: /feed/ Disallow: /*/feed/ Disallow: /*?feed= Disallow: /comments/feed/ Disallow: /*/trackback/ Disallow: /*?replytocom= # Facettes et tris — combinatoire infinie Disallow: /*?filter_ Disallow: /*&filter_ Disallow: /*?orderby= Disallow: /*&orderby= Disallow: /*?min_price= Disallow: /*?max_price= Disallow: /*?rating_filter= Disallow: /*?query_type_ # Paramètres sans valeur SEO Disallow: /*?attachment_id= Disallow: /*?author= Disallow: /*?preview= Disallow: /*?p= Disallow: /*?doing_wp_cron= Disallow: /*?utm_ Disallow: /*&utm_ # Honoré par bingbot, PetalBot, Yandex. Googlebot l'ignore. Crawl-delay: 10 # --- Usage IA — autorisé (visibilité dans les réponses génératives) --- User-agent: Google-Extended Disallow: User-agent: Applebot-Extended Disallow: # --- Collecte de corpus d'entraînement IA — non autorisée --- User-agent: GPTBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: CCBot Disallow: / User-agent: Bytespider Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: Meta-ExternalFetcher Disallow: / User-agent: FacebookBot Disallow: / User-agent: cohere-ai Disallow: / User-agent: Diffbot Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: omgili Disallow: / User-agent: omgilibot Disallow: / User-agent: AI2Bot Disallow: / User-agent: Timpibot Disallow: / User-agent: PanguBot Disallow: / User-agent: Webzio-Extended Disallow: / # --- Moteurs hors cible --- User-agent: Baiduspider Disallow: / User-agent: Baiduspider-render Disallow: / User-agent: Baiduspider-image Disallow: / User-agent: Baiduspider-video Disallow: / User-agent: Baiduspider-news Disallow: / User-agent: Sogou web spider Disallow: / User-agent: Sogou inst spider Disallow: / User-agent: Sogou spider2 Disallow: / User-agent: Sogou Disallow: / User-agent: YisouSpider Disallow: / User-agent: PetalBot Disallow: / User-agent: Amazonbot Disallow: / User-agent: Amzn-SearchBot Disallow: / User-agent: YandexBot Disallow: / User-agent: YandexImages Disallow: / # --- Crawlers SEO, backlinks et aspirateurs --- User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SemrushBot-SA Disallow: / User-agent: SemrushBot-BA Disallow: / User-agent: MJ12bot Disallow: / User-agent: DotBot Disallow: / User-agent: BLEXBot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: Barkrowler Disallow: / User-agent: serpstatbot Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: SeekportBot Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: MegaIndex Disallow: / User-agent: rogerbot Disallow: / User-agent: MauiBot Disallow: / User-agent: LinkpadBot Disallow: / User-agent: Mediatoolkitbot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: Scrapy Disallow: / User-agent: osentix-crawler Disallow: / User-agent: GlassDollarWWWIndexer Disallow: / User-agent: SeltzSitemapFetcher Disallow: / # --- Sitemap --- Sitemap: https://www.latabledelise.mc/sitemaps.xml