# Cloudrevels Website - robots.txt
# Last Updated: December 18, 2025
#
# This file tells search engine crawlers which pages they can and cannot access
# on the Cloudrevels website.

# Allow all search engines to crawl the site
User-agent: *
Allow: /

# Disallow API routes and internal directories
Disallow: /api/
Disallow: /_next/

# Disallow alternative home page layouts (not used in production)
Disallow: /home1
Disallow: /home3

# Disallow template/example pages that shouldn't be indexed
Disallow: /blog/blog-details
Disallow: /service/service-details
Disallow: /project/project-details
Disallow: /blog-sidebar

# ===========================================
# BLOCK SPAM/HACKED URLs FROM OLD WORDPRESS
# These are casino/gambling spam URLs that were injected
# into the old theme. Block them from being crawled.
# ===========================================

# Block all date-based archive URLs (spam content)
Disallow: /2020/
Disallow: /2021/
Disallow: /2022/
Disallow: /2023/
Disallow: /2024/
Disallow: /2025/
Disallow: /2026/

# Block WordPress category/tag/archive patterns
Disallow: /category/
Disallow: /tag/
Disallow: /author/
Disallow: /page/
Disallow: /feed/
Disallow: /cate/

# Block WordPress system files
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /xmlrpc.php

# Block common spam patterns seen in the indexed URLs
Disallow: /*casino*
Disallow: /*slot*
Disallow: /*poker*
Disallow: /*gambling*
Disallow: /*betting*
Disallow: /*roulette*
Disallow: /*blackjack*
Disallow: /*jackpot*

# Block feed URLs anywhere
Disallow: */feed/
Disallow: */feed

# XML Sitemap location (use www version for consistency)
Sitemap: https://www.cloudrevels.com/sitemap.xml