# 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.

# 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
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

# Global Rules for All Crawlers
User-Agent: *
Allow: /

# Crawl Restrictions for All Crawlers
Disallow: /wp-content/uploads/wpforms/
Disallow: /wp-admin/
Disallow: /admin/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /login/
Disallow: /register/
Disallow: /tag/*
Disallow: /?*
Disallow: /page/*
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /*/feed/
Disallow: /feed/
Disallow: /disclaimers/
Disallow: /typography/
Disallow: /career-sagesafe/
Disallow: /team-tools/
Disallow: /patient-video/
Disallow: /closed-practices/
Disallow: /sp25-nppplus/
Disallow: /patient-forms/
Disallow: /join-now/
Disallow: /career-form/
Disallow: /careers-post/
Disallow: /thank-you-transition/
Disallow: /new-doctor-bio/
Disallow: /solicitar-un-viaje/
Disallow: /winter-npp49-locations/
Disallow: /news/page/4/
Disallow: /feb-nppplus-locations/
Disallow: /thank-you-yoursmile/
Disallow: /thank-you-braceyourself/
Disallow: /sagecare-savings-activation/

# Block AI Crawlers & Extended Data-Collection Bots
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Standard Googlebot Rules (Fix #1 Applied)
# Allow Google search indexing but prevent image crawling only.
User-agent: Googlebot
Disallow: /images/

# Legacy MSNBot Rule (for compatibility)
User-agent: MSNBot
Disallow: /images/

# Sitemap
Sitemap: https://mysagedental.com/sitemap_index.xml