# Allow all user-agents
User-agent: *

# Block access to the following sensitive directories
Disallow: /app/
Disallow: /bin/
Disallow: /dev/
Disallow: /lib/
Disallow: /pkginfo/
Disallow: /var/
Disallow: /setup/
Disallow: /pub/errors/
Disallow: /pub/static/
Disallow: /pub/media/
Disallow: /generated/

# Block admin pages and other internal URLs
Disallow: /admin/
Disallow: /customer/
Disallow: /checkout/
Disallow: /onestepcheckout/
Disallow: /cart/
Disallow: /customer/account/
Disallow: /customer/account/login/
Disallow: /customer/account/create/
Disallow: /wishlist/
Disallow: /catalog/product_compare/
Disallow: /catalog/category/view/
Disallow: /catalogsearch/
Disallow: /search/

# Block URLs for sorting, filtering, and search result pages
Disallow: /*?dir=*
Disallow: /*?limit=*
Disallow: /*?mode=*
Disallow: /*?order=*
Disallow: /*?price=*
Disallow: /*?cat=*
Disallow: /*?q=*
Disallow: /*?*retailstore*

# Block common query strings
Disallow: /*?SID=
Disallow: /*?___from_store=
Disallow: /*?___store=
Disallow: /*?___currency=

# Allow indexing of important pages
Allow: /pub/media/
Allow: /pub/static/
Allow: /static/frontend/
Allow: /media/catalog/
Allow: /skin/frontend/

# Block AhrefsBot
User-agent: AhrefsBot
User-agent: AhrefsBot/7.0
User-agent: SemrushBot/7~bl
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Brightbot 1.0
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Crawlspace
User-agent: Diffbot
User-agent: DuckAssistBot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GoogleOther-Image
User-agent: GoogleOther-Video
User-agent: GPTBot
User-agent: iaskspider/2.0
User-agent: ICC-Crawler
User-agent: ImagesiftBot
User-agent: img2dataset
User-agent: ISSCyberRiskCrawler
User-agent: Kangaroo Bot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: omgilibot
User-agent: PanguBot
User-agent: PerplexityBot
User-agent: Perplexity‑User
User-agent: PetalBot
User-agent: Scrapy
User-agent: SemrushBot-OCOB
User-agent: SemrushBot-SWA
User-agent: Sidetrade indexer bot
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: YouBot
Disallow: /
Sitemap: https://www.michaelchell.co.uk/pub/sitemap.xml