# ================================================================
# Allow full access to major friendly crawlers
# ================================================================
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: AdsBot-Google
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

User-agent: SEMRushBot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Instagram
Allow: /

User-agent: LinkedInbot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: Facebook External Hit
Allow: /

# ================================================================
# General crawling rules for all bots
# ================================================================
User-agent: *
Disallow: /admin/
Disallow: /cart/
Disallow: /carts/
Disallow: /orders/
Disallow: /checkouts/
Disallow: /checkout/
Disallow: /55867801757/checkouts/
Disallow: /55867801757/orders/
Disallow: /account/
Disallow: /policies/
Disallow: /search/
Disallow: /a/downloads/
Disallow: /recommendations/products/
Disallow: /web-pixels-manager
Disallow: /web-pixel-shopify-custom-pixel
Disallow: /custom/web-pixel-shopify-custom-pixel@/
Disallow: /cdn/wpm/
Disallow: /.well-known/shopify/monorail
Disallow: /419
Disallow: /blocked
Disallow: /apple-app-site-association

# Block faceted navigation and duplicate content
Disallow: /*?q=
Disallow: /*?sort_by=
Disallow: /*?filter.
Disallow: /*?orderby=
Disallow: /*?size=
Disallow: /*?wordfence_lh=
Disallow: /*?pr_prod_strat=
Disallow: /*?oseid=
Disallow: /*preview_theme_id
Disallow: /*preview_script_id
Disallow: /*.atom

# Block collection and blog variations
Disallow: /collections/*sort_by*
Disallow: /collections/*+*
Disallow: /collections/*%2B*
Disallow: /collections/*%2b*
Disallow: /collections/*filter*&*filter*
Disallow: /blogs/*+*
Disallow: /blogs/*%2B*
Disallow: /blogs/*%2b*

# ================================================================
# Specific rules for other bots
# ================================================================
User-agent: Nutch
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: AhrefsSiteAudit
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

User-agent: Pinterest
Crawl-delay: 1

# ================================================================
# Sitemap
# ================================================================
Sitemap: https://mattressville.ca/sitemap.xml

# ================================================================
# AI Large Language Model crawling rules
# ================================================================
# LLM crawlers can find our policies at:
# https://mattressville.ca/llms.txt