# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# The FULL URL to the DSpace sitemaps
# The https://bvearmb.edu.do will be auto-filled with the value in dspace.cfg
# XML sitemap is listed first as it is preferred by most search engines
Sitemap: https://bvearmb.edu.do/sitemap
Sitemap: https://bvearmb.edu.do/htmlmap

##########################
# Default Access Group
# (NOTE: blank lines are not allowable in a group record)
##########################
User-agent: *
Crawl-delay: 5  
# Disable access to Discovery search and filters
Disallow: /discover
Disallow: /search-filter
Allow: /

#
# Optionally uncomment the following line ONLY if sitemaps are working
# and you have verified that your site is being indexed correctly.
# Disallow: /browse
# Disallow: /handle/123456789/*/browse
#
# If you have configured DSpace (Solr-based) Statistics to be publicly 
# accessible, then you may not want this content to be indexed
# Disallow: /statistics
#
# You also may wish to disallow access to the following paths, in order
# to stop web spiders from accessing user-based content
Disallow: /contact
Disallow: /feedback
Disallow: /forgot
Disallow: /login
Disallow: /register