# ---- AI-related CRAWLERS — Disallow ----

User-agent: AI2Bot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: ImagesiftBot 
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: YandexBot
Disallow: /

User-agent: YandexCalendar
Disallow: /

# ---- TRAINING BOTS — Disallow ----

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: GPTBot
Disallow: /

# ---- SEO CRAWLERS — Disallow ----

User-agent: BLEXBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SeznamBot
Disallow: /

# ---- GENERAL ----

Sitemap: https://smithengineering.queensu.ca/sitemap.xml

User-agent: *

# ---- Disallow (everything) crawling for these folders ----

Disallow: /_cms/
Disallow: /_cms/sandbox/
Disallow: /_cms/test/
Disallow: /_files/
Disallow: /_images/
Disallow: /Governance/

# ---- Allow crawling through folders that redirect to Schema ----

Allow: /programs/
Allow: /people/
Allow: /news/
Allow: /events/
Allow: /research/

# ---- Small Delay ----
Crawl-delay: 10