# 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

# robots.txt for taiboai.com
# 最后更新：2026-07-01
# 重要：请同时在 Cloudflare Dashboard 关闭 AI Scraping 默认封禁，
# 或在 WAF -> Tools 中为以下AI爬虫单独放行（不要仅依赖本文件）
# Cloudflare 默认封禁块已移除，改为白名单显式 Allow 模式

User-agent: Bytespider
Allow: /
# 豆包爬虫（字节跳动），豆包第一信源，必须放行

User-agent: DeepSeekBot
Allow: /
# DeepSeek爬虫

User-agent: QwenBot
Allow: /
# 通义千问爬虫（阿里）

User-agent: ErnieBot
Allow: /
# 文心一言爬虫（百度）

User-agent: TencentBot
Allow: /
# 腾讯元宝爬虫

User-agent: KimiBot
Allow: /
User-agent: MoonshotBot
Allow: /
# Kimi爬虫（月之暗面）

User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
# OpenAI/ChatGPT爬虫

User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /
# Anthropic/Claude爬虫

User-agent: Google-Extended
Allow: /
# Google AI Overviews爬虫

User-agent: Baiduspider
Allow: /
User-agent: Baiduspider-image
Allow: /
User-agent: Baiduspider-video
Allow: /
# 百度搜索引擎

User-agent: Sogou spider
Allow: /
User-agent: Sogou web spider
Allow: /
# 搜狗搜索引擎

User-agent: 360Spider
Allow: /
# 360搜索引擎

User-agent: AliSpider
Allow: /
# 夸克/UC/阿里系爬虫

User-agent: YisouSpider
Allow: /
# 神马搜索（移动）

User-agent: *
Disallow: /cgi-bin/
Disallow: /admin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /api/private/
Disallow: /*?s=
# 禁止抓取无意义路径和私有API
Allow: /

# Sitemap（注意：只放合法sitemap XML，不要放llms.txt）
Sitemap: https://taiboai.com/sitemap.xml

# Host
Host: https://taiboai.com/

# AI训练策略：允许抓取引用，禁止用于AI训练
#（此指令非标准robots指令，但多数AI爬虫会识别）
X-Robots-Tag: ai-train: no