# 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

User-agent: *
Allow: /

# Sitemaps
Sitemap: https://losslesspro.com/sitemap.xml

# Disallow admin areas
Disallow: /admin/
Disallow: /api/
Disallow: /livewire/
Disallow: /backoffice/
Disallow: /backend/
Disallow: /cgi-bin/
Disallow: /storage/
Disallow: /cache/
Disallow: /tmp/
Disallow: /api/
Disallow: /internal/
Disallow: /private/

# Allow crawling of public pages - All supported locales
# Locales: en, vi, fr, ja, ko, zh, de, pt, nl, ru

# Homepage for each locale
Allow: /en/
Allow: /vi/
Allow: /fr/
Allow: /ja/
Allow: /ko/
Allow: /zh/
Allow: /de/
Allow: /pt/
Allow: /nl/
Allow: /ru/

# Albums listing page
Allow: /en/albums
Allow: /vi/albums
Allow: /fr/albums
Allow: /ja/albums
Allow: /ko/albums
Allow: /zh/albums
Allow: /de/albums
Allow: /pt/albums
Allow: /nl/albums
Allow: /ru/albums

# Album detail pages
Allow: /en/album/
Allow: /vi/album/
Allow: /fr/album/
Allow: /ja/album/
Allow: /ko/album/
Allow: /zh/album/
Allow: /de/album/
Allow: /pt/album/
Allow: /nl/album/
Allow: /ru/album/

# Artists listing page
Allow: /en/artists
Allow: /vi/artists
Allow: /fr/artists
Allow: /ja/artists
Allow: /ko/artists
Allow: /zh/artists
Allow: /de/artists
Allow: /pt/artists
Allow: /nl/artists
Allow: /ru/artists

# Artist detail pages
Allow: /en/artist/
Allow: /vi/artist/
Allow: /fr/artist/
Allow: /ja/artist/
Allow: /ko/artist/
Allow: /zh/artist/
Allow: /de/artist/
Allow: /pt/artist/
Allow: /nl/artist/
Allow: /ru/artist/

# Products listing page
Allow: /en/products
Allow: /vi/products
Allow: /fr/products
Allow: /ja/products
Allow: /ko/products
Allow: /zh/products
Allow: /de/products
Allow: /pt/products
Allow: /nl/products
Allow: /ru/products

# Product detail pages
Allow: /en/product/
Allow: /vi/product/
Allow: /fr/product/
Allow: /ja/product/
Allow: /ko/product/
Allow: /zh/product/
Allow: /de/product/
Allow: /pt/product/
Allow: /nl/product/
Allow: /ru/product/

# Song detail pages
Allow: /en/song/
Allow: /vi/song/
Allow: /fr/song/
Allow: /ja/song/
Allow: /ko/song/
Allow: /zh/song/
Allow: /de/song/
Allow: /pt/song/
Allow: /nl/song/
Allow: /ru/song/


# ===========================
#   GOOGLE & MAJOR BOTS
# ===========================

# Google bots — full access
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Googlebot-Mobile
Allow: /

# Bing — allow but not overload
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# ===========================
#   LIMIT GPTBOT (OpenAI)
# ===========================

User-agent: GPTBot
Allow: /

Crawl-delay: 5

# Không cho train AI nếu bạn muốn
# Disallow: /

# ===========================
#   LIMIT AHREFSBOT
# ===========================

User-agent: AhrefsBot
Allow: /

Crawl-delay: 2

# ===========================
#   BLOCK BAD BOTS
# ===========================

# Blink (rác)
User-agent: BlinkBot
Disallow: /

# SemrushBot — rất nặng
User-agent: SemrushBot
Crawl-delay: 10

# DotBot — spam
User-agent: DotBot
Disallow: /

# MJ12bot — spam, rất nặng
User-agent: MJ12bot
Disallow: /