# 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.

# 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.


# ------------------------------------------------------------
# DEFAULT CRAWLER POLICY
# ------------------------------------------------------------

User-agent: *
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Restricted application/internal paths
Disallow: /admin/
Disallow: /mobile/viewer/
Disallow: /bt/
Disallow: /home/
Disallow: /genericdb/
Disallow: /dailyartshow/
Disallow: /engine/

# Restricted file/resource patterns
Disallow: /*cloudflare.js
Disallow: /*.php


# ------------------------------------------------------------
# BLOCKED CRAWLERS
# ------------------------------------------------------------

User-agent: MJ12bot
User-agent: swebot
User-agent: aihitbot
User-agent: Exabot
User-agent: sitebot
User-agent: TwengaBot-Discover
User-agent: dataprovider
User-agent: Ezooms
User-agent: Bender
User-agent: discobot
User-agent: panscient.com
User-agent: searchwebengine.net
User-agent: MLBot
User-agent: NextGenSearchBot
User-agent: Speedy
User-agent: dotbot
User-agent: AhrefsBot
User-agent: NerdByNature.Bot
User-agent: WBSearchBot
User-agent: sistrix
User-agent: SindiceBot
User-agent: plukkie
User-agent: findfiles.net
User-agent: SeznamBot
User-agent: Goodzer
User-agent: BacklinkCrawler
User-agent: lemurwebcrawler
User-agent: gigabot
User-agent: ccbot
User-agent: TurnitinBot
User-agent: EdisterBot
User-agent: Baiduspider
User-agent: HuaweiSymantecSpider
User-agent: PagePeeker
User-agent: YandexBot
User-agent: Yandex
User-agent: meta-externalagent
Disallow: /

Sitemap: https://www.saranaclakeartworks.org/sitemap.xml