# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
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

# $Id$

Sitemap: https://www.videolan.org/sitemap-https.xml

User-agent: *
Disallow: /pub
Disallow: /removed
Disallow: /doc/logs
Disallow: /mirror.php
Disallow: /mirror-geo.php
Disallow: /mirror-geo-redirect.php
Disallow: /vlc/download-skins2-go.php
Disallow: /private
Disallow: /~videolan/
Disallow: /developers/vlc/po
Disallow: /developers/vlc-branch/po

# Do not crawl CVS and .svn directories
User-agent: *
Disallow: CVS
Disallow: .svn

# "This robot collects content from the Internet for the sole purpose of
# helping educational institutions prevent plagiarism. [...] we compare
# student papers against the content we find on the Internet to see if we
# can find similarities." (http://www.turnitin.com/robot/crawlerinfo.html)
#  --> fuck off.
User-Agent: TurnitinBot
Disallow: /

# "NameProtect engages in crawling activity in search of a wide range of
# brand and other intellectual property violations that may be of interest
# to our clients." (http://www.nameprotect.com/botinfo.html)
#  --> fuck off.
User-Agent: NPBot
Disallow: /

# "iThenticate® is a new service we have developed to combat the piracy
# of intellectual property and ensure the originality of written work for#
# publishers, non-profit agencies, corporations, and newspapers."
# (http://www.slysearch.com/)
#  --> fuck off.
User-Agent: SlySearch
Disallow: /