# 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

# ====================================================================
# robots.txt для Механіко-математичного факультету
# ====================================================================

# Посилання на офіційні XML карти сайту
Sitemap: https://mmf.lnu.edu.ua/component/osmap/?view=xml&id=1&format=xml
Sitemap: https://mmf.com.ua/en/component/osmap/?view=xml&id=1&format=xml

# Обмеження для Microsoft Bing (дозволяємо індексацію, але повільно)
User-agent: Bingbot
Crawl-delay: 10
Disallow: /administrator/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/
# Блокування внутрішнього пошуку для Bing
Disallow: /component/search/
Disallow: /component/finder/
Disallow: /*?searchword=
Disallow: /*?searchphrase=
Disallow: /*?q=

# Повне блокування непотрібних комерційних та ШІ-ботів
User-agent: sentibot
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: SemrushBot
User-agent: DotBot
User-agent: PetalBot
User-agent: Bytespider
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Anthropic-ai
Disallow: /

# Загальні правила для Google та інших легітимних роботів
User-agent: *
Crawl-delay: 5

# Стандартні технічні папки Joomla (закриваємо від індексу)
Disallow: /administrator/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /components/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /modules/
Disallow: /plugins/
Disallow: /tmp/

# Блокування внутрішнього пошуку сайту (захист від SEO-спаму)
Disallow: /component/search/
Disallow: /component/finder/
Disallow: /*?searchword=
Disallow: /*?searchphrase=
Disallow: /*?q=

# Блокування відомих шляхів хакерського спаму (Казино/Слоти)
Disallow: /app/
Disallow: /game/
Disallow: /topic/
Disallow: /guide/
Disallow: /*?*halobet
Disallow: /*?*slot
Disallow: /*jawa138*
Disallow: /*tipobet*
Disallow: /*planet88*

# Дозволяємо роботам бачити стилі, скрипти та картинки в системних папках
Allow: /components/*.js
Allow: /components/*.css
Allow: /modules/*.js
Allow: /modules/*.css
Allow: /plugins/*.js
Allow: /plugins/*.css