AI 爬蟲 User-Agent 清單

# AI crawler block list — generated from clickfrom.ai/tools/ai-crawler-user-agent-list
# Remove the Disallow line for any crawler you want to allow.

# OpenAI — Crawls public web pages to improve OpenAI foundation models.
# Source: https://platform.openai.com/docs/bots
User-agent: GPTBot
Disallow: /

# OpenAI — Indexes web pages so ChatGPT search and SearchGPT can cite them.
# Source: https://platform.openai.com/docs/bots
User-agent: OAI-SearchBot
Disallow: /

# OpenAI — Fetches a page on the spot when a ChatGPT user asks the assistant about a specific URL.
# Source: https://platform.openai.com/docs/bots
User-agent: ChatGPT-User
Disallow: /

# Anthropic — Crawls public web pages for Anthropic foundation-model training.
# Source: https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler
User-agent: ClaudeBot
Disallow: /

# Anthropic — Indexes web pages so Claude can cite them in search-like answers.
# Source: https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler
User-agent: Claude-SearchBot
Disallow: /

# Anthropic — Fetches a page on the spot when a Claude user asks the assistant about a specific URL.
# Source: https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler
User-agent: Claude-User
Disallow: /

# Google — Opt-out token (not a real user-agent) controlling whether Gemini and Vertex AI may train on your content.
# Source: https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers#google-extended
User-agent: Google-Extended
Disallow: /

# Google — Internal R&D and product-team crawls outside of Search and Ads.
# Source: https://developers.google.com/search/docs/crawling-indexing/google-common-crawlers#googleother
User-agent: GoogleOther
Disallow: /

# Google — Classical Google Search indexer. Powers AI Overviews via the same index.
# Source: https://developers.google.com/search/docs/crawling-indexing/googlebot
User-agent: Googlebot
Disallow: /

# Perplexity — Indexes web pages so Perplexity can surface them as cited sources in answers.
# Source: https://docs.perplexity.ai/guides/bots
User-agent: PerplexityBot
Disallow: /

# Perplexity — Fetches a page on the spot when a Perplexity user asks the assistant about a specific URL.
# Source: https://docs.perplexity.ai/guides/bots
User-agent: Perplexity-User
Disallow: /

# Apple — Powers Siri, Spotlight, and Safari Suggestions search.
# Source: https://support.apple.com/en-us/119829
User-agent: Applebot
Disallow: /

# Apple — Opt-out token controlling whether Apple Intelligence may train on your content.
# Source: https://support.apple.com/en-us/119829
User-agent: Applebot-Extended
Disallow: /

# Common Crawl — Bulk crawl of the public web. Downstream datasets feed many AI model training pipelines (including some at OpenAI, Anthropic, and academic groups).
# Source: https://commoncrawl.org/ccbot
User-agent: CCBot
Disallow: /

# Meta — Crawls public web pages for Meta AI (Llama family) training and indexing.
# Source: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/
User-agent: Meta-ExternalAgent
Disallow: /

# Meta — Fetches a page on the spot when a Meta AI user asks the assistant about a specific URL.
# Source: https://developers.facebook.com/docs/sharing/webmasters/web-crawlers/
User-agent: Meta-ExternalFetcher
Disallow: /

# ByteDance — Crawls public web pages for ByteDance's foundation-model training (Doubao and related models).
# Source: https://bytespider.bytedance.com/
User-agent: Bytespider
Disallow: /

# Amazon — Powers Alexa and other Amazon answer/AI experiences.
# Source: https://developer.amazon.com/amazonbot
User-agent: Amazonbot
Disallow: /

# DuckDuckGo — Indexes web pages so DuckAssist can summarize them in DuckDuckGo answers.
# Source: https://duckduckgo.com/duckduckgo-help-pages/results/duckassistbot/
User-agent: DuckAssistBot
Disallow: /

# Mistral — Fetches a page on the spot when a Mistral Le Chat user asks the assistant about a specific URL.
# Source: https://docs.mistral.ai/robots/
User-agent: MistralAI-User
Disallow: /

# You.com — Indexes web pages for You.com AI search and chat.
# Source: https://about.you.com/youbot/
User-agent: YouBot
Disallow: /