# 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: *
# Core public routes
Allow: /
Allow: /about
Allow: /contact
Allow: /shuleni/privacy
Allow: /shuleni/terms
Allow: /shuleni/disclaimer
Allow: /shuleni/advertise
Allow: /matokeo
Allow: /tie-books

# Shuleni - primary public content (schools, regions, subjects, etc.)
Allow: /shuleni/

# Faceted "shule-zote" filter permutations are an infinite, thin/duplicate crawl
# trap: every stacked filter combination (ownership × level × boarding × sex ×
# comb × subject …) is a filtered subset of the parent location hub, which is
# already indexed. They also render on-demand (~4s each), so crawling them wastes
# both crawl budget and origin CPU. Block the filtered depth; the unfiltered
# "shule-zote" listing and all location hubs remain crawlable. Shallow (≤2) facet
# pages that the app still indexes keep their value via canonical/noindex in the
# page metadata — this only stops the wasteful crawl, not the useful hubs.
Disallow: /shuleni/region/*/shule-zote/*
Disallow: /shuleni/council/*/shule-zote/*
Disallow: /shuleni/ward/*/shule-zote/*
# Crawlers must not walk the sorted-filter query variants either
Disallow: /shuleni/*/shule-zote/*?*

# Disallow protected/internal routes
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/
Disallow: /fees/
Disallow: /exametrics/
Disallow: /onboarding/
Disallow: /s/
Disallow: /hub/
Disallow: /shuleyetu/
Disallow: /necta-portal/
Disallow: /school-info/

# Sitemap
Sitemap: https://shuleyetu.co.tz/sitemap.xml