# 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

User-agent: *
Allow: /

# High-priority pages for SEO crawling
Allow: /blog/
Allow: /posts/
Allow: /about/
Allow: /categories/
Allow: /tags/
Allow: /archives/

# Important static content
Allow: /assets/css/
Allow: /assets/js/
Allow: /assets/img/
Allow: /favicon.ico

# Sitemaps - Critical for indexing
Sitemap: https://buggymaytricks.page/sitemap.xml
Sitemap: https://buggymaytricks.page/feed.xml

# Crawl optimization
Crawl-delay: 1

# Block unnecessary paths to focus crawler budget
Disallow: /tools/
Disallow: /_site/
Disallow: /node_modules/
Disallow: /.git/
Disallow: /vendor/
Disallow: /Gemfile*
Disallow: /*.config.js
Disallow: /package*.json

# Block bot traps and private content
Disallow: /trap/
Disallow: /honeypot/
Disallow: /private/
Disallow: /admin/

# Specify host for clarity
Host: https://buggymaytricks.page