# 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

# ─────────────────────────────────────────────────────────────
# CleanTextTools — robots.txt
# All search engines and AI crawlers are explicitly allowed.
# ─────────────────────────────────────────────────────────────

# Default: every bot, every page
User-agent: *
Allow: /

# ─── Traditional search engines ───────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# ─── OpenAI (ChatGPT, SearchGPT) ──────────────────────────────
# https://platform.openai.com/docs/bots
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# ─── Google AI (Gemini, Vertex AI, AI Overviews) ──────────────
# Google-Extended controls inclusion in Gemini & Vertex training.
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# ─── Anthropic (Claude) ───────────────────────────────────────
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# ─── Perplexity ───────────────────────────────────────────────
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ─── Microsoft Copilot ────────────────────────────────────────
# Copilot uses the Bing index — Bingbot (above) is the gate.

# ─── Apple Intelligence ───────────────────────────────────────
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ─── Meta AI ──────────────────────────────────────────────────
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# ─── DuckDuckGo Assist ────────────────────────────────────────
User-agent: DuckAssistBot
Allow: /

# ─── Common Crawl (feeds many AI training pipelines) ──────────
User-agent: CCBot
Allow: /

# ─── xAI Grok ─────────────────────────────────────────────────
# xAI has not published an official robots.txt user-agent.
# Grok is covered by the wildcard "User-agent: *" rule above.

Sitemap: https://cleantexttools.com/sitemap-index.xml