#===================================================================#
#Crawler IA
#===================================================================#
#  OPENAI
#  GPTBot         → entraînement des modèles          ✗ BLOQUÉ
#  OAI-SearchBot  → indexation pour ChatGPT Search    ✓ AUTORISÉ
#  ChatGPT-User   → requêtes RAG en temps réel        ✓ AUTO
#===================================================================#
User-agent: GPTBot
Disallow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /

#===================================================================#
#  ANTHROPIC (Claude)
#  ClaudeBot       → entraînement des modèles         ✗ BLOQUÉ
#  Claude-SearchBot → indexation pour claude.ai       ✓ AUTORISÉ
#  Claude-User     → requêtes RAG en temps réel       ✓ AUTORISÉ
#===================================================================#
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: Claude-User
Allow: /
#===================================================================#
#  PERPLEXITY
#  PerplexityBot   → entraînement + indexation        ✓ AUTORISÉ
#  Perplexity-User → requêtes RAG en temps réel       ✓ AUTORISÉ
#===================================================================#
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
#===================================================================#
#  GOOGLE
#  Googlebot       → indexation Search classique      ✓ AUTORISÉ
#  Google-Extended → entraînement Gemini              ✗ BLOQUÉ
#  GoogleOther     → divers services Google           ✓ AUTORISÉ (Search, SGE…)
#===================================================================#
User-agent: Googlebot
Allow: /
User-agent: Google-Extended
Disallow: /
User-agent: GoogleOther
Allow: /
#===================================================================#
#  MICROSOFT / BING
#  Bingbot         → indexation Bing + Copilot        ✓ AUTORISÉ
#===================================================================#
User-agent: Bingbot
Allow: /
#===================================================================#
#  APPLE
#  Applebot        → Siri, Spotlight, Apple Search    ✓ AUTORISÉ
#  Applebot-Extended → entraînement Apple Intelligence ✗ BLOQUÉ
#===================================================================#
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Disallow: /
#===================================================================#
#  COMMON CRAWL
#  CCBot           → dataset public, base de nombreux LLMs  ✗ BLOQUÉ
User-agent: CCBot
Disallow: /
#===================================================================#
# Meta AI (entraînement LLaMA)             → BLOQUÉ
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /

# Cohere                                    → BLOQUÉ
User-agent: cohere-ai
Disallow: /

# ByteDance / Bytespider                    → BLOQUÉ
User-agent: Bytespider
Disallow: /
#===================================================================#

#Autres

User-agent: Mediapartners-Google
Disallow: /search?*
Disallow: /search/*
Disallow: /Product/Download/
Disallow: /Account/
Disallow: /Cart
Disallow: /Cart/
Disallow: /Product/DownloadFile/

User-agent: *
Disallow: /*/publications/*excluded_language_id*
Disallow: /*/publications/*excluded_theme_id*
Disallow: /*/publications/*not_in_theme_id*
Disallow: /Account/
Disallow: /Account/AddToLibrary/
Disallow: /Account/LoadReplies/
Disallow: /BnFService
Disallow: /BookReader/
Disallow: /BookReader/Index*
Disallow: /BookReader/CanSearch*
Disallow: /BookReader/Embed*
Disallow: /BookReader/EmbedJs*
Disallow: /BookReader/EmbedPreview*
Disallow: /BookReader/FontCss*
Disallow: /BookReader/HtmlPage*
Disallow: /BookReader/IframeEmbed*
Disallow: /BookReader/Info*
Disallow: /BookReader/MainTemplate*
Disallow: /BookReader/Page*
Disallow: /BookReader/Print*
Disallow: /BookReader/RatioImage*
Disallow: /BookReader/Search*
Disallow: /BookReader/AudioReader*
Disallow: /Cart
Disallow: /Cart/
Disallow: /Catalog/Certify*
Disallow: /Catalog/LoadProducts*
Disallow: /Catalog/Store*access_type=*
Disallow: /Catalog/Store*category_id=*
Disallow: /Catalog/Store*is_free=*
Disallow: /Catalog/Store*is_french_domain=*
Disallow: /Catalog/Store*language_id=*
Disallow: /Catalog/Store*sort=*
Disallow: /Catalog/Store*tag_id=*
Disallow: /Catalog/Store*theme_id=*
Disallow: /catalogue/*access_type=*
Disallow: /catalogue/*category_id=*
Disallow: /catalogue/*is_free=*
Disallow: /catalogue/*is_french_domain=*
Disallow: /catalogue/*language_id=*
Disallow: /catalogue/*price_group=*
Disallow: /catalogue/*sort=*
Disallow: /catalogue/*tag_id=*
Disallow: /catalogue/*theme_id=*
Disallow: /DataCapture/
Disallow: /Error
Disallow: /Error/
Disallow: /Facebook/
Disallow: /Feedback/
Disallow: /FlashReader/Page
Disallow: /Image/
Disallow: /page/*access_type=*
Disallow: /page/*category_id=*
Disallow: /page/*is_free=*
Disallow: /page/*is_french_domain=*
Disallow: /page/*language_id=*
Disallow: /page/*price_group=*
Disallow: /page/*sort=*
Disallow: /page/*tag_id=*
Disallow: /page/*theme_id=*
Disallow: /page/products/
Disallow: /Premium/LeadSharingProcess/
Disallow: /Premium/Payment/
Disallow: /Product/Certify/
Disallow: /Product/Download/
Disallow: /Product/DownloadFile/
Disallow: /Product/LoadCommentReplies*
Disallow: /Product/LoadLikeProducts/
Disallow: /Product/LoadRelatedProducts/
Disallow: /Product/PublishComplete/
Disallow: /Product/Report/
Disallow: /Product/ReportInfraction/
Disallow: /Product/Share/
Disallow: /ProductPage/LoadCommentReplies*
Disallow: /ProductPage/ReplyComment/
Disallow: /Public/GetLibraryProducts/
Disallow: /Search
Disallow: /Search/
Disallow: /Stat/ViewProduct/
Disallow: /Static/ConcoursPubliezEtGagnez
Disallow: /Static/Js/
Disallow: /Static/MeteoJob/
Disallow: /Static/Quiz/*
Disallow: /Static/RedirectAction
Disallow: /Static/Tracking
Disallow: /Subscription/*
Disallow: /tag/*access_type=*
Disallow: /tag/*category_id=*
Disallow: /tag/*is_free=*
Disallow: /tag/*is_french_domain=*
Disallow: /tag/*language_id=*
Disallow: /tag/*page=*
Disallow: /tag/*sort=*
Disallow: /tag/*tag_id=*
Disallow: /tag/*theme_id=*
Disallow: /*?ni=1
Disallow: /communaute/
Disallow: /communaute/*
Disallow: /plan/communaute/
Disallow: /plan/communaute/*

User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: ShopWiki
Disallow: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
User-agent: wget
Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /



Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_audiobooks.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_bd.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_documents.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_documents_scolaires.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_ebooks.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_partitions.xml
Sitemap: https://www.youscribe.com/sitemaps/ys_fr_catalog_presse.xml