User-agent: *
Allow: /

# Don't index admin and internal endpoints
Disallow: /admin/
Disallow: /captcha/
Disallow: /analytics/
Disallow: /ipns/
Disallow: /api/rating/
Disallow: /api/newsletter/

# Tracking-only query params — every internal-link click was getting indexed
# as a distinct duplicate URL with proper canonical to the bare path. The
# canonical was working, but Google still spent crawl budget on variants.
# Blocking the crawl here cuts that to zero. Both ?param= and &param= forms
# are blocked since either can appear depending on whether the param is first
# in the query string.
Disallow: /*?ref=
Disallow: /*&ref=
Disallow: /*?from=
Disallow: /*&from=
Disallow: /*?next=
Disallow: /*&next=
Disallow: /*?return=
Disallow: /*&return=
Disallow: /*?sort=
Disallow: /*&sort=
Disallow: /*?utm_
Disallow: /*&utm_
Disallow: /*?gclid=
Disallow: /*&gclid=
Disallow: /*?fbclid=
Disallow: /*&fbclid=
Disallow: /*?msclkid=
Disallow: /*&msclkid=

# `?lang=en` is the default language with a redundant param. Server-side
# middleware also 301s these to the bare path; Disallow stops Google from
# finding them in the first place.
Disallow: /*?lang=en
Disallow: /*&lang=en

# Clicky first-party analytics beacon (proxied, same-origin) — Googlebot
# re-crawls /3313609894e7?site_id=... + loader as junk 200s, crawl-budget waste.
# Crawl directive only; analytics unaffected. See ~/seo/playbook/06.
Disallow: /3313609894e7
Disallow: /ee3e0327e314.js

Sitemap: https://www.vps.org/sitemap.xml