Search

#05-Feb-26: all user agents
User-agent: *
Disallow: /0000-*/
Disallow: /accueil/
Disallow: /bas*/
Disallow: /*jahia/
Disallow: /ex*/
Disallow: /Jahia/
Disallow: /refonte-*/
Disallow: /test*/
Disallow: /modules/
Disallow: /webdav/
Disallow: /cms/
Disallow: /generated-resources/
Disallow: /*?*actunilMenuParam=*
Disallow: /*?*actunilParam=*
Disallow: /*?*c=*
Disallow: /*?*cl=*
Disallow: /*?*doLogin=*
Disallow: /*?*matrix=*
Disallow: /*?*pubsIdParam=*
Disallow: /*?*redirect=*
Disallow: /*?*rememberme=*
Disallow: /*?*set_language=*
Disallow: /*?*showActu=*
Disallow: /*?*showFrom=*
Disallow: /*?*site=*
Disallow: /*?*url_params=*
Disallow: /*?*url=*
Disallow: /*?*utm_campaign=*
Disallow: /*?*utm_medium=*
Disallow: /*?*utm_source_platform=*
Disallow: /*?*utm_source=*
Disallow: /*?*CSRFTOKEN=*
Disallow: /*?*channelIds=*
Disallow: /*?*sortedBy=*
Disallow: /*?*status=*
Disallow: /*?*publicationStatus=*
Disallow: /*?*summarize=*
Disallow: /*?*languages=*
Disallow: /*?*size=*
Disallow: /*?*windowDays=*
Disallow: /*?*resourceType=*
Disallow: /*?*resourceId=*
Disallow: /*?*eco=*
Disallow: /*?*beginEventDate=*
Disallow: /*?*endEventDate=*
Disallow: /*?*nodeIdK=*
Disallow: /*?*parentNodeIdK=*
Disallow: /*mobileMenu.do*
Disallow: /*resourcesProxy.do*
Disallow: /*generateEventIcs.do*
Disallow: /*newsMostViewedProxy.do*
Disallow: /*newsProxy.do*
Disallow: /*eventsProxy.do*
Disallow: /*?*cat_publication*
Disallow: /*?*cat_mastersthesis*
Disallow: /*?*cat_phdthesis=*
Disallow: /*?*current_cat*
Allow: /

#26-Feb-24: add sitemaps index
Sitemap: https://www.unil.ch/sitemap_www.xml

#30-Jun-26: exclude some ai bots
# Block all known AI crawlers and assistants
# from using content for training AI models.
# Source: https://robotstxt.com/ai
User-Agent: GPTBot
User-Agent: ClaudeBot
User-Agent: Claude-User
User-Agent: Claude-SearchBot
User-Agent: CCBot
User-Agent: Google-Extended
User-Agent: Applebot-Extended
User-Agent: Facebookbot
User-Agent: Meta-ExternalAgent
User-Agent: Meta-ExternalFetcher
User-Agent: diffbot
User-Agent: PerplexityBot
User-Agent: Perplexity‑User
User-Agent: Omgili
User-Agent: Omgilibot
User-Agent: webzio-extended
User-Agent: ImagesiftBot
User-Agent: Bytespider
User-Agent: TikTokSpider
User-Agent: Amazonbot
User-Agent: Youbot
User-Agent: SemrushBot-OCOB
User-Agent: Petalbot
User-Agent: VelenPublicWebCrawler
User-Agent: TurnitinBot
User-Agent: Timpibot
User-Agent: OAI-SearchBot
User-Agent: ICC-Crawler
User-Agent: AI2Bot
User-Agent: AI2Bot-Dolma
User-Agent: DataForSeoBot
User-Agent: AwarioBot
User-Agent: AwarioSmartBot
User-Agent: AwarioRssBot
User-Agent: Google-CloudVertexBot
User-Agent: PanguBot
User-Agent: Kangaroo Bot
User-Agent: Sentibot
User-Agent: img2dataset
User-Agent: Meltwater
User-Agent: Seekr
User-Agent: peer39_crawler
User-Agent: cohere-ai
User-Agent: cohere-training-data-crawler
User-Agent: DuckAssistBot
User-Agent: Scrapy
User-Agent: Cotoyogi
User-Agent: aiHitBot
User-Agent: Factset_spyderbot
User-Agent: FirecrawlAgent
User-Agent: bedrockbot
User-Agent: DeepSeekBot
User-Agent: GoogleAgent-Mariner
User-Agent: Gemini-Deep-Research
User-Agent: Google-NotebookLM
User-Agent: Google-Agent
User-Agent: GoogleAgent-URLContext
User-Agent: Google-Firebase
User-Agent: MistralAI-User
User-Agent: SemrushBot-FT
User-Agent: SemrushBot-ESI
User-Agent: AddSearchBot
User-Agent: bigsur.ai
User-Agent: Brightbot
User-Agent: Crawlspace
User-Agent: EchoboxBot
User-Agent: FriendlyCrawler
User-Agent: LinerBot
User-Agent: Panscient
User-Agent: Panscient.com
User-Agent: Poseidon Research Crawler
User-Agent: SBIntuitionsBot
User-Agent: TerraCotta
User-Agent: Thinkbot
User-Agent: Yak
User-Agent: YandexAdditional
User-Agent: YandexAdditionalBot
Disallow: /
DisallowAITraining: /

## Block any non-specified AI crawlers (e.g., new
## or unknown bots) from using content for training
## AI models, while allowing the website to be
## indexed and accessed by bots.  These directives
## are still experimental and may not be supported
## by all AI crawlers.
#User-Agent: *
#DisallowAITraining: /
#Content-Usage: ai=n
#Content-Signal: search=yes, ai-input=no, ai-train=no
#Allow: /

# In case of security incidents please contact our CSIRT.
Contact: mailto:security@unil.ch

# For vulnerability reports.
Contact: mailto:security@unil.ch

Preferred-Languages: fr, en, de
Canonical: https://www.unil.ch/.well-known/security.txt

Expires: 2026-12-31T23:59:59.999Z