# 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: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# ═══════════════════════════════════════════════════════════════
# robots.txt — ScoreCC
# https://scorecc.com
# อัปเดต: 2025-03
# ═══════════════════════════════════════════════════════════════

# ── อนุญาต Bot หลักทุกตัว ──────────────────────────────────────
User-agent: *
Allow: /
Allow: /sitemap.xml
Allow: /pic/
Allow: /css/
Allow: /js/

# ── ห้าม Crawl ไฟล์ระบบและ Config ────────────────────────────
Disallow: /config.php
Disallow: /header.php
Disallow: /footer.php
Disallow: /*.log$
Disallow: /*.sql$
Disallow: /*.bak$
Disallow: /*.env$
Disallow: /tmp/
Disallow: /cache/
Disallow: /vendor/
Disallow: /node_modules/
Disallow: /.git/
Disallow: /.htaccess

# ── ป้องกัน Duplicate Content จาก Query Strings ──────────────
Disallow: /*?*mark=
Disallow: /*?*TimeZone=
Disallow: /*?*width=
Disallow: /*?*cpageBgColor=

# ── Google ─────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Googlebot-Image
Allow: /pic/
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.ico$
Allow: /*.webp$
Allow: /*.svg$

# ── Bing / MSN ─────────────────────────────────────────────────
User-agent: Bingbot
Allow: /
Crawl-delay: 2

# ── Yahoo ──────────────────────────────────────────────────────
User-agent: Slurp
Allow: /
Crawl-delay: 2

# ── DuckDuckGo ─────────────────────────────────────────────────
User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

# ── Yandex ─────────────────────────────────────────────────────
User-agent: YandexBot
Allow: /
Crawl-delay: 3

# ── Facebook / Meta OG Scraper ─────────────────────────────────
User-agent: facebookexternalhit
Allow: /

# ── Twitter / X Card Crawler ───────────────────────────────────
User-agent: Twitterbot
Allow: /

# ── LINE OpenGraph Crawler ─────────────────────────────────────
User-agent: LineCrawler
Allow: /

# ── GPTBot / AI Crawlers — ห้าม Train บนเนื้อหาเว็บ ──────────
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: PerplexityBot
Disallow: /

# ── Bad Bots / Scrapers ────────────────────────────────────────
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

# ── Sitemap ────────────────────────────────────────────────────
Sitemap: https://scorecc.com/sitemap.xml

# ── Host (canonical domain) ───────────────────────────────────
Host: scorecc.com