# 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

# Primary domain: megav.app
# All search engines should index only the primary domain
# Alternative domains redirect bots to primary domain for SEO consolidation

User-agent: *
Allow: /

# Sitemaps
Sitemap: https://megav.site/sitemap.xml
Sitemap: https://megav.site/news-sitemap.xml
Sitemap: https://megav.site/news-sitemap-index.xml

# Crawl-delay for respectful crawling
Crawl-delay: 1

# Allow all important pages
Allow: /en/
Allow: /ru/
Allow: /vi/
Allow: /de/

# Allow all VPN and service pages
Allow: /dns-servers
Allow: /internet-radio
Allow: /browser
Allow: /vpn-for-*
Allow: /encryption
Allow: /server-network
Allow: /split-tunneling
Allow: /no-logs-policy
Allow: /gdpr-compliance
Allow: /v2ray-servers
Allow: /iptv-playlists
Allow: /ip-checker
Allow: /ad-blocker
Allow: /adblock-test
Allow: /speed-test
Allow: /donate
Allow: /privacy-policy
Allow: /terms-of-service
Allow: /news-feeds/
Allow: /*/news-feeds/

# Allow XML and technical files
Allow: /sitemap.xml
Allow: /robots.txt
Allow: /news-sitemap.xml
Allow: /news-sitemap-index.xml
Allow: /news-sitemap/

# Disallow admin/private areas and technical files
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /.well-known/