# 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.

# BEGIN Cloudflare Managed content

User-Agent: *
Content-signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

Allow: facebookexternalhit
Allow: facebookexternalhit
Disallow: /rek
Disallow: /bn

User-agent: Mediapartners-Google
Disallow:
 User-agent: AdsBot-Google
Disallow:
 User-agent: AdsBot-Google-Mobile
Disallow:
 User-agent: Googlebot
Disallow:
 User-agent: *
Disallow: /downloads/
Disallow: /.zip$
Disallow: /.pdf$
Disallow: /?download=
Sitemap: https://baltic-ireland.ie/sitemap.xml 

# BEGIN Magic robots.txt
# ---------------------------

# General
User-agent: *
Allow: 
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-admin/
Disallow: /readme.html$
Crawl-Delay: 0

# Debug mode: search engines -> calm
# Ad networks
# Debug mode: ad networks -> tame
User-agent: Mediapartners-Google
Crawl-Delay: 5
User-agent: AdsBot-Google
Crawl-Delay: 5
User-agent: proximic
Crawl-Delay: 5
User-agent: CriteoBot/0.1
Crawl-Delay: 5
User-agent: grapeshot
Crawl-Delay: 5

# Link analyzers
# Debug mode: link analyzers -> block
User-agent: AhrefsBot
Disallow: /
Crawl-Delay: 0
User-agent: SemrushBot
Disallow: /
Crawl-Delay: 0
User-agent: MJ12Bot
Disallow: /
Crawl-Delay: 0
User-agent: dotbot
Disallow: /
Crawl-Delay: 0
User-agent: BLEXBot
Disallow: /
Crawl-Delay: 0
User-agent: serpstatbot
Disallow: /
Crawl-Delay: 0
User-agent: DataForSeoBot
Disallow: /
Crawl-Delay: 0
User-agent: omgilibot
Disallow: /
Crawl-Delay: 0
User-agent: barkrowler
Disallow: /
Crawl-Delay: 0

# Downloaders
# Debug mode: downloaders -> block
User-agent: webreaper
Disallow: /
Crawl-Delay: 0
User-agent: MSIECrawler
Disallow: /
Crawl-Delay: 0
User-agent: WebCopier
Disallow: /
Crawl-Delay: 0
User-agent: HTTrack
Disallow: /
Crawl-Delay: 0
User-agent: VelenPublicWebCrawler
Disallow: /
Crawl-Delay: 0
User-agent: AwarioBot
Disallow: /
Crawl-Delay: 0
User-agent: AwarioRssBot
Disallow: /
Crawl-Delay: 0
User-agent: AwarioSmartBot
Disallow: /
Crawl-Delay: 0
User-agent: Amazonbot
Disallow: /
Crawl-Delay: 0

# Debug mode: Already have sitemap
# ---------------------------
# END Magic robots.txt