# 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: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# -----------------------------------------
# SoftCon Robots.txt - SEO Optimized
# https://soft-con.co
# -----------------------------------------

User-agent: *
Allow: /

# Disallowed Sensitive Areas
Disallow: /admin/
Disallow: /private/
Disallow: /api/internal/
Disallow: /.env
Disallow: /node_modules/
Disallow: /src/
Disallow: /*.log$
Disallow: /*.zip$
Disallow: /*.env$
Disallow: /*?*preview=true

# Allowed Public Pages
Allow: /services/
Allow: /about
Allow: /portfolio
Allow: /contact
Allow: /careers

# Crawl Rate Control
Crawl-delay: 5

# Sitemap Location
Sitemap: https://soft-con.co/sitemap.xml

# Specific Bot Instructions
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Disallow: /

# Block Bad Bots (optional)
User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /