# robots.txt for https://bodhaka.org/ # Place this file at the site root so it is served from: # https://bodhaka.org/robots.txt # # Purpose: # 1. Tell every well-behaved crawler that the entire site is # allowed to be crawled. # 2. Explicitly allow CSS, JS and image assets so Googlebot # can render the page as a real user would. Blocking these # is a common, silent SEO killer. # 3. Point search engines at the sitemap. User-agent: * Allow: / # Explicit asset allowances (defensive — some hosts ship templates # that block these by default). Allow: /assets/ Allow: /images/ Allow: /videos/ Allow: /*.css$ Allow: /*.js$ Allow: /*.svg$ Allow: /*.png$ Allow: /*.jpg$ Allow: /*.jpeg$ Allow: /*.webp$ Allow: /*.mp4$ # Block typical noise paths if they ever exist. Safe to keep even # if the paths are not present today. Disallow: /admin/ Disallow: /wp-admin/ Disallow: /*?utm_* Disallow: /*?fbclid= Disallow: /*?gclid= # Sitemap discovery — Google, Bing, DuckDuckGo and others read this. Sitemap: https://bodhaka.org/sitemap.xml