# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

user-agent: *
Allow: /$
Disallow: /

User-agent: archive.org_bot
Disallow: /

# The example for img2dataset, although the default is *None*
User-agent: img2dataset
Disallow: /

# Brandwatch - "AI to discover new trends"
User-agent: magpie-crawler
Disallow: /

# webz.io - they sell data for training LLMs.
User-agent: Omgilibot
Disallow: /

# Items below were sourced from darkvisitors.com
# Categories included: "AI Data Scraper", "AI Assistant", "AI Search Crawler", "Undocumented AI Agent"

# AI Search Crawler
# https://darkvisitors.com/agents/amazonbot

User-agent: Amazonbot
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/anthropic-ai

User-agent: anthropic-ai
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/applebot

User-agent: Applebot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/applebot-extended

User-agent: Applebot-Extended
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/bytespider

User-agent: Bytespider
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/ccbot

User-agent: CCBot
Disallow: /

# AI Assistant
# https://darkvisitors.com/agents/chatgpt-user

User-agent: ChatGPT-User
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/claude-web

User-agent: Claude-Web
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/claudebot

User-agent: ClaudeBot
Disallow: /

# Undocumented AI Agent
# https://darkvisitors.com/agents/cohere-ai

User-agent: cohere-ai
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/diffbot

User-agent: Diffbot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/facebookbot

User-agent: FacebookBot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/google-extended

User-agent: Google-Extended
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/gptbot

User-agent: GPTBot
Disallow: /

# AI Data Scraper
# https://darkvisitors.com/agents/omgili

User-agent: omgili
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/perplexitybot

User-agent: PerplexityBot
Disallow: /

# AI Search Crawler
# https://darkvisitors.com/agents/youbot

User-agent: YouBot
Disallow: /