# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# サナのAI副業教室 robots.txt
# 方針（2026-09-10 更新）:
#   - 検索エンジンの通常クロールは許可
#   - AI検索・AIアシスタントによる「引用・参照」（出典リンク付きの回答生成）は許可
#   - AIモデルの「学習」目的のクロールは拒否
# Cloudflare 側の AI ボットポリシー（混合目的クローラーは許可）と方針を揃えている。

# ---- Content Signals（Cloudflare 提唱の意思表示）
# search=yes   : 検索インデックスは許可
# ai-input=yes : AI回答（検索・引用・要約）への利用は許可
# ai-train=no  : AI学習への利用は不可
Content-Signal: search=yes, ai-input=yes, ai-train=no

# ---- AI学習専用クローラーの拒否（2026-09-14 に img2dataset を追加。詳細は利用規約 https://ai-fukugyo-lab.tech/terms/ ）
# （検索・引用用の OAI-SearchBot / ChatGPT-User / Claude-SearchBot / Claude-User /
#   PerplexityBot / Perplexity-User / DuckAssistBot / MistralAI-User などは拒否しない）
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: CCBot
User-agent: Bytespider
User-agent: Amazonbot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: omgili
User-agent: omgilibot
User-agent: webzio-extended
User-agent: PetalBot
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Kangaroo Bot
User-agent: PanguBot
User-agent: SemrushBot-OCOB
User-agent: Sidetrade-indexer-bot
User-agent: VelenPublicWebCrawler
User-agent: iaskspider/2.0
User-agent: ISSCyberRiskCrawler
User-agent: Scrapy
User-agent: img2dataset
Disallow: /

# ---- 通常の検索エンジン・AI検索クローラーは許可（有料教材の閲覧ページと API は除外）
# 「授業」の閲覧ページも教科書と同じ扱いにした（2026-09-17）。
# 未認証のアクセスは Worker がアクセスゲートへ 303 で返すため、Googlebot は本文にも
# noindex にも到達できない。クロールさせても「リダイレクトがあります」が積み上がるだけなので
# robots.txt で止める。現時点でこの配下にインデックス済み URL はない。
#
# 逆に /product/*/access/ と /product/bundle/ は Disallow しない。303 を返すのは
# read/ 配下だけで、これらは 200 + noindex を返す静的ページであり、しかも index 可能な
# /product/ からリンクされている。robots.txt で止めると Googlebot が noindex を読めず
# 「robots.txt でブロックされましたが、インデックスに登録しました」になり得る。
# 200 + noindex のページはクロールさせて noindex を読ませるのが正しい。
User-agent: *
Allow: /
Disallow: /product/textbook/read/
Disallow: /product/class/read/
Disallow: /api/

Sitemap: https://ai-fukugyo-lab.tech/sitemap-index.xml