# 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

# See https://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file
#
# Search engines are welcome on every page here, and so is a crawler that
# fetches one page to answer a question somebody asked it and links back. The
# groups below are the other kind: crawlers whose operators say the pages they
# take may go into training a model. A puzzle on this site was written by a
# person and published under CC BY-SA 4.0, which asks for two things, credit
# and the same freedom passed on, and a model gives back neither.
#
# The reasoning is Orbit's decisions/0021-refuse-the-crawlers-that-train-models.md.
# The same refusal in the form a machine reads is /.well-known/tdmrep.json.
# What it promises a player is at /documentation/terms.
#
# The rule for editing this list: a crawler is here because its operator
# documents training as a use of what it takes. One that only fetches to answer
# and cite stays out of it, whatever its parent company also sells.

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: Meta-ExternalAgent
User-agent: meta-externalfetcher
User-agent: Amazonbot
User-agent: Bytespider
User-agent: TikTokSpider
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: Diffbot
User-agent: omgili
User-agent: omgilibot
User-agent: Webzio-Extended
User-agent: ImagesiftBot
User-agent: PanguBot
User-agent: Timpibot
User-agent: ICC-Crawler
User-agent: img2dataset
User-agent: FriendlyCrawler
Disallow: /

# Answer engines. These fetch a page because a reader asked something, show a
# few lines of it and link here, which is a visit. Written out rather than left
# to the wildcard so that a later blanket rule cannot swallow them by accident.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
Disallow:

# Everyone else is welcome on every page, and refused the LiveView socket.
#
# A crawler does not do WebSockets, so app.js boots, the socket fails and
# LiveView falls back to longpoll, which answers JSON and then asks again. On
# 2026-08-05 that had cost 41% of ten days of Google's crawling here, with
# another 39% on the grammar chunks pulled in behind it. HTML got 10%, and
# discovery, the part that puts a new page in the index, got 3%.
#
# None of it could ever rank. The dead render carries the whole page already;
# the socket only adds the interactivity a crawler has no use for. Blocking the
# two transports is safe for the same reason: the rule against hiding JavaScript
# from a crawler is about resources a page needs in order to render, and these
# run after it already has.
#
# Only the transports, and nothing under /assets. A grammar chunk is a rendering
# resource by that same test, and guessing which ones a crawler may skip is how
# a page ends up indexed with half of itself missing.
User-agent: *
Disallow: /live/longpoll
Disallow: /live/websocket

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