# NOTICE: The collection of content and other data on this
# site through automated means, including any device, tool,
# or process designed to data mine or scrape content, is
# prohibited except (1) for the purpose of search engine indexing or
# artificial intelligence retrieval augmented generation or (2) with express
# written permission from this site’s operator.

# To request permission to license our intellectual
# property and/or other materials, please contact this
# site’s operator directly.

# BEGIN Cloudflare Managed content

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Robots.txt for Heleum Internship Reviews
# Optimized for maximum search engine indexing

User-agent: *
Allow: /

# Explicitly allow important pages
Allow: /index.html
Allow: /sitemap.xml
Allow: /robots.txt

# Allow all major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

User-agent: DuckDuckBot
Allow: /
Crawl-delay: 1

User-agent: Baiduspider
Allow: /
Crawl-delay: 2

User-agent: YandexBot
Allow: /
Crawl-delay: 1

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

# Disallow unnecessary files to focus crawling budget
Disallow: /create_favicon.html
Disallow: /generate_favicon.html
Disallow: /*.log$
Disallow: /.htaccess$
Disallow: /.htaccess_backup$

# Sitemap location (critical for indexing)
Sitemap: https://heleum-internship-reviews.com/sitemap.xml

# Host directive for canonical domain
Host: heleum-internship-reviews.com