# As a condition of accessing this website, you agree to abide by the following # content signals: # (a) If a Content-Signal = yes, you may collect content for the corresponding # use. # (b) If a Content-Signal = no, you may not collect content for the # corresponding use. # (c) If the website operator does not include a Content-Signal for a # corresponding use, the website operator neither grants nor restricts # permission via Content-Signal with respect to the corresponding use. # The content signals and their meanings are: # search: building a search index and providing search results (e.g., returning # hyperlinks and short excerpts from your website's contents). Search does not # include providing AI-generated search summaries. # ai-input: inputting content into one or more AI models (e.g., retrieval # augmented generation, grounding, or other real-time taking of content for # generative AI search answers). # ai-train: training or fine-tuning AI models. # use: how AI systems may consume the content (immediate, reference, or full). # ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF # RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT # AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET. # BEGIN Cloudflare Managed content User-agent: * Content-Signal: search=yes,ai-train=no,use=reference Allow: / # Training crawlers User-agent: Amazonbot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Diffbot Disallow: / User-agent: Google-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: omgili Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: cohere-ai Disallow: / User-agent: MistralAI-Training Disallow: / User-agent: meta-externalagent Disallow: / User-agent: GoogleOther Disallow: / User-agent: Baiduspider Disallow: / User-agent: PetalBot Disallow: / User-agent: AwarioSmartBot User-agent: AwarioRssBot Disallow: / User-agent: Google-CloudVertexBot Disallow: / User-agent: QualifiedBot Disallow: / User-agent: Cotoyogi Disallow: / User-agent: ICC-Crawler Disallow: / User-agent: atlassian-bot Disallow: / User-agent: FishBot Disallow: / User-agent: BorderxBot Disallow: / User-agent: NavuBot Disallow: / User-agent: SemrushBot-SWA Disallow: / User-agent: WARDBot Disallow: / User-agent: magpie-crawler Disallow: / User-agent: KimiBot Disallow: / User-agent: CitibotSiteCrawler Disallow: / # END Cloudflare Managed Content # ============================================================================= # robots.txt for hylesanderson.edu # Last updated: 2026-03-02 # User: Daniel Wruck # ============================================================================= # --------------------------------------------------------------------------- # SEO tool crawlers — blocked # These crawl your site to build THEIR index for THEIR paying customers. # They consume significant server resources and provide no benefit unless # you are paying for their services. Remove a block if you subscribe. # --------------------------------------------------------------------------- User-agent: AhrefsBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: DotBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: BLEXBot Disallow: / User-agent: DataForSeoBot Disallow: / User-agent: Bytespider Disallow: / # --------------------------------------------------------------------------- # AI training crawlers — blocked # These scrape content to train large language models. Block unless you # want your content used for AI training. # --------------------------------------------------------------------------- User-agent: GPTBot Disallow: / User-agent: CCBot Disallow: / User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: Google-Extended Disallow: / User-agent: FacebookBot Disallow: / User-agent: meta-externalindexer Disallow: / User-agent: meta-webindexer Disallow: / User-agent: Facebot Disallow: / User-agent: Omgilibot Disallow: / # --------------------------------------------------------------------------- # Default rules for all well-behaved bots (Googlebot, BingBot, Applebot, etc) # --------------------------------------------------------------------------- User-agent: * # WordPress internals Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /wp-content/plugins/ Disallow: /wp-content/cache/ Disallow: /wp-json/ Disallow: /xmlrpc.php Disallow: /readme.html Disallow: /license.txt # WooCommerce — cart, checkout, and account pages have no search value Disallow: /cart/ Disallow: /checkout/ Disallow: /my-account/ # WooCommerce — block sorted/filtered/paginated product variations # These create infinite crawl loops with parameter combinations Disallow: /*?add-to-cart=* Disallow: /*?product_order=* Disallow: /*?product_count=* Disallow: /*?product_sort=* Disallow: /*?orderby=* Disallow: /*?add_to_wishlist=* # hac-music pages — these are generating massive 404 floods Disallow: /hac-music Disallow: /*?ms_song=* Disallow: /*?ms_collection=* # Calendar crawl traps (all-in-one-event-calendar views) Disallow: /calendar/action~posterboard/ Disallow: /calendar/action~agenda/ Disallow: /calendar/action~oneday/ Disallow: /calendar/action~month/ Disallow: /calendar/action~week/ Disallow: /calendar/action~stream/ Disallow: /calendar-2/action~posterboard/ Disallow: /calendar-2/action~agenda/ Disallow: /calendar-2/action~oneday/ Disallow: /calendar-2/action~month/ Disallow: /calendar-2/action~week/ Disallow: /calendar-2/action~stream/ Disallow: /calendar-3/action~posterboard/ Disallow: /calendar-3/action~agenda/ Disallow: /calendar-3/action~oneday/ Disallow: /calendar-3/action~month/ Disallow: /calendar-3/action~week/ Disallow: /calendar-3/action~stream/ Disallow: /*?plugin=all-in-one-event-calendar* # Event calendar iCal exports Disallow: /*?controller=ai1ec_exporter_controller* # Music store _msr tracking parameters — crawl trap Disallow: /*?_msr=* # Feed discovery (keep the main feed, block parameterized ones) Disallow: /*?feed=* # WordPress login Disallow: /wp-login.php # Allow CSS/JS for rendering (Google wants this) Allow: /wp-content/uploads/ Allow: /wp-content/themes/ Allow: /wp-includes/js/ Allow: /wp-includes/css/ # Sitemaps Sitemap: https://hylesanderson.edu/sitemap_index.xml Sitemap: https://store.hylesanderson.edu/sitemap_index.xml