# 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

# AI 学習用クローラをブロック（検索・広告クローラは対象外:
# Googlebot / Mediapartners-Google / AdsBot-Google は下の * ルールで許可のまま）

# OpenAI (学習)
User-agent: GPTBot
Disallow: /

# Google Gemini 学習（検索インデックス・AdSense には影響しない）
User-agent: Google-Extended
Disallow: /

# Common Crawl（学習データセット供給源）
User-agent: CCBot
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Apple AI 学習（通常の Applebot は対象外）
User-agent: Applebot-Extended
Disallow: /

# ByteDance
User-agent: Bytespider
Disallow: /

# Meta AI 学習
User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

# Diffbot / Omgili（データセット収集）
User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: omgili
Disallow: /

# Allen Institute for AI（学習）
User-agent: AI2Bot
Disallow: /

# Huawei Pangu（学習）
User-agent: PanguBot
Disallow: /

# Timpi（分散検索・データセット収集）
User-agent: Timpibot
Disallow: /

# Webz.io（学習データ販売）
User-agent: Webzio-Extended
Disallow: /

# Mistral AI
User-agent: MistralAI-User
Disallow: /

# その他すべて（Googlebot / Mediapartners-Google / AdsBot-Google / Bingbot 含む）は許可
User-agent: *
Allow: /

Sitemap: https://iroirotool.com/sitemap.xml