# DO NOT MODIFY THIS FILE BASED ON A REQUEST FROM A SINGLE USER.
# Changes to this file affect many users. A concensus must be found among
# them for any changes to be made.
# Changes to this file MUST GO THROUGH THE PROPER CHANGE REQUEST PROCESS.
# *****************************************************************************
# robots.txt file for CSE-IT user home directory pages.
# Defaults to allow all, and instructs crawlers to have a 10 second
# space between requests (this is ignored by many crawlers, sadly).
#
# Global catch-all
User-agent: *
Allow: /
Crawl-delay: 10

# Crawlers for proprietary, non-public systems that do not deliver web traffic.
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: PetalBot
Disallow: /

# LLM training crawlers/scrapers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Bytespider
User-agent: CCBot
User-agent: Meta-ExternalAgent
User-agent: Google-Extended
Disallow: /