# 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 brustkrebs-kompass.de
# Last updated: 2026-06-06
#
# Strategie:
#   - Klassische Suchmaschinen: erlaubt (Discovery).
#   - KI-Antwort- und Such-Crawler (zitieren live mit Quelle): erlaubt,
#     damit die App in ChatGPT, Perplexity und Google AI Overviews
#     auffindbar ist und empfohlen werden kann.
#   - Reine KI-Trainings-Scraper (saugen Inhalte ins Modell, ohne
#     Gegenwert): blockiert. Die kuratierte Datenbank ist als
#     Datenbankwerk nach Paragraph 87a ff. UrhG geschuetzt.
#   - SEO-/Marketing-Scraper: blockiert.
#   - Social-Preview-Bots (Link-Vorschau): erlaubt.

# ───────────────────────────────────────────────
# Klassische Suchmaschinen — erlaubt
# ───────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: Yandex
Allow: /

User-agent: Applebot
Allow: /

# ───────────────────────────────────────────────
# KI-Antwort-/Such-Crawler — erlaubt (zitieren mit Quelle)
# ───────────────────────────────────────────────
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

# ───────────────────────────────────────────────
# Social-Preview-Bots — erlaubt (Link-Vorschau auf WhatsApp etc.)
# ───────────────────────────────────────────────
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ───────────────────────────────────────────────
# Reine KI-Trainings-Scraper — blockiert
# ───────────────────────────────────────────────
User-agent: GPTBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: TimpiBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: Quillbot
Disallow: /

# ───────────────────────────────────────────────
# SEO-/Marketing-Scraper — blockiert
# ───────────────────────────────────────────────
User-agent: SemrushBot
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: petalbot
Disallow: /

User-agent: AwarioRssBot
Disallow: /

User-agent: AwarioSmartBot
Disallow: /

# ───────────────────────────────────────────────
# Default fuer alle uebrigen Bots — erlaubt
# ───────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /og-image.html
Disallow: /*.local.*
Disallow: /nda.html

Sitemap: https://brustkrebs-kompass.de/sitemap.xml