# 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

# Robots.txt for Karmic Parenting Website
# https://karmicparenting.com/robots.txt

# Allow all bots to access public content
User-agent: *
Allow: /

# Block all admin pages and sensitive areas
Disallow: /admin/
Disallow: /api/
Disallow: /test-payment

# Block specific pages that should not be indexed
Disallow: /order/success

# Allow access to public assets
Allow: /logo.png
Allow: /logo.svg
Allow: /*.css
Allow: /*.js
Allow: /_next/static/

# Block common bot traps and security endpoints
Disallow: /.env
Disallow: /.git/
Disallow: /node_modules/
Disallow: /.next/
Disallow: /database/

# Crawl delay to be respectful
Crawl-delay: 1

# Sitemap location
Sitemap: https://karmicparenting.com/sitemap.xml

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /test-payment
Disallow: /order/success

User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /test-payment
Disallow: /order/success

# Block malicious bots and scrapers
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /