# ------------------------------------------
# robots.txt for https://www.mithilatoday.com/
# Last Updated: 25 Oct 2025
# ------------------------------------------

User-agent: *

# ------------------------------------------
# Core & Functional Rules
# ------------------------------------------
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Disallow: /wp-login.php
Disallow: /wp-register.php
Disallow: /trackback/
Disallow: /*/feed/
Disallow: /*/feed

# ------------------------------------------
# Disallow sensitive and duplicate paths
# ------------------------------------------
Disallow: /adblocker
Disallow: /?s=
Disallow: /search/
Disallow: /readme.html

# ------------------------------------------
# Crawl rate control
# ------------------------------------------
Crawl-delay: 5

# ------------------------------------------
# AI & Data Scraper Bots (Blocked)
# ------------------------------------------
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /
User-agent: Anthropic-ai
Disallow: /
User-agent: Cohere-ai
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: YouBot
Disallow: /
User-agent: huggingface
Disallow: /
User-agent: DataForSeoBot
Disallow: /
User-agent: AwarioRssBot
Disallow: /
User-agent: AwarioSmartBot
Disallow: /
User-agent: Diffbot
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-Web
Disallow: /
User-agent: TurnitinBot
Disallow: /
User-agent: Scrapy
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: ImagesiftBot
Disallow: /
User-agent: Magpie-crawler
Disallow: /
User-agent: Omgili
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: news-please
Disallow: /

# ------------------------------------------
# Search Engine Bots (Allowed / Restricted)
# ------------------------------------------
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: DuckDuckBot
Allow: /
User-agent: Googlebot-News
Allow: /
Disallow: /sponsored/

# Social Bots
User-agent: FacebookBot
Disallow: /
User-agent: Twitterbot
Allow: /
User-agent: LinkedInBot
Allow: /

# ------------------------------------------
# Sitemaps
# ------------------------------------------
Sitemap: https://www.mithilatoday.com/sitemap-news.xml
Sitemap: https://www.mithilatoday.com/sitemap_index.xml
Sitemap: https://www.mithilatoday.com/post-sitemap2.xml
Sitemap: https://www.mithilatoday.com/post-sitemap1.xml
Sitemap: https://www.mithilatoday.com/category-sitemap.xml
Sitemap: https://www.mithilatoday.com/post_tag-sitemap.xml
Sitemap: https://www.mithilatoday.com/page-sitemap.xml