# Maison Cealus - robots.txt
# Search engines are welcome. Copying, scraping and AI training are not.
# Copyright policy: https://cealus.com/copyright/

# 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.

# Maison Cealus, as rightholder, expressly reserves the reproduction of its content
# on this website for text and data mining, including the training of AI models,
# under Art. 26^3 of the Polish Act of 4 February 1994 on Copyright and Related Rights
# and Art. 4(3) of Directive (EU) 2019/790. Indexing by search engines is permitted.

# Every crawler: crawling for search indexing and link previews is allowed.
# Copying, scraping, AI training and AI answers are not.
User-agent: *
Content-Signal: search=yes, ai-input=no, ai-train=no
Content-Usage: train-ai=n
Allow: /

# The shared AI-training preference. A policy token, not a crawler.
User-agent: __usage_ai-training
Disallow: /

# AI crawlers, data scrapers and AI-training control tokens.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: GoogleOther-Image
Disallow: /

User-agent: GoogleOther-Video
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: TikTokSpider
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: cohere-ai
Disallow: /

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

User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: bedrockbot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

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