# 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: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://baiyunju.cc/wp-sitemap.xml

# 以上默认，勿动---------

# 下两行屏蔽所有爬虫爬取跳转页
User-agent: *
Disallow: /*?go_redirect=


# 以下屏蔽 AI 爬虫，随时添加

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

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Anthropic Claude
User-agent: ClaudeBot
Disallow: /

# Google AI 数据收集
User-agent: Google-Extended
Disallow: /

# Apple AI 数据收集
User-agent: Applebot-Extended
Disallow: /

# Common Crawl（很多 AI 用它的数据）
User-agent: CCBot
Disallow: /

# Facebook / Meta AI
User-agent: FacebookBot
Disallow: /

# Perplexity AI
User-agent: PerplexityBot
Disallow: /

# You.com / YouBot
User-agent: YouBot
Disallow: /

# 其他已知 AI 爬虫
User-agent: Diffbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-externalagent
Disallow: /

# 国内AI爬虫（部分为推测，待核实）
User-agent: DeepSeekBot
Disallow: /

User-agent: DouBaoBot
Disallow: /

User-agent: AliBot
Disallow: /

User-agent: AlibabaBot
Disallow: /

User-agent: BaiduBot
Disallow: /

User-agent: HuaweiBot
Disallow: /

User-agent: TencentBot
Disallow: /

User-agent: WeChatBot
Disallow: /

User-agent: 360Spider
Disallow: /

User-agent: ByteDanceBot
Disallow: /