# 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.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: Bytespider
Disallow: /

User-agent: Sogou web spider
Disallow: /

User-agent: Sogou inst spider
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: ClaudeBot/1.0
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: omgili
Disallow: /

User-agent: AcademicBotRTU
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: test-bot
Disallow: /

User-agent: *
# Take into account both the default view and any non-default views
# (hence two versions of each url)
Crawl-delay: 1
Disallow: /AJAX/
Disallow: /*/AJAX/
Disallow: /Search/FacetList
Disallow: /*/Search/FacetList
# Block QRCodes:
Disallow: /QRCode/
Disallow: /*/QRCode/
# Block any api version:
Disallow: /*/api/
Disallow: /*/*/api/
Disallow: /MetaLib/
Disallow: /*/MetaLib/
Disallow: /Primo/
Disallow: /*/Primo/
Disallow: /PrimoRecord/
Disallow: /*/PrimoRecord/
Disallow: /Record/*/Holdings
Disallow: /*/Record/*/Holdings
Disallow: /SearchApi/
Disallow: /*/SearchApi/
Disallow: /EDS/
Disallow: /*/EDS/
Disallow: /EdsRecord/
Disallow: /*/EdsRecord/
Disallow: /Summon/
Disallow: /*/Summon/
Disallow: /SummonRecord/
Disallow: /*/SummonRecord/
Disallow: /Record/DownloadFile
# Allow indexing of record pages by commenting out the following two lines:
Disallow: /Record/
Disallow: /*/Record/

Disallow: /AJAX/
Disallow: */AJAX/
Disallow: /Blender/
Disallow: */Blender/
Disallow: /Browse/
Disallow: */Browse/
Disallow: /EDS/
Disallow: */EDS/
Disallow: /EDSRecord/
Disallow: */EDSRecord/
Disallow: /L1/
Disallow: */L1/
Disallow: /MyResearch/
Disallow: */MyResearch/
Disallow: /Primo/
Disallow: */Primo/
Disallow: /PrimoRecord/
Disallow: */PrimoRecord/
Disallow: /QRCode/
Disallow: */QRCode/
Disallow: /Search/
Disallow: */Search/
Disallow: /Search2/
Disallow: */Search2/
Disallow: /Summon/
Disallow: */Summon/
Disallow: /SummonRecord/
Disallow: */SummonRecord/
Sitemap: https://koulutus.finna.fi/sitemapIndex.xml.gz