# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# MIF Technologies Robots.txt
# Last updated: 2026-06-03
# Website: https://www.miftechno.com

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

# Disallow sensitive/admin directories
Disallow: /assets/
Disallow: /css/
Disallow: /js/
Disallow: /fonts/
Disallow: /images/
Disallow: /temp/
Disallow: /backup/
Disallow: /admin/
Disallow: /includes/

# Disallow specific file types
Disallow: /*.pdf$
Disallow: /*.zip$
Disallow: /*.doc$
Disallow: /*.docx$

# Disallow common template/component files
Disallow: /components/
Disallow: /partials/

# Block bots from accessing form submission scripts
Disallow: /contact-form-handler/
Disallow: /careers-form-handler/

# Block access to error pages
Disallow: /error/
Disallow: /404.html
Disallow: /500.html

# Crawl delay to prevent server overload
Crawl-delay: 5

# Sitemap location
Sitemap: https://www.miftechno.com/sitemap.xml

# Specify crawl rate for specific bots (optional)
User-agent: Googlebot
Crawl-delay: 2

User-agent: Bingbot
Crawl-delay: 2

User-agent: Yandex
Crawl-delay: 3

User-agent: Baiduspider
Crawl-delay: 10

# Host directive for better SEO (optional)
Host: https://www.miftechno.com