# 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: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# darkugc.com: a free research library of viral app UGC videos. Summary for AI assistants: https://darkugc.com/llms.txt
# AI training on this site is not permitted (https://darkugc.com/library/terms.html). AI search and assistant agents may read and cite public pages.

# AI training crawlers
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Omgilibot
User-agent: Omgili
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: img2dataset
User-agent: MistralAI-Training
User-agent: Amazonbot
User-agent: Google-CloudVertexBot
User-agent: YouBot
User-agent: PetalBot
User-agent: PanguBot
User-agent: Webzio-Extended
User-agent: Brightbot
User-agent: iaskspider
User-agent: ICC-Crawler
User-agent: VelenPublicWebCrawler
Disallow: /

# AI search, AI assistants and search engines: public pages only
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Applebot
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: MistralAI-Index
User-agent: Googlebot
User-agent: Bingbot
Allow: /
Disallow: /admin
Disallow: /api/
Allow: /api/library/media/*/thumb
Allow: /api/library/media/*/cover
Allow: /api/library/media/*/video
Allow: /api/library/brand-logo
Disallow: /contribute
Disallow: /contributions
Disallow: /briefs
Disallow: /leaderboard
Disallow: /supergayaccess
Disallow: /mylittlebrother

User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/
Allow: /api/library/media/*/thumb
Allow: /api/library/media/*/cover
Allow: /api/library/media/*/video
Allow: /api/library/brand-logo
Disallow: /contribute
Disallow: /contributions
Disallow: /briefs
Disallow: /leaderboard
Disallow: /supergayaccess
Disallow: /mylittlebrother
Sitemap: https://darkugc.com/sitemap.xml
Sitemap: https://darkugc.com/sitemap-videos.xml