# 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. # 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. # ============================================ # DEFAULT RULES (all crawlers) # ============================================ User-agent: * Content-Signal: search=yes,ai-train=no Allow: / # Year-calendar: allow yearly pages for 2016-2036, block month sub-pages Disallow: /*/time-and-date/year-calendar Disallow: /*/time-and-date/year-calendar/*/*/* # Year-calendar month pages: block all by default Disallow: /*/time-and-date/year-calendar/*/*/*/* Allow: /*/time-and-date/year-calendar/*/*/2025 Allow: /*/time-and-date/year-calendar/*/*/2026 Allow: /*/time-and-date/year-calendar/*/*/2027 # Allow month pages only for key countries (US, DE, NO, FR, ES) in 2026 Allow: /*/time-and-date/year-calendar/us/*/2026/* Allow: /*/time-and-date/year-calendar/de/*/2026/* Allow: /*/time-and-date/year-calendar/no/*/2026/* Allow: /*/time-and-date/year-calendar/fr/*/2026/* Allow: /*/time-and-date/year-calendar/es/*/2026/* # Days-left-until: block dynamic holiday URLs (XX__holiday__YYYY pattern) # Static slugs (midnight, tomorrow, halloween, etc.) remain allowed with all units Disallow: /*/time-and-date/days-left-until/*__* # Week-number: only allow current and next year Disallow: /*/time-and-date/week-number Allow: /*/time-and-date/week-number/2026 Allow: /*/time-and-date/week-number/2026/* Allow: /*/time-and-date/week-number/2027 Allow: /*/time-and-date/week-number/2027/* # Colors: block individual hex code pages # Named color pages, paint brands, tools etc. remain allowed Disallow: /*/colors/color/ # Converter deep pages: block from-X-to-Y detail pages Disallow: /*/converters/volume-flow-rate/*/* # API endpoints Disallow: /getHoliday Disallow: /holidaysCache Disallow: /getCustomHolidayDescription Disallow: /countriesCelebratingHoliday # ============================================ # AI CRAWLERS - Block (Cloudflare Managed) # ============================================ User-agent: Amazonbot Disallow: / User-agent: Applebot-Extended Disallow: / User-agent: Bytespider Disallow: / User-agent: CCBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Google-Extended Disallow: / User-agent: GPTBot Disallow: / User-agent: meta-externalagent Disallow: / # ============================================ # AD TECH CRAWLERS - Allow (revenue-critical) # Blocking these reduces CPM and excludes you from premium campaigns. # Sources: IAS, DoubleVerify, Google Ad Manager, Playwire # ============================================ User-agent: Mediapartners-Google Allow: / User-agent: ias_crawler Allow: / User-agent: ias_wombles Allow: / User-agent: ias_admantx Allow: / User-agent: DVbot Allow: / User-agent: DoubleVerifyBot Allow: / User-agent: Peer39_crawler Allow: / User-agent: TTD-Content Allow: / User-agent: PubMatic_Crawler Allow: / User-agent: GumGum Allow: / User-agent: AdsBot-Google Allow: / User-agent: AdsBot-Google-Mobile Allow: / User-agent: AdsBot-Google-Mobile-Apps Allow: / User-agent: Google-AdSense-Reachability Allow: / User-agent: adidxbot Allow: / # ============================================ # SOCIAL MEDIA CRAWLERS - Allow (link previews) # ============================================ User-agent: facebookexternalhit Allow: / User-agent: Twitterbot Allow: / User-agent: LinkedInBot Allow: / User-agent: Pinterestbot Allow: / # ============================================ # SEO/SCRAPER BOTS - Block # ============================================ User-agent: ImagesiftBot Disallow: / User-agent: SemrushBot Disallow: / User-agent: SiteAuditBot Disallow: / User-agent: SemrushBot-BA Disallow: / User-agent: SemrushBot-SI Disallow: / User-agent: SemrushBot-SWA Disallow: / User-agent: SemrushBot-CT Disallow: / User-agent: SemrushBot-BM Disallow: / User-agent: SplitSignalBot Disallow: / User-agent: MJ12bot Disallow: / User-agent: dotbot Disallow: / User-agent: RogerBot Disallow: / User-agent: MSIECrawler Disallow: / User-agent: PortalBSpider Disallow: / User-agent: Yahoo Pipes 1.0 Disallow: / User-agent: tadcrawler Disallow: / User-agent: ScoutJet Disallow: / User-agent: AhrefsBot Disallow: / Sitemap: https://calculatorian.com/sitemap.xml