# Block all known AI crawlers and assistants
# from using content for training AI models.
# Source: https://robotstxt.com/ai
User-Agent: GPTBot
User-Agent: ClaudeBot
User-Agent: Claude-User
User-Agent: Claude-SearchBot
User-Agent: CCBot
User-Agent: Google-Extended
User-Agent: Applebot-Extended
User-Agent: Facebookbot
User-Agent: Meta-ExternalAgent
User-Agent: Meta-ExternalFetcher
User-Agent: meta-webindexer
User-Agent: diffbot
User-Agent: PerplexityBot
User-Agent: Perplexity‑User
User-Agent: Omgili
User-Agent: Omgilibot
User-Agent: webzio-extended
User-Agent: ImagesiftBot
User-Agent: Bytespider
User-Agent: TikTokSpider
User-Agent: Amazonbot
User-Agent: Youbot
User-Agent: SemrushBot-OCOB
User-Agent: Petalbot
User-Agent: VelenPublicWebCrawler
User-Agent: TurnitinBot
User-Agent: Timpibot
User-Agent: OAI-SearchBot
User-Agent: ICC-Crawler
User-Agent: AI2Bot
User-Agent: AI2Bot-Dolma
User-Agent: DataForSeoBot
User-Agent: AwarioBot
User-Agent: AwarioSmartBot
User-Agent: AwarioRssBot
User-Agent: Google-CloudVertexBot
User-Agent: PanguBot
User-Agent: Kangaroo Bot
User-Agent: Sentibot
User-Agent: img2dataset
User-Agent: Meltwater
User-Agent: Seekr
User-Agent: peer39_crawler
User-Agent: cohere-ai
User-Agent: cohere-training-data-crawler
User-Agent: DuckAssistBot
User-Agent: Scrapy
User-Agent: Cotoyogi
User-Agent: aiHitBot
User-Agent: Factset_spyderbot
User-Agent: FirecrawlAgent

Disallow: /
DisallowAITraining: /

# Block any non-specified AI crawlers (e.g., new
# or unknown bots) from using content for training
# AI models, while allowing the website to be
# indexed and accessed by bots.  These directives
# are still experimental and may not be supported
# by all AI crawlers.
User-Agent: *
DisallowAITraining: /
Content-Usage: ai=n
Allow: /

#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
Crawl-delay: 10
# CSS, JS, Images
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png
Allow: /modules/*.css$
Allow: /modules/*.css?
Allow: /modules/*.js$
Allow: /modules/*.js?
Allow: /modules/*.gif
Allow: /modules/*.jpg
Allow: /modules/*.jpeg
Allow: /modules/*.png
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /themes/*.css$
Allow: /themes/*.css?
Allow: /themes/*.js$
Allow: /themes/*.js?
Allow: /themes/*.gif
Allow: /themes/*.jpg
Allow: /themes/*.jpeg
Allow: /themes/*.png
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/
# Paths (no clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/