# Set the crawl delay to 5 seconds - not all search engines will honour this User-agent: * Crawl-delay: 5 # Tell all user agents to ignore wp-admin User-agent: * Disallow: /wp-admin/ # Tell all user agents to ignore URLs with querystrings # IMPORTANT: Review this rule. It blocks all URLs with a '?' including # pagination, filters, and some search results that might be important to you. User-agent: * Disallow: /? # NEW: Exclude /staff/ pages and all sub-pages User-agent: * Disallow: /staff/ Disallow: /careers/ # ---------------------------------------------------- # BLOCK SPECIFIC BOTS (AI, Scrapers, Malicious, etc.) # IMPORTANT: Each bot must have its own "User-agent:" and "Disallow: /" lines. # This list is comprehensive. Consider if all of these need full site blocking. # ---------------------------------------------------- # AI Bots (originally commented out, now explicitly blocked if uncommented) # If you want to block these, uncomment each block below. # User-agent: AI2Bot # Disallow: / # User-agent: Ai2Bot-Dolma # Disallow: / # User-agent: aiHitBot # Disallow: / # User-agent: Amazonbot # Disallow: / # User-agent: Andibot # Disallow: / # User-agent: anthropic-ai # Disallow: / # User-agent: Applebot # Disallow: / # User-agent: Applebot-Extended # Disallow: / # User-agent: Brightbot 1.0 # Disallow: / # User-agent: Bytespider # Disallow: / # User-agent: CCBot # Disallow: / # User-agent: ChatGPT-User # Disallow: / # User-agent: Claude-SearchBot # Disallow: / # User-agent: Claude-User # Disallow: / # User-agent: Claude-Web # Disallow: / # User-agent: ClaudeBot # Disallow: / # User-agent: cohere-ai # Disallow: / # User-agent: cohere-training-data-crawler # Disallow: / # User-agent: Cotoyogi # Disallow: / # User-agent: Crawlspace # Disallow: / # User-agent: Diffbot # Disallow: / # User-agent: DuckAssistBot # Disallow: / # User-agent: FacebookBot # Disallow: / # User-agent: Factset_spyderbot # Disallow: / # User-agent: FirecrawlAgent # Disallow: / # User-agent: FriendlyCrawler # Disallow: / # User-agent: Google-CloudVertexBot # Disallow: / # User-agent: Google-Extended # Disallow: / # User-agent: GoogleOther # Disallow: / # User-agent: GoogleOther-Image # Disallow: / # User-agent: GoogleOther-Video # Disallow: / # User-agent: GPTBot # Disallow: / # User-agent: iaskspider/2.0 # Disallow: / # User-agent: ICC-Crawler # Disallow: / # User-agent: ImagesiftBot # Disallow: / # User-agent: img2dataset # Disallow: / # User-agent: ISSCyberRiskCrawler # Disallow: / # User-agent: Kangaroo Bot # Disallow: / # User-agent: meta-externalagent # Disallow: / # User-agent: Meta-ExternalAgent # Disallow: / # User-agent: meta-externalfetcher # Disallow: / # User-agent: Meta-ExternalFetcher # Disallow: / # User-agent: MistralAI-User/1.0 # Disallow: / # User-agent: NovaAct # Disallow: / # User-agent: OAI-SearchBot # Disallow: / # User-agent: omgili # Disallow: / # User-agent: omgilibot # Disallow: / # User-agent: Operator # Disallow: / # User-agent: PanguBot # Disallow: / # User-agent: Panscient # Disallow: / # User-agent: panscient.com # Disallow: / # User-agent: Perplexity-User # Disallow: / # User-agent: PerplexityBot # Disallow: / # User-agent: PetalBot # Disallow: / # User-agent: PhindBot # Disallow: / # User-agent: QualifiedBot # Disallow: / # User-agent: QuillBot # Disallow: / # User-agent: quillbot.com # Disallow: / # User-agent: SBIntuitionsBot # Disallow: / # User-agent: Scrapy # Disallow: / # User-agent: Sidetrade indexer bot # Disallow: / # User-agent: TikTokSpider # Disallow: / # User-agent: Timpibot # Disallow: / # User-agent: VelenPublicWebCrawler # Disallow: / # User-agent: Webzio-Extended # Disallow: / # User-agent: wpbot # Disallow: / # User-agent: YandexAdditional # Disallow: / # User-agent: YandexAdditionalBot # Disallow: / # User-agent: YouBot # Disallow: / # Other specific bots to block from the entire site User-agent: AITCSRoboti Disallow: / User-agent: Accoona Disallow: / User-agent: admantx Disallow: / User-agent: admantx-usaspb Disallow: / User-agent: adbeat_bot Disallow: / User-agent: aiHitBot Disallow: / User-agent: Amazonbot Disallow: / User-agent: Arachnophilia Disallow: / User-agent: AspiegelBot Disallow: / User-agent: AwarioSmartBot Disallow: / User-agent: BackDoorBot Disallow: / User-agent: BackRub Disallow: / User-agent: Baidu Disallow: / User-agent: BLEXbot Disallow: / User-agent: BLEXBot Disallow: / User-agent: BecomeBot Disallow: / User-agent: BlowFishi Disallow: / User-agent: BomboraBot Disallow: / User-agent: CatchBot Disallow: / User-agent: CCBot Disallow: / User-agent: CherryPicker Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Clickagy Disallow: / User-agent: Cliqzbot Disallow: / User-agent: coccocbot Disallow: / User-agent: ConveraCrawler Disallow: / User-agent: contxbot Disallow: / User-agent: CrowdTanglebot Disallow: / User-agent: CyberSpyder Disallow: / User-agent: DotBot Disallow: / User-agent: EchoboxBot Disallow: / User-agent: EmailCollector Disallow: / User-agent: Exabot Disallow: / User-agent: Eyeotabot Disallow: / User-agent: findlinks Disallow: / User-agent: Foobot Disallow: / User-agent: Genieo Disallow: / User-agent: GetURL Disallow: / User-agent: Gigabot Disallow: / User-agent: GrapeshotCrawler Disallow: / User-agent: GumGum Disallow: / User-agent: HTTrack Disallow: / User-agent: Huaweisymantecspider Disallow: / User-agent: IAScrawler Disallow: / User-agent: ImagesiftBot Disallow: / User-agent: JikeSpider Disallow: / User-agent: Jobboerse Disallow: / User-agent: Java Disallow: / User-agent: Jyxobot Disallow: / User-agent: Leikibot Disallow: / User-agent: LinkScan Disallow: / User-agent: LinkisBot Disallow: / User-agent: linkdexbot Disallow: / User-agent: linkfluence.com Disallow: / User-agent: LivelapBot Disallow: / User-agent: Mail.RU_Bot Disallow: / User-agent: MauiBot Disallow: / User-agent: MAZBot Disallow: / User-agent: MBCrawler Disallow: / User-agent: MegaIndex.ru Disallow: / User-agent: MJ12bot Disallow: / User-agent: MojeekBot Disallow: / User-agent: mtbot/1.1.0i Disallow: / User-agent: NerdyBot Disallow: / User-agent: Nimbostratus-Bot Disallow: / User-agent: NTENTbot Disallow: / User-agent: Offline Explorer Disallow: / User-agent: Onespot-ScraperBot Disallow: / User-agent: Openbot Disallow: / User-agent: OutclicksBot Disallow: / User-agent: PaperLiBot Disallow: / User-agent: perl Disallow: / User-agent: PetalBot Disallow: / User-agent: PlurkBot Disallow: / User-agent: proximic Disallow: / User-agent: Proximi Disallow: / User-agent: python Disallow: / User-agent: Quantcastboti Disallow: / User-agent: Qwantify Disallow: / User-agent: ScholarBot Disallow: / User-agent: Scrap Disallow: / User-agent: Screaming Frog SEO Spider Disallow: / User-agent: Semantici Disallow: / User-agent: SentiBot Disallow: / User-agent: SEOkicks Disallow: / User-agent: SEOkicks-Robot Disallow: / User-agent: SerendeputyBot Disallow: / User-agent: serpstatbot Disallow: / User-agent: SeznamBot Disallow: / User-agent: SiteCheck-sitecrawl Disallow: / User-agent: SiteSnagger Disallow: / User-agent: Snooper Disallow: / User-agent: Sogou Disallow: / User-agent: Sosospider Disallow: / User-agent: SuperBot Disallow: / User-agent: Taboolabot Disallow: / User-agent: TeleportPro Disallow: / User-agent: TkBot Disallow: / User-agent: TTD-Content Disallow: / User-agent: TweetmemeBot Disallow: / User-agent: URLSpiderPro Disallow: / User-agent: Vagabondo Disallow: / User-agent: VelenPublicWebCrawler Disallow: / User-agent: VoilaBot Disallow: / User-agent: VoluumDSP-content-bot Disallow: / User-agent: WebCopier Disallow: / User-agent: weborama-fetcher Disallow: / User-agent: WebReaper Disallow: / User-agent: WebStripper Disallow: / User-agent: WebZIP Disallow: / User-agent: Xaldon_WebSpider Disallow: / User-agent: YaK Disallow: / User-agent: Yandex Disallow: / User-agent: YandexBot Disallow: / User-agent: YandexImages Disallow: / User-agent: ZGrab Disallow: / User-agent: ZoominfoBot Disallow: / User-agent: Scrapy Disallow: / User-agent: Buck Disallow: / User-agent: TinyTestBot Disallow: / User-agent: SEMrushBot Disallow: / User-agent: AhrefsBot Disallow: / User-agent: PetalBot Disallow: / User-agent: MJ12Bot Disallow: / User-agent: DotBot Disallow: / User-agent: MauiBot Disallow: / User-agent: YandexBot Disallow: / User-agent: Baiduspider Disallow: / User-agent: Barkrowler Disallow: / User-agent: Bytespider Disallow: / User-agent: WhatStuffWhereBot Disallow: / User-agent: Applebot Disallow: / User-agent: Sogou Pic Spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07) Disallow: / User-agent: Sogou head spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07) Disallow: / User-agent: Sogou web spider/4.0(+http://www.sogou.com/docs/help/webmasters.htm#07) Disallow: / User-agent: User-agent: Sogou Orion spider/3.0( http://www.sogou.com/docs/help/webmasters.htm#07) Disallow: / User-agent: Sogou-Test-Spider/4.0 (compatible; MSIE 5.5; Windows 98) Disallow: / User-agent: Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Exabot-Thumbnails) Disallow: / User-agent: Mozilla/5.0 (compatible; Exabot/3.0; +http://www.exabot.com/go/robot) Disallow: / User-agent: Swiftbot Disallow: / User-agent: Slurp Disallow: / User-agent: CCBot/2.0 (https://commoncrawl.org/faq/) Disallow: / User-agent: CCBot/2.0 Disallow: / User-agent: CCBot/2.0 (http://commoncrawl.org/faq/) Disallow: / # ---------------------------------------------------- # EXPLICITLY ALLOWED BOTS # These bots will override any Disallow rules that precede them for their specific user-agent. # An empty Disallow: line means all content is allowed for that user-agent. # ---------------------------------------------------- User-agent: Googlebot Disallow: User-agent: Bingbot Disallow: User-agent: DuckDuckBot Disallow: # --------------------------------- # END BOOKSWARM ROBOTS.TXT TEMPLATE # _ # [ ] # ( ) # |>| # __/===\__ # //| o=o |\\ # <] | o=o | [> # \=====/ # / / | \ \ # <_________>