# *
User-agent: *
Allow: /

# Host
Host: https://matchbest.ai/

User-agent: Slurp
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 2

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

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

User-agent: facebookexternalhit
Allow: /
Crawl-delay: 1

User-agent: Twitterbot
Allow: /
Crawl-delay: 1

User-agent: LinkedInBot
Allow: /
Crawl-delay: 1

# Block known malicious and scraping bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SEOkicks
Disallow: /

User-agent: Cliqzbot
Disallow: /

User-agent: archive.org_bot
Disallow: /

User-agent: spbot
Disallow: /

User-agent: ScoutJet
Disallow: /

# Block headless browsers and automation tools
User-agent: HeadlessChrome
Disallow: /

User-agent: Selenium
Disallow: /

User-agent: PhantomJS
Disallow: /

User-agent: Nightmare
Disallow: /

User-agent: Puppeteer
Disallow: /

# Block AI training data scrapers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

# Block common scraping tools
User-agent: Scrapy
Disallow: /

User-agent: Python-urllib
Disallow: /

User-agent: java
Disallow: /

User-agent: okhttp
Disallow: /

User-agent: curl
Disallow: /

User-agent: wget
Disallow: /

# Block API access from scrapers
Disallow: /api/
Disallow: /_next/

# Allow sitemap
Allow: /sitemap.xml
Allow: /robots.txt

# Sitemap location
Sitemap: https://www.matchbest.ai/sitemap.xml