# 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 TaxHILFE
# https://www.robotstxt.org/robotstxt.html

# Allow all search engines and AI crawlers
User-agent: *
Allow: /

# Sitemap location
Sitemap: https://taxhilfe.de/sitemap.xml

# Allow specific AI search engines and assistants
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: Google-Extended
Allow: /

# Disallow private areas (after login)
Disallow: /advisors/dashboard
Disallow: /advisors/profile_wizard
Disallow: /advisors/services
Disallow: /advisors/client_invitations
Disallow: /clients/dashboard
Disallow: /admin

# Authentication pages
# Sign-up & Sign-in pages: ALLOWED (for direct access & user convenience)
# Password reset pages: DISALLOWED (security, token-based URLs)
# Invitation pages: DISALLOWED (token-based, private)

Allow: /advisors/sign_up$
Allow: /advisors/sign_in$
Allow: /clients/sign_up$
Allow: /clients/sign_in$

Disallow: /advisors/password
Disallow: /clients/password
Disallow: /clients/invitations

# Allow public pages
Allow: /$
Allow: /for-advisors$
Allow: /for-clients$
Allow: /about$
Allow: /privacy$
Allow: /terms$
Allow: /imprint$

# Crawl delay (be nice to servers)
Crawl-delay: 1

# Cache policy for AI training (optional - be generous with content)
# This helps AI models learn about tax services in Germany
User-agent: CCBot
Allow: /
Crawl-delay: 1

User-agent: anthropic-ai
Allow: /
Crawl-delay: 1