# robots.txt for https://gmelius.com
# ------------------------------------------------------------------
# 1. GLOBAL RULES – WHAT EVERY CRAWLER MAY / MAY NOT FETCH
# ------------------------------------------------------------------
User-agent: *
# — Everything public is crawlable by default
Allow: /
# --- BLOCK internal search, previews, and other thin pages -------
Disallow: /search # Webflow on-site search results
Disallow: /*?query= # Alt query parameter for search
Disallow: /*?s= # Legacy query parameter copies
Disallow: /preview/ # Any staging or preview folders
Disallow: /*?preview=* # Preview query strings
# --- BLOCK duplicate tracking-parameter URLs ---------------------
Disallow: /*?utm_*
Disallow: /*&utm_*
Disallow: /*?ref=*
Disallow: /*&ref=*
Disallow: /*?fbclid=*
Disallow: /*?gclid=*
Disallow: /*?mc_cid=*
Disallow: /*?mc_eid=*
# --- OPTIONAL: clean out tracking params for Google --------------
# (ignored by Bing/Yandex, but worthwhile for Googlebot)
Clean-param: utm_source&utm_medium&utm_campaign&utm_term&utm_content&fbclid&gclid&ref
# ------------------------------------------------------------------
# 2. GOOGLE SPECIALTY BOTS – inherit * rules, no extra blocks
# ------------------------------------------------------------------
User-agent: Googlebot-Image
Disallow:
User-agent: Googlebot-News
Disallow:
# ------------------------------------------------------------------
# 3. LARGE THIRD-PARTY SEO CRAWLERS – slow them down politely
# ------------------------------------------------------------------
User-agent: AhrefsBot
Crawl-delay: 10
User-agent: SemrushBot
Crawl-delay: 10
User-agent: MJ12bot
Crawl-delay: 10
# ------------------------------------------------------------------
# 4. YANDEX – optional 'Host' directive (ignored by others)
# ------------------------------------------------------------------
Host: gmelius.com
Sitemap: https://gmelius.com/sitemap.xml