# 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

# DegreeAtlas robots policy — production

User-agent: *
Allow: /$
Allow: /institutions/
Allow: /countries/
Allow: /programs/
Allow: /compare/
Allow: /search/
Allow: /deadlines/
Allow: /scholarships/
Allow: /eligibility/
Allow: /journey/
Allow: /prepare/
Allow: /developers/
Allow: /for-institutions/
Allow: /services/
Allow: /legal/
Allow: /methodology/
Allow: /guides/
Allow: /corrections/
Allow: /contact/

# Machine-readable payloads and build internals carry no reader value and must
# not enter a search index.
Disallow: /data/
Disallow: /vendor/
Disallow: /integration/
Disallow: /pagefind/
Disallow: /fixtures/
Disallow: /reports/
Disallow: /operator/
Disallow: /404.html

# Pagefind serves the on-site editorial lane; it is not a crawl surface.
User-agent: Pagefind
Disallow: /

Sitemap: https://degreeatlas.org/sitemap.xml