# For all robots
User-agent: *

# Block access to specific groups of pages
Disallow: /results$
Disallow: /results?

# Block excessive pagination to prevent crawl budget waste
Disallow: /*?page=
Disallow: /*&page=

# Block tracking parameters to reduce duplicate URLs
Disallow: /*?utm_
Disallow: /*&utm_
Disallow: /*?cid=
Disallow: /*&cid=
Disallow: /*?bid=
Disallow: /*&bid=

# Allow search crawlers to discover the sitemap
Sitemap: https://www.aldi.ie/sitemap.xml
Categories Sitemap:  https://www.aldi.ie/sitemap_categories.xml

# Block CazoodleBot as it does not present correct accept content headers
User-agent: CazoodleBot
Disallow: /

# Block MJ12bot as it is just noise
User-agent: MJ12bot
Disallow: /

# Block dotbot as it cannot parse base URLs properly
User-agent: dotbot/1.0
Disallow: /

# Block Gigabot
User-agent: Gigabot
Disallow: /