# robots.txt - merisarkariyojana.in
# Last updated: 25 July 2026

# ---- 1) All normal crawlers (Googlebot, Bingbot etc.) ----
User-agent: *

Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /readme.html
Disallow: /license.txt

Disallow: /*?s=
Disallow: /*?replytocom=

Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /*/embed/

Allow: /wp-includes/
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /*.css$
Allow: /*.js$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.webp$
Allow: /*.svg$
Allow: /*.gif$

# ---- 2) AI assistants - full access ----
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: DuckAssistBot
User-agent: cohere-ai
User-agent: YouBot
User-agent: CCBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /*?s=

# ---- 3) Blocked ----
User-agent: Bytespider
Disallow: /

# ---- 4) Sitemap ----
Sitemap: https://merisarkariyojana.in/sitemap_index.xml