# 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

User-agent: *
# CSS, JS, Images
Allow: /core/*.css$
Allow: /core/*.css?
Allow: /core/*.js$
Allow: /core/*.js?
Allow: /core/*.avif
Allow: /core/*.gif
Allow: /core/*.jpg
Allow: /core/*.jpeg
Allow: /core/*.png
Allow: /core/*.svg
Allow: /core/*.webp
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.avif
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /profiles/*.svg
Allow: /profiles/*.webp
# Directories
Disallow: /core/
Disallow: /profiles/
# Files
Disallow: /README.md
Disallow: /composer/Metapackage/README.txt
Disallow: /composer/Plugin/ProjectMessage/README.md
Disallow: /composer/Plugin/Scaffold/README.md
Disallow: /composer/Plugin/VendorHardening/README.txt
Disallow: /composer/Template/README.txt
Disallow: /modules/README.txt
Disallow: /sites/README.txt
Disallow: /themes/README.txt
# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips
Disallow: /node/add/
Disallow: /search/
Disallow: /search?
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /media/oembed
Disallow: /*/media/oembed
# 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/search?
Disallow: /index.php/user/password
Disallow: /index.php/user/register
Disallow: /index.php/user/login
Disallow: /index.php/user/logout
Disallow: /index.php/media/oembed
Disallow: /index.php/*/media/oembed


# Language prefixes.
#
# Every content page links to its 27 language variants through the language
# switcher, but the content behind those prefixes is not translated: of 34,532
# groups none have a translation, and 6 of 1,644 nodes do. Each variant serves
# the English page with a translated interface, and already carries a canonical
# link back to the English URL, so there is nothing unique for a crawler to
# index -- only ~1M near-duplicate URLs to fetch, each one a cache miss and a
# full page render.
#
# Canonical tags stop these being indexed; they do not stop them being crawled.
# That is what these rules are for.
#
# Generated from language.negotiation:url.prefixes. Regenerate if the set of
# enabled languages changes. Both forms are needed per prefix: "/xx/" covers
# everything below the prefix, "/xx$" covers the language's front page without
# also matching unrelated paths such as /archive.
Disallow: /ar/
Disallow: /ar$
Disallow: /bg/
Disallow: /bg$
Disallow: /ca/
Disallow: /ca$
Disallow: /cs/
Disallow: /cs$
Disallow: /de/
Disallow: /de$
Disallow: /el/
Disallow: /el$
Disallow: /es/
Disallow: /es$
Disallow: /es-419/
Disallow: /es-419$
Disallow: /fa/
Disallow: /fa$
Disallow: /fr/
Disallow: /fr$
Disallow: /he/
Disallow: /he$
Disallow: /hr/
Disallow: /hr$
Disallow: /id/
Disallow: /id$
Disallow: /ja/
Disallow: /ja$
Disallow: /ko/
Disallow: /ko$
Disallow: /pl/
Disallow: /pl$
Disallow: /pt-br/
Disallow: /pt-br$
Disallow: /ro/
Disallow: /ro$
Disallow: /ru/
Disallow: /ru$
Disallow: /sk/
Disallow: /sk$
Disallow: /th/
Disallow: /th$
Disallow: /tr/
Disallow: /tr$
Disallow: /uk/
Disallow: /uk$
Disallow: /ur/
Disallow: /ur$
Disallow: /vi/
Disallow: /vi$
Disallow: /zh-hans/
Disallow: /zh-hans$
Disallow: /zh-hant/
Disallow: /zh-hant$