# 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.
# use:      how AI systems may consume the content (immediate, reference, or full).

# 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,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# AI Agents
User-agent: Perplexity-User
Disallow: /

User-agent: FireCrawl
Disallow: /

User-agent: FirecrawlAgent
Disallow: /

User-agent: Claude-User
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: Google-Agent
Disallow: /

User-agent: Google-GeminiNotebook
User-agent: Google-NotebookLM
Disallow: /

User-agent: MistralAI-User
Disallow: /

User-agent: Kimi-User
Disallow: /

User-agent: Amzn-User
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

User-agent: Retool
Disallow: /

User-agent: Instapaper
Disallow: /

User-agent: ChathiveCrawler
Disallow: /

# END Cloudflare Managed Content

# Sitemap location
Sitemap: https://www.giriblog.com/sitemap_index.xml

# Twitterbot settings
User-agent: Twitterbot
Disallow: *
Allow: /wp-content/uploads/*

# General user-agent settings
User-agent: *

# Disallow unnecessary or duplicate pages
Disallow: /cgi-bin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/  # Disallow all of wp-content except uploads
Disallow: /go/
Disallow: /archives/
Disallow: /author
Disallow: /comments/feed/

# Allow necessary assets for all user agents
Allow: /wp-content/uploads/
Allow: /wp-content/themes/
Allow: /wp-content/plugins/
Allow: /wp-includes/js/
Allow: /wp-includes/css/

# Googlebot settings
User-agent: Googlebot
Allow: *.js
Allow: *.css

# Mediapartners-Google (AdSense bots)
User-agent: Mediapartners-Google
Disallow:
Allow: /*

# Googlebot-Image (Image crawling settings)
User-agent: Googlebot-Image
Allow: /wp-content/uploads/

# Adsbot-Google (Google Ads Bot)
User-agent: Adsbot-Google
Allow: /

# Googlebot-Mobile (Mobile bot settings)
User-agent: Googlebot-Mobile
Allow: /

# Allow Google AI to use content for Discover/Gemini
User-agent: Google-Extended
Allow: /

# Block other AI crawlers from using content to train models
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: anthropic-ai
Disallow: /