User-agent: *
Disallow: /checkout/
Disallow: /customer/
Disallow: /search/
Disallow: /catalogsearch/
Disallow: /wishlist/
Disallow: /review/
Disallow: /blog/tag/
Disallow: /blog/archive/

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

# Block specific bots identified in logs or common aggressive crawlers
User-agent: Slackbot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: Rogerbot
Disallow: /

# Standard Magento Security & Performance Exclusions for all other bots
User-agent: *
# Protected Directories
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /phpserver/
Disallow: /pub/
Disallow: /var/
Disallow: /vendor/
Disallow: /setup/
Disallow: /update/

# Technical Paths
Disallow: /cgi-bin/
Disallow: /errors/
Disallow: /includes/
Disallow: /magento/
Disallow: /shell/

# Magento Native Catalog and Search Protection
Disallow: /catalogsearch/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalog/product/view/
Disallow: /catalog/product/gallery/

# Checkout and Customer Account Protection
Disallow: /checkout/
Disallow: /onestepcheckout/
Disallow: /customer/
Disallow: /customer/account/
Disallow: /customer/account/login/
Disallow: /wishlist/

# Block probing paths identified in logs
Disallow: /adminer*
Disallow: /phpmyadmin*
Disallow: /_adminer*
Disallow: /sqlnet.log
Disallow: /.env*

# Prevent crawling of common dynamic parameters
Disallow: /*?SID=
Disallow: /*?dir=
Disallow: /*?mode=
Disallow: /*?limit=
Disallow: /*?order=

# Block Meta AI training and scraping crawlers
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-webindexer
Disallow: /

User-agent: facebookexternalhit
Disallow: /

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

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