# As a condition of accessing this website, you agree to abide by the following
# content signals:
# (a) If a Content-Signal = yes, you may collect content for the corresponding
# use.
# (b) If a Content-Signal = no, you may not collect content for the
# corresponding use.
# (c) If the website operator does not include a Content-Signal for a
# corresponding use, the website operator neither grants nor restricts
# permission via Content-Signal with respect to the corresponding use.
# The content signals and their meanings are:
# search: building a search index and providing search results (e.g., returning
# hyperlinks and short excerpts from your website's contents). Search does not
# include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
# augmented generation, grounding, or other real-time taking of content for
# generative AI search answers).
# ai-train: training or fine-tuning AI models.
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
# BEGIN Cloudflare Managed content
User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: CloudflareBrowserRenderingCrawler
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: GPTBot
Disallow: /
User-agent: meta-externalagent
Disallow: /
# END Cloudflare Managed Content
#
# 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: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
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: /profiles/*.svg
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.txt
Disallow: /web.config
# 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: /index.php/admin/
Disallow: /index.php/comment/reply/
Disallow: /index.php/filter/tips/
Disallow: /index.php/node/add/
Disallow: /index.php/search/
Disallow: /index.php/user/password/
Disallow: /index.php/user/register/
Disallow: /index.php/user/login/
Disallow: /index.php/user/logout/
User-agent: GPTBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: Perplexity-User
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Applebot-Extended
Disallow: /
User-agent: Facebookbot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: Omgili
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: TikTokSpider
Disallow: /
User-agent: diffbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: TurnitinBot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: AI2Bot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: AwarioBot
Disallow: /
User-agent: AwarioSmartBot
Disallow: /
User-agent: AwarioRssBot
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /
User-agent: PanguBot
Disallow: /
User-agent: Kangaroo Bot
Disallow: /
User-agent: Sentibot
Disallow: /
User-agent: img2dataset
Disallow: /
User-agent: Meltwater
Disallow: /
User-agent: Seekr
Disallow: /
User-agent: peer39_crawler
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: cohere-training-data-crawler
Disallow: /
User-agent: DuckAssistBot
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: Cotoyogi
Disallow: /
User-agent: aiHitBot
Disallow: /
User-agent: Factset_spyderbot
Disallow: /
User-agent: FirecrawlAgent
Disallow: /