# 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

# Grove Video — AI crawl policy
# https://grovevideo.com/
#
# Public pages: / (app landing), /terms/, /privacy/, /cookies/, /extension/, /llms.txt
# Never crawl: /api/* (backend proxy), /media/* (user media proxy)
#
# Search engines may index public marketing and legal pages.
# AI training crawlers are blocked or limited to /llms.txt only.
# Claude search/user bots may fetch public shell + legal pages for discovery.
# All other AI training/indexing bots are disallowed unless listed below.

# --- Default: public shell + legal; block backend paths ---
User-agent: *
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

# --- Search engines ---
User-agent: Googlebot
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

User-agent: Bingbot
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

# --- Anthropic (Claude) ---
# Training crawler: /llms.txt only — no site content for model training
User-agent: ClaudeBot
Disallow: /
Allow: /llms.txt

# Search indexing and user-initiated fetches: public pages only
User-agent: Claude-SearchBot
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

User-agent: Claude-User
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

# --- OpenAI ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

User-agent: OAI-SearchBot
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

# --- Google AI training (separate from Googlebot search) ---
User-agent: Google-Extended
Disallow: /

# --- Other AI training and scraping bots ---
User-agent: anthropic-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: PerplexityBot
Allow: /
Allow: /terms/
Allow: /privacy/
Allow: /cookies/
Allow: /extension/
Allow: /llms.txt
Disallow: /api/
Disallow: /media/

# Machine-readable site summary for LLMs
# https://grovevideo.com/llms.txt

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