# 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

####################################################################
#   DEFAULT + AI / SEARCH BOTS (ALLOWED, SHARE THE SAME RULES)     #
####################################################################

User-agent: *
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Google-Extended
User-agent: Googlebot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: Amazonbot
User-agent: amazon-kendra
User-agent: Bytespider
User-agent: CCBot
User-agent: bingbot
User-agent: BingPreview
User-agent: FriendlyCrawler
User-agent: AhrefsBot
User-agent: SemrushBot
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /
Disallow: /*.docx
Disallow: /*.pdf
Disallow: /*.xlsx
Disallow: /*?page=
Disallow: /*?v=
Disallow: /*?search=
Disallow: /*?utm_
Disallow: /*?redirect=
Disallow: /referral
Disallow: /api
Disallow: /*?site=
Disallow: /*posts-manifest.js
Disallow: /assets/blog/covers/

Sitemap: https://joinotto.com/sitemap-index.xml

####################################################################
#          ----  SCRAPERS & BAD BOTS *BLOCKED*  ----              #
####################################################################

User-agent: SleepBot
Disallow: /

User-agent: AI2Bot
Disallow: /

User-agent: Brightbot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: iaskspider/2.0
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: img2dataset
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: LinerBot
Disallow: /

User-agent: MachineLearningForPeaceBot
Disallow: /

User-agent: Meltwater
Disallow: /

User-agent: Nicecrawler
Disallow: /

User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: PiplBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Scoop.it
Disallow: /

User-agent: Seekr
Disallow: /

User-agent: SemrushBot-OCOB
Disallow: /

User-agent: Sidetrade indexer bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: VelenPublicWebCrawler
Disallow: /

User-agent: Webzio-Extended
Disallow: /