# ==============================================================================
# OGPN - 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.
#
# Policy: no-permission-without-prior-express-written-authorisation
# Complete policy: https://ogpn.eu/legal#llm-tdm-moissonnage
# Rights and reproduction: https://ogpn.eu/legal#copyright
# TDMRep: https://ogpn.eu/.well-known/tdmrep.json
# Contact: https://ogpn.eu/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
# ------------------------------------------------------------------------------

# Archiveurs externes refusés.
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: /

# Bots SEO commerciaux et crawlers non essentiels refusés.
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: /

# Exploration publique générale.
# Ce fichier ne liste pas les routes internes ou sensibles : robots.txt n'est pas
# un mécanisme de sécurité et ne doit pas servir de plan d'administration.
User-agent: *
Allow: /

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

Sitemap: https://ogpn.eu/sitemap.xml