# robots.txt for https://www.alomone.com/ (https://www.alomone.com/)
# Goal: allow SEO pages, block lowvalue commerce, account, search and filter URLs.
User-agent: *
# Account, cart, checkout and quote flows
Disallow: /customer/
Disallow: /checkout/
Disallow: /onestepcheckout/
Disallow: /sales/
Disallow: /wishlist/
Disallow: /negotiable_quote/
Disallow: /quote/
# Internal search and comparison
Disallow: /catalogsearch/
Disallow: /search/
Disallow: /catalog/product_compare/
# Magento/system paths
Disallow: /admin/
Disallow: /backend/
Disallow: /app/
Disallow: /var/
Disallow: /vendor/
Disallow: /lib/
Disallow: /pkginfo/
Disallow: /report/
Disallow: /setup/
Disallow: /update/
Disallow: /dev/
Disallow: /errors/
Disallow: /index.php/
Disallow: /rest/
Disallow: /graphql
Disallow: /api/
# User-generated or low-value utility paths
Disallow: /review/
Disallow: /sendfriend/

Disallow: /newsletter/
Disallow: /paypal/
# Session IDs and common faceted/filter/sort parameters
Disallow: /*SID=
Disallow: /*?SID=
Disallow: /*?dir=
Disallow: /*?order=
Disallow: /*?limit=
Disallow: /*?mode=
Disallow: /*?price=
Disallow: /*?manufacturer=
Disallow: /*?cat=
# Layered-nav multi-select filter combinations (crawler traps: cat[0]=..&cat[1]=..
# and products_categories=..; meta-externalagent/GPTBot walked millions of combos)
Disallow: /*?cat%5B
Disallow: /*&cat%5B
Disallow: /*?cat[
Disallow: /*&cat[
Disallow: /*products_categories=
Disallow: /*?product_list_
Disallow: /*?q=
Disallow: /*?search=
Disallow: /*?___store=
Disallow: /*?___from_store=
# Keep crawl-critical assets open for rendering
Allow: /media/
Allow: /static/
Allow: /pub/media/
Allow: /pub/static/
# Keep key public SEO sections open
# NOTE: the $ is required. A bare "Allow: /categories" prefix-matches every URL
# under /categories and, being longer than the /*?cat%5B-style Disallow patterns,
# WINS the RFC 9309 longest-match tie-break - silently re-allowing every filter
# URL the section above tries to block. With $ they allow the landing pages only
# (sub-pages are allowed by default anyway).
Allow: /categories$
Allow: /categories/product-portfolio$
Allow: /blog
Allow: /protocols
Allow: /citations-search-tool
Allow: /panel-builder
Allow: /mw-calculator
Allow: /contact-us
Allow: /privacy-policy
Allow: /terms-of-use
Sitemap: https://www.alomone.com/sitemap.xml
# Sitemap location (the Sitemap: line itself is auto-appended by Magento from the XML-sitemap config)
# AI crawlers: clean pages only - never parameterized URLs. A named group REPLACES
# the * group for these agents, so this one rule is their entire policy: after the
# cat%5B 403s (2026-07-06) GPTBot just moved to a pagination trap (?p=..) on another
# category - any query string is crawl-waste for these bots. meta-webindexer added
# 2026-07-12: Meta's successor crawler resumed the exact same filter-combo walk
# (79/day -> 20k/day within 48h, 99.2% of hits carrying a query string).
User-agent: GPTBot
User-agent: meta-externalagent
User-agent: meta-webindexer
Disallow: /*?
Sitemap: https://www.alomone.com/media/sitemap/sitemap.xml