# 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 - AOTHUNPLUS (XƯỞNG MAY & IN ÁO THUN ĐỒNG PHỤC PHAN THIẾT)
# Điều hướng Googlebot, Googlebot-Image, Bingbot, Zalo/Facebook Crawler
# tập trung thu thập dữ liệu cấu trúc cây và ngăn chặn các thư mục hệ thống.
# =============================================================================

User-agent: *
Allow: /
Allow: /ao-polo/
Allow: /ao-polo-3d/
Allow: /ao-hawaii-polo/
Allow: /ao-lop-nhom-su-kien/
Allow: /in-ao-theo-yeu-cau/
Allow: /in-sieu-toc-lay-ngay-trong-ngay/
Allow: /quy-trinh/
Allow: /dich-vu/
Allow: /gioi-thieu/
Allow: /tin-tuc/
Allow: /lien-he/
Allow: /wp-content/uploads/

# Ngăn các bot thu thập các thư mục quản trị, công cụ nội bộ và tham số rác
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-content/uploads/wc-logs/
Disallow: /wp-content/uploads/woocommerce_transient_files/
Disallow: /wp-content/uploads/woocommerce_uploads/
Disallow: /scripts/
Disallow: /tools/
Disallow: /temp/
Disallow: /scratch/
Disallow: /*?add-to-cart=
Disallow: /*?*add-to-cart=
Disallow: /*?replytocom=
Disallow: /*?s=

# Cho phép Googlebot-Image lập chỉ mục toàn bộ hình ảnh mẫu áo thực tế tại Phan Thiết
User-agent: Googlebot-Image
Allow: /wp-content/uploads/
Allow: /ao-bosung/
Allow: /du-lieu-hinh-anh/

# Khai báo Sitemap thời gian thực (Tree-structured XML Sitemap)
Sitemap: https://aothunplus.com/sitemap.xml