# 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

# --------------------------------------------------------
# 1. DEFAULT RULES FOR ALL BOTS (Wildcard)
# --------------------------------------------------------
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /search-results/
Allow: /static/js/
Allow: /static/css/

# --------------------------------------------------------
# 2. EXPLICITLY ALLOWED BOTS (From your list + Major AI)
# --------------------------------------------------------
# -- Search Engine Crawlers --
User-agent: Googlebot
User-agent: bingbot
User-agent: Baiduspider
User-agent: YandexBot
User-agent: Applebot

# -- AI Crawlers (From screenshot + others) --
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Meta-ExternalAgent
User-agent: Amazonbot
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: CCBot

# -- Social Media & Page Previews --
User-agent: facebookexternalhit
User-agent: Pinterestbot

# -- Advertising & APIs --
User-agent: AdsBot-Google
User-agent: APIs-Google
User-agent: Meta-ExternalAds

# -- SEO Tools --
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: SemrushBotBacklinks

# *RULES FOR ALL THE BOTS LISTED ABOVE:*
# Because these bots ignore the "*" wildcard block once they see 
# their name, we must duplicate your site rules here for them.
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /search-results/
Allow: /static/js/
Allow: /static/css/

# --------------------------------------------------------
# 3. SITEMAP LOCATION
# --------------------------------------------------------
Sitemap: https://customclass.planpaths.com/sitemap.xml