# =========================================
# AIChipLink Robots.txt
# Updated: 2025-12
# Purpose: Optimize crawl efficiency, protect bandwidth, and improve SEO
# =========================================

User-agent: *
Allow: /
Disallow: /login
Disallow: /search
Disallow: /cart
Disallow: /checkout
Disallow: /user/
Disallow: /admin/
Disallow: /zh_hant/
Disallow: /zh_hants/
Disallow: /ru/

# =========================================
# AI Crawlers
# =========================================
User-agent: GPTBot
Allow: /
Crawl-delay: 5

User-agent: OAI-SearchBot
Allow: /
Crawl-delay: 5

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 5

User-agent: ClaudeBot
Allow: /
Crawl-delay: 5

User-agent: Claude-User
Allow: /
Crawl-delay: 5

User-agent: PerplexityBot
Allow: /
Crawl-delay: 5

User-agent: Perplexity-User
Allow: /
Crawl-delay: 5

User-agent: Meta-ExternalAgent
Allow: /
Crawl-delay: 5

User-agent: Meta-ExternalFetcher
Allow: /
Crawl-delay: 5

User-agent: MistralAI-User
Allow: /
Crawl-delay: 5

User-agent: Novellum
Allow: /
Crawl-delay: 5

User-agent: ProRataInc
Allow: /
Crawl-delay: 5

User-agent: Timpibot
Allow: /
Crawl-delay: 5

User-agent: archive.org_bot
Allow: /
Crawl-delay: 5

User-agent: CCBot
Allow: /
Crawl-delay: 5

# =========================================
# SEO Tools / Data Crawlers (Blocked)
# =========================================
User-agent: AhrefsBot
Disallow: /
User-agent: SEMrushBot
Disallow: /
User-agent: SemrushBot-SA
Disallow: /
User-agent: Majestic SEO
Disallow: /
User-agent: SISTRIX Crawler
Disallow: /
User-agent: seoscanners.net
Disallow: /
User-agent: BuiltWith
Disallow: /
User-agent: Sitebulb
Disallow: /
User-agent: RavenCrawler
Disallow: /
User-agent: deepcrawl
Disallow: /
User-agent: SEOkicks
Disallow: /
User-agent: SEOkicks-Robot
Disallow: /
User-agent: Searchmetrics
Disallow: /
User-agent: magpie-crawler
Disallow: /
User-agent: NinjaBot
Disallow: /
User-agent: adscanner
Disallow: /
User-agent: AwarioBot
Disallow: /

# =========================================
# Low-value regional crawlers (Blocked)
# =========================================
User-agent: BLEXBot
Disallow: /
User-agent: WBSearchBot
Disallow: /
User-agent: Yeti
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: Linespider
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: ICC-Crawler
Disallow: /
User-agent: SeznamBot
Disallow: /
User-agent: naver
Disallow: /
User-agent: Daum Bot
Disallow: /
User-agent: Baiduspider
Disallow: /
User-agent: Sogou web spider
Disallow: /
User-agent: 360Spider
Disallow: /
User-agent: HaosouSpider
Disallow: /
User-agent: YisouSpider
Disallow: /

# =========================================
# Controlled Crawlers (Rate limited)
# =========================================
User-agent: Amazonbot
Crawl-delay: 200
User-agent: facebookexternalhit
Crawl-delay: 200

# =========================================
# Major Search Engines (Allowed)
# =========================================
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: PetalBot
Allow: /


# =========================================
# Sitemap Files
# =========================================
Sitemap: https://aichiplink.com/sitemaps/sitemap.xml
Sitemap: https://aichiplink.com/sitemaps/sitemap-main.xml
Sitemap: https://aichiplink.com/sitemaps/sitemap-blog.xml