# ============================ # Global rules for all bots # ============================ User-agent: * # Allow critical assets for rendering Allow: /wp-admin/admin-ajax.php Allow: /*/*.css Allow: /*/*.js Allow: /wp-includes/js/ # Block non-SEO WordPress core areas Disallow: /wp-admin/ Disallow: /wp-includes/ Disallow: /readme.html Disallow: /license.txt Disallow: /xmlrpc.php Disallow: /wp-login.php Disallow: /wp-register.php # Block internal search & low-value parameters Disallow: /search/ Disallow: /?s= Disallow: *?s=* Disallow: *?attachment_id= Disallow: *&preview= # Block WordPress JSON API if not needed for bots Disallow: /wp-json/ Disallow: /?rest_route= # Block feeds & comment noise (optional but good for crawl budget) Disallow: /feed/ Disallow: /comments/feed Disallow: */feed Disallow: /?feed= Disallow: /wp-feed # Block spammy comment/trackback URLs Disallow: /trackback/ Disallow: */trackback Disallow: */comments$ Disallow: /wp-comments Disallow: /wp-trackback Disallow: */replytocom= # ============================ # Sitemaps (important for SEO) # ============================ Sitemap: https://techfusiongear.com/post-sitemap.xml Sitemap: https://techfusiongear.com/page-sitemap.xml # ============================ # Block SEO/scanner/link bots # (bandwidth savers, not “good” for you) # ============================ User-agent: AhrefsBot Disallow: / User-agent: rogerbot Disallow: / User-agent: MJ12bot Disallow: / User-agent: Xenu Disallow: / # ============================ # Block unwanted scrapers # (condensed list – keep only what you really see in logs) # ============================ User-agent: DotBot Disallow: / User-agent: Dataprovider Disallow: / User-agent: DataproviderSiteExplorer Disallow: / User-agent: DomainStatsBot Disallow: / User-agent: BUbiNG Disallow: / User-agent: 008 Disallow: / User-agent: feedly Disallow: / User-agent: FeedlyBot Disallow: / User-agent: Feedspot Disallow: / User-agent: Feedspotbot Disallow: / User-agent: Discobot Disallow: / # ============================ # Archive.org / Wayback Machine # ============================ User-agent: ia_archiver Disallow: / User-agent: archive.org_bot Disallow: / User-agent: ia_archiver-web.archive.org Disallow: / # ============================ # Block popular AI crawlers (optional – tweak to your strategy) # ============================ User-agent: GPTBot Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Meta-ExternalAgent Disallow: / User-agent: Amazonbot Disallow: / User-agent: CCBot Disallow: / User-agent: PerplexityBot Disallow: / Sitemap: https://techfusiongear.com/sitemap_index.xml