# See http://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file

# Allow crawling of main pages
User-agent: *
Allow: /
Allow: /play
Allow: /about
Allow: /books
Allow: /educators
Allow: /contact

# Disallow crawling of filtered/parameterized exercise pages
# These create infinite crawl paths and overwhelm the server
Disallow: /play?
Disallow: /en/play?
Disallow: /fi/play?
Disallow: /de/play?
Disallow: /ja/play?
Disallow: /nl/play?
Disallow: /pl/play?
Disallow: /it/play?
Disallow: /lt/play?
Disallow: /lv/play?
Disallow: /ua/play?
Disallow: /dk/play?
Disallow: /no/play?
Disallow: /ro/play?

# Disallow admin area
Disallow: /admin

# Rate limit aggressive crawlers
User-agent: Baiduspider
Crawl-delay: 10
Disallow: /play?
Disallow: /en/play?

User-agent: Applebot
Crawl-delay: 5
Disallow: /play?
Disallow: /en/play?

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10