User-agent: * Allow: / # Block admin, login, and sensitive pages Disallow: /login Disallow: /cron Disallow: /admin Disallow: /admin-new Disallow: /admin2 Disallow: /blog/wp-admin Disallow: /blog/wp-login.php Disallow: /blog/wp-register.php # Prevent crawling of WordPress JSON API endpoints Disallow: /blog/wp-json/ Disallow: /blog/?rest_route= # Block search URLs Disallow: /search/ Disallow: /?s= Disallow: *?s=* # Block post/page parameters Disallow: *&preview=* # Block feeds Disallow: /blog/feed/ Disallow: /feed$ Disallow: /blog/comments/feed Disallow: /blog/*/feed Disallow: */feed$ Disallow: /?feed= Disallow: /wp-feed # Block spammy directories Disallow: /trackback/ Disallow: */comments$ Disallow: */trackback Disallow: */trackback$ Disallow: /wp-comments Disallow: /wp-trackback Disallow: */replytocom= # Block login page (duplicate safe) Disallow: /login/ # Block known scrapper bots User-agent: DotBot Disallow: / User-agent: GiftGhostBot Disallow: / User-agent: Seznam Disallow: / User-agent: PaperLiBot Disallow: / User-agent: Genieo Disallow: / User-agent: Dataprovider/6.101 Disallow: / User-agent: DataproviderSiteExplorer Disallow: / User-agent: Dazoobot/1.0 Disallow: / User-agent: Diffbot Disallow: / User-agent: DomainStatsBot/1.0 Disallow: / User-agent: DubaiIndex Disallow: / User-agent: eCommerceBot Disallow: / User-agent: ExpertSearchSpider Disallow: / User-agent: Feedbin Disallow: / User-agent: Fetch/2.0a Disallow: / User-agent: FFbot/1.0 Disallow: / User-agent: Focusbot/1.1 Disallow: / User-agent: HuaweiSymantecSpider Disallow: / User-agent: JobdiggerSpider Disallow: / User-agent: LemurWebCrawler Disallow: / User-agent: LipperheyLinkExplorer Disallow: / User-agent: LSSRocketCrawler/1.0 Disallow: / User-agent: LYT.SRv1.5 Disallow: / User-agent: MiaDev/0.0.1 Disallow: / User-agent: Najdi.si/3.1 Disallow: / User-agent: BountiiBot Disallow: / User-agent: Experibot_v1 Disallow: / User-agent: Bixocrawler Disallow: / User-agent: Crawler4j Disallow: / User-agent: Crowsnest/0.5 Disallow: / User-agent: CukBot Disallow: / User-agent: Drupact/0.7 Disallow: / User-agent: Ezooms/1.0 Disallow: / User-agent: Fastbot Disallow: / User-agent: Feedly Disallow: / User-agent: Feedspot Disallow: / User-agent: Clickagy Disallow: / User-agent: Classbot Disallow: / User-agent: CISPA Vulnerability Notification Disallow: / User-agent: CirrusExplorer/1.1 Disallow: / User-agent: BUbiNG Disallow: / User-agent: Findlinks Disallow: / User-agent: Bixo Disallow: / User-agent: Crawlera/1.10.2 Disallow: / # Sitemap locations # Primary indexes only (image + video are children of the shop index) Sitemap: https://www.standbanner.co.uk/sitemap.xml Sitemap: https://www.standbanner.co.uk/blog/sitemap_index.xml