# robots.txt for itnow.net
# Allow major search engines and AI crawlers to index content for visibility

# Allow all major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
User-agent: YahooSeeker
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebookexternalhit
Allow: /

# Allow AI/LLM crawlers for enhanced visibility in AI search results
User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Block common administrative and sensitive areas
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/themes/
Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /wp-config.php
Disallow: /wp-cron.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt
Disallow: /cgi-bin/
Disallow: /private/
Disallow: /tmp/
Disallow: /?s=
Disallow: /search/
Disallow: /author/
Disallow: /tag/
Disallow: /*?replytocom
Disallow: /wp-content/cache/
Disallow: /wp-content/backup*/
Disallow: /trackback/
Disallow: */trackback/
Disallow: */feed/
Disallow: */comments/
Disallow: */attachment/

# Allow specific directories we want indexed
Allow: /wp-content/uploads/
Allow: /wp-content/themes/*/css/
Allow: /wp-content/themes/*/js/
Allow: /wp-content/themes/*/images/

# Block specific spam bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: Exabot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: BLEXBot
Disallow: /

# Crawl delay for heavy crawlers
User-agent: Bingbot
Crawl-delay: 1

User-agent: Slurp
Crawl-delay: 1

# Sitemap location
Sitemap: https://itnow.net/sitemap.xml
Sitemap: https://itnow.net/sitemap_index.xml