# Ministry of Cannabis - robots.txt
# Goal: block sensitive/low-value areas BUT allow crawling of static assets (CSS/JS/images/fonts),
# including those served from plugins/themes/wp-includes and with query strings (?ver=...)

User-agent: *

############################################################
# 1) ALWAYS ALLOW STATIC ASSETS (with or without querystring)
############################################################

# Common assets
Allow: /*.css$
Allow: /*.css?
Allow: /*.css?*
Allow: /*.js$
Allow: /*.js?
Allow: /*.js?*
Allow: /*.map$
Allow: /*.map?*
Allow: /*.svg$
Allow: /*.svg?*
Allow: /*.png$
Allow: /*.png?*
Allow: /*.jpg$
Allow: /*.jpg?*
Allow: /*.jpeg$
Allow: /*.jpeg?*
Allow: /*.gif$
Allow: /*.gif?*
Allow: /*.webp$
Allow: /*.webp?*
Allow: /*.ico$
Allow: /*.ico?*

# Fonts
Allow: /*.woff$
Allow: /*.woff?*
Allow: /*.woff2$
Allow: /*.woff2?*
Allow: /*.ttf$
Allow: /*.ttf?*
Allow: /*.eot$
Allow: /*.eot?*

# WordPress asset directories (important for Google “blocked resources” issues)
Allow: /wp-content/uploads/
Allow: /wp-content/plugins/
Allow: /wp-content/themes/
Allow: /wp-includes/

############################################################
# 2) BLOCK SENSITIVE / LOW-VALUE AREAS
############################################################

# Core sensitive endpoints
Disallow: /wp-admin/
Disallow: /cgi-bin/
Disallow: /xmlrpc.php

# Attachments / comments / trackbacks
Disallow: /*/attachment/
Disallow: /comments/
Disallow: /trackback
Disallow: /*trackback
Disallow: /*trackback*
Disallow: /*/trackback

# Blog/archive/tag pagination (as you had)
Disallow: /blog/tag/
Disallow: /archive/
Disallow: /archives/
Disallow: /tag/*/page/
Disallow: /tag/*/feed/
Disallow: /page/

# Parameter-based URLs (DON'T block all ? — it breaks ?ver= assets)
Disallow: /*?s=
Disallow: /?s=
Disallow: /*?attachment_id*
Disallow: /*?amp=1

# Site-specific paths you listed
Disallow: */customer/account/*
Disallow: */seed-finder*
Disallow: */moc_size/
Disallow: */moczoo/*

# If this is Magento legacy/no longer used, keep or remove (you had it)
Disallow: /pub/media/

############################################################
# 3) FEEDS RULES (kept, but structured)
############################################################

# If you truly want to allow only the root feed, keep this:
Allow: /feed/$

# Block other feeds
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /*/feed/rss/
Disallow: /*/feed/$
Disallow: /*/feed/rss/$

############################################################
# 4) CRAWL DELAYS FOR SPECIFIC BOTS
############################################################

User-agent: noxtrumbot
Crawl-delay: 20

User-agent: msnbot
Crawl-delay: 20

User-agent: Slurp
Crawl-delay: 20

############################################################
# 5) BLOCK “LOW VALUE” / OFFLINE COPYING BOTS (as you had)
############################################################

User-agent: MSIECrawler
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: libwww
Disallow: /

User-agent: Orthogaffe
Disallow: /

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: wget
Disallow: /

User-agent: grub-client
Disallow: /

User-agent: k2spider
Disallow: /

User-agent: NPBot
Disallow: /

User-agent: WebReaper
Disallow: /

############################################################
# 6) GOOGLEBOT EXTRA SAFETY (optional, but fine to keep)
############################################################

User-agent: Googlebot
Allow: /*.css$
Allow: /*.js$
Allow: /*.css?*
Allow: /*.js?*

############################################################
# 7) SITEMAP
############################################################

Sitemap: https://www.ministryofcannabis.com/sitemap.xml