# ==============================================================================
# Interface-Initiatives - robots.txt
# Public crawl policy, copyright and TDM reservation
# ==============================================================================


# This website and its contents are protected by copyright, database rights
# and related rights. Public availability does not grant permission for
# scraping, automated extraction, text and data mining, AI training,
# dataset creation, archiving or republication unless expressly authorised
# by the policy selected for this site.
#
# Strategy: strict-allowlist
# Policy: no-permission-without-prior-express-written-authorisation
# Complete policy: https://interfaces-initiatives.org/legal#llm-tdm-moissonnage
# Rights and reproduction: https://interfaces-initiatives.org/legal#copyright
# TDMRep: https://interfaces-initiatives.org/.well-known/tdmrep.json
# Contact: https://interfaces-initiatives.org/legal#contact
#
# Governing-Law: Belgian and European law
# Rights-Reserved: copyright, database rights, related rights, text and data mining rights
# Reference: Regulation (EU) 2016/679 - GDPR
# Reference: Directive (EU) 2019/790 - Copyright in the Digital Single Market
# Reference: Regulation (EU) 2024/1689 - Artificial Intelligence Act

# ------------------------------------------------------------------------------
# ROBOTS RULES
# ------------------------------------------------------------------------------

# ------------------------------------------------------------------------------
# PUBLIC SEARCH ENGINES EXPLICITLY AUTHORISED
# ------------------------------------------------------------------------------

User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Qwantify
User-agent: Ecosia_bot
User-agent: MojeekBot
User-agent: SeznamBot
User-agent: Slurp
Allow: /

# ------------------------------------------------------------------------------
# PUBLIC SEARCH ENGINES NOT RETAINED FOR THIS SITE
# ------------------------------------------------------------------------------

User-agent: Baiduspider
User-agent: YandexBot
User-agent: Sogouwebspider
User-agent: Sogou
User-agent: NaverBot
User-agent: Yeti
Disallow: /

# ------------------------------------------------------------------------------
# PUBLIC ARCHIVERS REFUSED
# ------------------------------------------------------------------------------

User-agent: ia_archiver
User-agent: archive.org_bot
User-agent: Wayback
User-agent: heritrix
User-agent: webrecorder
User-agent: ArchiveTeam
User-agent: archivebot
User-agent: webcitation
Disallow: /

# ------------------------------------------------------------------------------
# COMMERCIAL SEO BOTS AND NON-ESSENTIAL CRAWLERS REFUSED
# ------------------------------------------------------------------------------

User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: PetalBot
User-agent: DataForSeoBot
User-agent: MegaIndex
User-agent: serpstatbot
User-agent: ScreamingFrogSEOSpider
User-agent: Sitebulb
User-agent: SeobilityBot
Disallow: /

# ------------------------------------------------------------------------------
# AI CRAWLERS EXPLICITLY AUTHORISED FOR CONSULTATION
# ------------------------------------------------------------------------------

User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Amazonbot
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: MistralAI-User1.0
User-agent: MistralAI-Index
User-agent: MistralAI-Index1.0
User-agent: Applebot-Extended
User-agent: cohere-ai
Allow: /

# ------------------------------------------------------------------------------
# AI CRAWLERS, TDM AND TRAINING AGENTS REFUSED
# ------------------------------------------------------------------------------

User-agent: CCBot
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: Diffbot
User-agent: PanguBot
User-agent: YouBot
User-agent: omgili
User-agent: omgilibot
User-agent: GeistHaus-PageFetcher
User-agent: netEstateImprintCrawler
Disallow: /

# ------------------------------------------------------------------------------
# DEFAULT RULE FOR ALL OTHER AUTOMATED AGENTS
# ------------------------------------------------------------------------------

# robots.txt is not a security mechanism and does not expose internal routes.
# Any automated access not expressly authorised above is disallowed by default.

User-agent: *
Disallow: /

# ------------------------------------------------------------------------------
# SITEMAP
# ------------------------------------------------------------------------------

Sitemap: https://interfaces-initiatives.org/sitemap.xml