# 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

User-agent: *
Allow: /
Disallow: /auth/
# Unofficial client design concept - not Capitalism.com's own site.
# A robots file is only honoured at the origin root, so any copy shipped
# inside the concept is inert at a sub-path and THIS line is the one that
# counts. Every page there is also noindex.
Disallow: /capitalism-com/
Disallow: /cart
Disallow: /checkout/success
Disallow: /confirm-email
Disallow: /create-account
Disallow: /custom-hostname
Disallow: /forgot-password
# Unofficial client design concept - not Oregon Diner's own site.
# Same reasoning as the entries above: a sub-path robots.txt is never
# read, so this origin-root line is the only crawler directive that
# applies. Every page there is also noindex.
Disallow: /oregon-diner/
# Client design concepts / prospect pitch builds - not these companies' own
# sites. Same reasoning as the entries above: a robots file is only honoured
# at the origin root, so these origin-level lines are the only crawler
# directives that apply to a nested sub-path. Pages are also noindex.
Disallow: /portrex/
Disallow: /homeworks365/
Disallow: /homeworks365-fresh/
Disallow: /reset-password
Disallow: /sign-in
Disallow: /site-preview/
# Unofficial client design concept - not Grossman Furniture's own site.
# The concept ships its own disallow-all robots.txt, but a robots file is
# only honoured at the origin root, so that copy is inert at a sub-path and
# THIS line is the one that counts. Every page there is also noindex.
Disallow: /grossman-furniture/
# Example build hosted under this domain — a draft site with placeholder
# content. It cannot disallow itself: robots.txt only counts at a domain root.
Disallow: /mortgage-office/
Disallow: /verify-email
Disallow: /webinar/confirmed
Disallow: /webinar/watch
Disallow: /vsl/thank-you

Sitemap: https://leadcaravan.com/sitemap.xml