# 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

# General Directives - All User Agents
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /login/
Disallow: /checkout/
Disallow: /user-profile/
Disallow: /cart/
Disallow: /search/
Disallow: /wp-admin/
Disallow: /*? 
Allow: /wp-content/uploads/
Allow: /blog/
Allow: /our-courses/
Allow: /popular-online-courses/
Allow: /course/
Disallow: /all-courses/
Disallow: /course-category/
Disallow: /course-tag/
Disallow: /all-courses/*
Disallow: /tag/
Disallow: /category/*?category=*
Disallow: /our-courses/course-category-*
Disallow: /our-courses/course-category-*/tag-*
Disallow: /our-courses/course-category-extended-*/*/tag-*
Disallow: /our-courses/tag-*
Disallow: /*.pdf$
Disallow: /cgi-bin/
Disallow: /private/
Disallow: /tmp/ 

# Block Specific File Types
Disallow: /*.php$
Disallow: /*.cgi$
Disallow: /*.pl$
Disallow: /*.jsp$
Disallow: /*.asp$
Disallow: /*.aspx$

# Sitemap
Sitemap: https://www.lsbr.uk/sitemap_index.xml

# Googlebot Specific Directives
User-agent: Googlebot
Allow: /wp-content/
Allow: /wp-includes/js/
Allow: /*.js$
Allow: /*.css$
Disallow: /private/
Crawl-delay: 10

# Bingbot Specific Directives
User-agent: Bingbot
Sitemap: https://www.lsbr.uk/sitemap_index.xml
Allow: /images/
Allow: /videos/
Allow: /wp-content/uploads/
Allow: /our-courses/
Allow: /popular-online-courses/
Allow: /course/
Allow: /course-category/
Disallow: /private/
Disallow: /*?*
Crawl-delay: 5

# Yandexbot
User-agent: Yandex
Sitemap: https://www.lsbr.uk/sitemap_index.xml
Allow: /course-catalog/
Allow: /our-courses/
Allow: /popular-online-courses/
Allow: /course/
Allow: /course-category/
Allow: /blog/
Crawl-delay: 10

# Baiduspider
User-agent: Baiduspider
Sitemap: https://www.lsbr.uk/sitemap_index.xml
Allow: /course-catalog/
Allow: /our-courses/
Allow: /popular-online-courses/
Allow: /course/
Allow: /course-category/
Allow: /blog/
Disallow: /private/
Crawl-delay: 10

# Social Media Bots
User-agent: Twitterbot
Allow: /public/
Disallow: /private/
User-agent: facebookexternalhit
Allow: /public/
Disallow: /private/
User-agent: LinkedInBot
Allow: /public/
Disallow: /private/

# Block Known Spam and Data Harvesting Bots
User-agent: AhrefsBot
Disallow: /
User-agent: SEMrushBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: Barkrowler
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: MauiBot
Disallow: /
User-agent: Baiduspider-cpro
Disallow: /
User-agent: Sogou web spider
Disallow: /
User-agent: Exabot
Disallow: /
User-agent: SeznamBot
Disallow: /
User-agent: Screaming Frog SEO Spider
Disallow: /
User-agent: ZoominfoBot
Disallow: /
User-agent: Ezooms
Disallow: /
User-agent: FemtosearchBot
Disallow: /
User-agent: LinkpadBot
Disallow: /
User-agent: spbot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: PagePeeker
Disallow: /
User-agent: Wget
Disallow: /
User-agent: curl
Disallow: /
User-agent: HTTrack
Disallow: /
User-agent: Python-urllib
Disallow: /
User-agent: libwww-perl
Disallow: /
User-agent: UptimeRobot
Disallow: /
User-agent: PycURL
Disallow: /
User-agent: CheckMarkNetwork
Disallow: /
User-agent: SISTRIX
Disallow: /
User-agent: MegaIndex.ru
Disallow: /

# Additional Security Rules
User-agent: Mediapartners-Google
Disallow: /
User-agent: AdsBot-Google
Disallow: /
User-agent: YisouSpider
Disallow: /
User-agent: Daumoa
Disallow: /
User-agent: wotbox
Disallow: /
User-agent: SurveyBot
Disallow: /
User-agent: XoviBot
Disallow: /
User-agent: Findxbot
Disallow: /
User-agent: B2B Bot
Disallow: /