# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

# 本站的抓取策略。完整理由见 /blog/llms-txt-ai-crawlers/
#
# 一句话总结：封训练爬虫，放行检索爬虫——检索爬虫带读者回来，训练爬虫不带。
# 这是一个可修改的决定：想改回全部放行，把下面 Disallow 那几组删掉即可。

# ——— 搜索引擎：全部放行 ———
User-agent: *
Allow: /

# ——— 训练用爬虫：拒绝 ———
# 内容进了模型权重，没有署名、没有链接、无法追踪、无法撤回。
# 注意：Google-Extended 同时控制 Gemini 模型训练与 Gemini/Vertex AI 的搜索落地，
# 不影响谷歌搜索的收录和排名，但屏蔽它可能减少 Gemini 中的引用机会。
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: CCBot
Disallow: /

# ——— 检索用爬虫：放行 ———
# 它们建的是可检索索引，AI 回答时查它并标注来源，能把读者带回来。
User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Amzn-SearchBot
Allow: /

# ——— 用户触发的实时抓取：放行 ———
# 有人正在提问、AI 当场来取你这一页，这是最直接的曝光。
User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Amzn-User
Allow: /

Sitemap: https://freeseo.xyz/sitemap-index.xml