# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# https://www.robotstxt.org/robotstxt.html
# MyItura — https://myitura.com

User-agent: *
Allow: /

# Authenticated, transactional and single-use flows. These have no stable public
# content, and crawling them wastes crawl budget on pages that can never rank.
Disallow: /dashboard/
Disallow: /providers/
Disallow: /provider-onboarding
Disallow: /cart
Disallow: /cart/
Disallow: /empty-cart
Disallow: /checkout/
Disallow: /confirm-order
Disallow: /order-status
Disallow: /handoff
Disallow: /onboarding
Disallow: /checkpoint
Disallow: /login
Disallow: /sign-up
Disallow: /phone-login
Disallow: /phone-sign-up
Disallow: /phone-otp-verify
Disallow: /lab-sign-up
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /accept-invite
Disallow: /verify-email
Disallow: /verify-otp
Disallow: /verify-phone
Disallow: /verification-type
Disallow: /verify-success
Disallow: /auth-success
Disallow: /auth/
Disallow: /mfa/
Disallow: /chat-doctor
Disallow: /chat-itura
Disallow: /subscribe

# The doctor directory reads /consultations/doctors, which requires an
# Authorization header — an anonymous visitor (and any crawler) is redirected to
# the login screen, so there is nothing here to index. Re-open this once the
# directory has a public read endpoint; see scripts/routes.mjs.
Disallow: /specialist

# --- AI crawlers -------------------------------------------------------------
# Explicitly allowed. These agents do not execute JavaScript, so they depend on
# the build-time prerendered HTML (scripts/prerender.mjs) to see any content at
# all. Allowing them is what makes MyItura eligible to be cited in AI answers
# about healthcare in Nigeria.

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (Gemini grounding / AI Overviews; separate from Googlebot search)
User-agent: Google-Extended
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Microsoft Copilot
User-agent: Bingbot
Allow: /

# Common Crawl (feeds many downstream models)
User-agent: CCBot
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

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