# Initial attempt to slow crawlers. 
# Not all bots will obey the Crawl-delay, so lets see.

User-agent: CCBot
Allow: /
Crawl-delay: 10

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 10

User-agent: GPTBot
Allow: /
Crawl-delay: 10

User-agent: Google-Extended
Allow: /
Crawl-delay: 10

User-agent: Google-CloudVertexBot
Allow: /
Crawl-delay: 10

User-agent: Applebot-Extended 
Allow: /
Crawl-delay: 10

User-agent: anthropic-ai
Allow: /
Crawl-delay: 10

User-agent: ClaudeBot 
Allow: /
Crawl-delay: 10

User-agent: Omgilibot
Allow: /
Crawl-delay: 10

User-agent: Omgili
Allow: /
Crawl-delay: 10

User-agent: FacebookBot
Allow: /
Crawl-delay: 10

User-agent: Diffbot
Allow: /
Crawl-delay: 10

User-agent: DuckAssistBot
Allow: /
Crawl-delay: 10

User-agent: AI2Bot
Allow: /
Crawl-delay: 10

User-agent: Bytespider
Allow: /
Crawl-delay: 10

User-agent: Kangaroo Bot
Allow: /
Crawl-delay: 10

User-agent: PanguBot
Allow: /
Crawl-delay: 10

User-agent: ImagesiftBot 
Allow: /
Crawl-delay: 10

User-agent: PerplexityBot
Allow: /
Crawl-delay: 10

User-agent: cohere-ai
Allow: /
Crawl-delay: 10

User-agent: cohere-training-data-crawler
Allow: /
Crawl-delay: 10

User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 10

User-agent: Meta-ExternalFetcher
Allow: /
Crawl-delay: 10

User-agent: Timpibot
Allow: /
Crawl-delay: 10

User-agent: Webzio-Extended
Allow: /
Crawl-delay: 10

User-agent: YouBot
Allow: /
Crawl-delay: 10


# These rules from https://meta.wikimedia.org/robots.txt

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /

# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /

# Per their statement, semrushbot respects crawl-delay directives
# We want them to overall stay within reasonable request rates to
# the backend (20 rps); keeping in mind that the crawl-delay will 
# be applied by site and not globally by the bot, 5 seconds seem
# like a reasonable approximation
User-agent: SemrushBot
Crawl-delay: 5

# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
User-agent: *
Allow: /w/api.php?action=mobileview&
Allow: /w/load.php?
Allow: /api/rest_v1/?doc
Allow: /w/rest.php/site/v1/sitemap
Disallow: /w/
Disallow: /api/
Disallow: /wiki/Special: