# robots.txt - jewelxy.com # # GENERATED by scripts/jxy-crawler-policy.py - do not hand-edit. # # Physical file: while it exists it takes precedence over Yoast's virtual robots.txt. # # POLICY (set by the site owner, 2026-08-24) # ------------------------------------------------------------------ # ALLOWED to crawl the catalogue: # * classic search engines - Google, Bing, DuckDuckGo, Yandex, Baidu # * eight AI answer engines - OpenAI (ChatGPT), Google (Gemini), # Perplexity, xAI (Grok), Anthropic (Claude), DeepSeek, # Meta (Facebook) and Apple. # REFUSED outright: # * every other AI / LLM crawler, agent and training harvester # * SEO backlink scrapers and data brokers # # The allowed crawlers are deliberately NOT given their own groups. A crawler # obeys only the single most specific group that matches it, so giving them an # "Allow: /" group of their own would also drop the crawler-trap rules below for # precisely the crawlers whose crawl budget we most want to protect. They # inherit the "User-agent: *" group instead, which already permits the catalogue. # # Google-Extended and Applebot-Extended are robots.txt-only opt-out tokens with # no crawler of their own. They are deliberately absent, which is how Gemini and # Apple Intelligence stay permitted. # # Enforcement: this file is the polite layer. The refused agents below are ALSO # hard-blocked with HTTP 403 at the CloudFront edge (jxy-edge-router function), # so ignoring this file does not get them in. User-agent: * Disallow: /wp-admin/ Allow: /wp-admin/admin-ajax.php # Per-visitor transactional pages - no crawl or index value. Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ # Crawler traps: on-site search results and cart-mutation links generate # effectively unlimited unique URLs. Disallow: /?s= Disallow: /*?s= Disallow: /*&s= Disallow: /*add-to-cart= Disallow: /*add-to-wishlist= Disallow: /*add_to_compare= Disallow: /*remove_compare_item= Disallow: /*clear_compare_list= # --------------------------------------------------------------------------- # REFUSED - AI/LLM crawlers outside the eight approved vendors, plus SEO # scrapers and data brokers. # --------------------------------------------------------------------------- User-agent: AddSearchBot Disallow: / User-agent: AgentTimes Disallow: / User-agent: AhrefsBot Disallow: / User-agent: AI2Bot Disallow: / User-agent: AI2Bot-DeepResearchEval Disallow: / User-agent: Ai2Bot-Dolma Disallow: / User-agent: aiHitBot Disallow: / User-agent: AIWebIndex Disallow: / User-agent: amazon-kendra Disallow: / User-agent: amazon-QBusiness Disallow: / User-agent: Amazonbot Disallow: / User-agent: AmazonBuyForMe Disallow: / User-agent: Amzn-SearchBot Disallow: / User-agent: Amzn-User Disallow: / User-agent: Andibot Disallow: / User-agent: ApifyBot Disallow: / User-agent: ApifyWebsiteContentCrawler Disallow: / User-agent: Aranet-SearchBot Disallow: / User-agent: atlassian-bot Disallow: / User-agent: Awario Disallow: / User-agent: AzureAI-SearchBot Disallow: / User-agent: bedrockbot Disallow: / User-agent: bigsur.ai Disallow: / User-agent: BLEXBot Disallow: / User-agent: Bravebot Disallow: / User-agent: Brightbot Disallow: / User-agent: BuddyBot Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: Channel3Bot Disallow: / User-agent: ChatGLM-Spider Disallow: / User-agent: Cloudflare-AutoRAG Disallow: / User-agent: cohere-ai Disallow: / User-agent: cohere-training-data-crawler Disallow: / User-agent: Cotoyogi Disallow: / User-agent: CragCrawler Disallow: / User-agent: Crawl4AI Disallow: / User-agent: Crawlspace Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: Diffbot Disallow: / User-agent: DotBot Disallow: / User-agent: DuckAssistBot Disallow: / User-agent: EchoboxBot Disallow: / User-agent: ExaBot Disallow: / User-agent: ExaSearchBot Disallow: / User-agent: Factset_spyderbot Disallow: / User-agent: FirecrawlAgent Disallow: / User-agent: FriendlyCrawler Disallow: / User-agent: GeistHaus-PageFetcher Disallow: / User-agent: HenkBot Disallow: / User-agent: iAskBot Disallow: / User-agent: iaskspider Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: imageSpider Disallow: / User-agent: img2dataset Disallow: / User-agent: ISSCyberRiskCrawler Disallow: / User-agent: kagi-fetcher Disallow: / User-agent: Kimi-User Disallow: / User-agent: KlaviyoAIBot Disallow: / User-agent: KunatoCrawler Disallow: / User-agent: laion-huggingface-processor Disallow: / User-agent: LAIONDownloader Disallow: / User-agent: LinerBot Disallow: / User-agent: LinkupBot Disallow: / User-agent: MistralAI-User Disallow: / User-agent: MJ12bot Disallow: / User-agent: Mozilla-Tabstack Disallow: / User-agent: MyCentralAIScraperBot Disallow: / User-agent: NagetBot Disallow: / User-agent: netEstate Imprint Crawler Disallow: / User-agent: NovaAct Disallow: / User-agent: omgilibot Disallow: / User-agent: PanguBot Disallow: / User-agent: Panscient Disallow: / User-agent: PetalBot Disallow: / User-agent: PhindBot Disallow: / User-agent: Poggio-Citations Disallow: / User-agent: QualifiedBot Disallow: / User-agent: Querit-SearchBot Disallow: / User-agent: QueritBot Disallow: / User-agent: QuillBot Disallow: / User-agent: Reflectionbot Disallow: / User-agent: SBIntuitionsBot Disallow: / User-agent: Scrapy Disallow: / User-agent: SemrushBot Disallow: / User-agent: SemrushBot-OCOB Disallow: / User-agent: SemrushBot-SWA Disallow: / User-agent: Shap-User Disallow: / User-agent: ShapBot Disallow: / User-agent: TavilyBot Disallow: / User-agent: Thinkbot Disallow: / User-agent: TikTokSpider Disallow: / User-agent: Timpibot Disallow: / User-agent: TongyiBot Disallow: / User-agent: TwinAgent Disallow: / User-agent: UseAI Disallow: / User-agent: VelenPublicWebCrawler Disallow: / User-agent: WARDBot Disallow: / User-agent: webzio-extended Disallow: / User-agent: Webzio-Extended Disallow: / User-agent: wpbot Disallow: / User-agent: WRTNBot Disallow: / User-agent: YandexAdditional Disallow: / User-agent: YandexAdditionalBot Disallow: / User-agent: YiyanBot Disallow: / User-agent: YouBot Disallow: / User-agent: ZanistaBot Disallow: / User-agent: ZoominfoBot Disallow: / Sitemap: https://www.jewelxy.com/sitemap_index.xml