# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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
#
# For syntax checking, see:
# http://www.robotstxt.org/checker.html

User-agent: *
Crawl-delay: 10
# CSS, JS, Images
Allow: /core/misc/*.css$
Allow: /core/misc/*.css?
Allow: /core/misc/*.js$
Allow: /core/misc/*.js?
Allow: /core/misc/*.gif
Allow: /core/misc/*.jpg
Allow: /core/misc/*.jpeg
Allow: /core/misc/*.png
Allow: /core/modules/*.css$
Allow: /core/modules/*.css?
Allow: /core/modules/*.js$
Allow: /core/modules/*.js?
Allow: /core/modules/*.gif
Allow: /core/modules/*.jpg
Allow: /core/modules/*.jpeg
Allow: /core/modules/*.png
Allow: /core/profiles/*.css$
Allow: /core/profiles/*.css?
Allow: /core/profiles/*.js$
Allow: /core/profiles/*.js?
Allow: /core/profiles/*.gif
Allow: /core/profiles/*.jpg
Allow: /core/profiles/*.jpeg
Allow: /core/profiles/*.png
Allow: /core/themes/*.css$
Allow: /core/themes/*.css?
Allow: /core/themes/*.js$
Allow: /core/themes/*.js?
Allow: /core/themes/*.gif
Allow: /core/themes/*.jpg
Allow: /core/themes/*.jpeg
Allow: /core/themes/*.png
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
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: /?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