# =========================================
# VCCINEWS ROBOTS
# =========================================

# Last update: 2026-05-12

# =========================================
# GLOBAL RULE
# =========================================

User-agent: *
Disallow: /news/home
Disallow: /cate.asp?cate_id=947
Disallow: /cms/
Disallow: /inc/
Disallow: /Library/
Disallow: /sass/
Disallow: /.well-known/
Disallow: /ckupload/
Disallow: /admin/
Disallow: /upload/files/
Disallow: /upload/temp/

Allow: /css/
Allow: /js/
Allow: /images/
Allow: /fonts/

# Giảm crawl thông thường
Crawl-delay: 5

# =========================================
# AI CRAWLERS
# =========================================

User-agent: Scrapy
Disallow: /

User-agent: trendictionbot
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: meta-webindexer
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: facebookexternalhit
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: cohere-ai
Disallow: /

# =========================================
# SEO / SCRAPER / AGGRESSIVE BOTS
# =========================================

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: SeekportBot
Disallow: /

User-agent: trendictionbot
Disallow: /

# =========================================
# SEARCH ENGINES KHÔNG MONG MUỐN
# =========================================

User-agent: Baiduspider
Disallow: /

User-agent: YandexBot
Disallow: /

# =========================================
# SITEMAP
# =========================================

Sitemap: https://vccinews.com/sitemap.xml