# Mejix robots.txt
# https://www.mejix.com

# Default rules for all crawlers
User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /api/
# Legacy WordPress crawl waste — RSS feeds, oEmbed endpoints, attachment
# variants and tracking-parameter duplicates that split crawl budget.
Disallow: /*/feed
Disallow: /*/feed/
Disallow: /*/embed
Disallow: /*/transparent
Disallow: /*?utm_
Disallow: /*?fbclid
Disallow: /*?gclid
Disallow: /wp-content/
Disallow: /wp-json/
Disallow: /wp-admin/
Disallow: /wp-includes/

# Major search engines — explicit allow
User-agent: Googlebot
Allow: /
Disallow: /admin

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /
Disallow: /admin

User-agent: DuckDuckBot
Allow: /
Disallow: /admin

User-agent: Applebot
Allow: /
Disallow: /admin

User-agent: YandexBot
Allow: /
Disallow: /admin

# Social preview crawlers
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Discordbot
Allow: /

# AI crawlers — allow indexing
User-agent: GPTBot
Allow: /
Disallow: /admin

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

# Block aggressive scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Sitemap
Sitemap: https://www.mejix.com/sitemap.xml