# 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

User-agent: *
Allow: /

# Private / authenticated-only areas — defense in depth (these pages
# also set <meta name="robots" content="noindex"> in their Seo helper).
Disallow: /submit
Disallow: /submit/
Disallow: /favorites
Disallow: /activity
Disallow: /messages
Disallow: /messages/
Disallow: /collections/new
Disallow: /reset-password
Disallow: /admin
Disallow: /admin/

# Noindex app surfaces that Google previously indexed as a generic shell.
# The pages also send <meta name="robots" content="noindex">; the disallow
# rules speed up recrawl + drop.
Disallow: /b/*/edit

# Faceted / search-param variants of /browse — keep canonical /browse
# crawlable, block parameterised duplicates.
Disallow: /*?cats=*
Disallow: /*&cats=*

# Allow AdSense crawler explicitly — Google recommends this so
# Mediapartners-Google is never accidentally blocked by * rules.
# (Must come AFTER the global Disallow list so the build validator
# regex doesn't see a Disallow under this user-agent.)
User-agent: Mediapartners-Google
Allow: /

Sitemap: https://sfsblueprints.com/sitemap.xml