# 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: /

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

# Content Signals (contentsignals.org)
Content-Signal: ai-train=no, search=yes, ai-input=yes

# Default Rules
User-Agent: *
Allow: /
Allow: /api/og
Allow: /api/citations/feed
Allow: /api/webmention
Allow: /api/health
Allow: /search?q=*
Disallow: /dashboard/
Disallow: /api/
Disallow: /login/
Disallow: /search$
Disallow: /*?*sort=*
Disallow: /*?*ref=*
Disallow: /*?*utm_*
Disallow: /*?*preview=*
Disallow: /*?*source=*

# Social Sharing & Rich Pin Crawlers (Explicitly Allowed)
User-Agent: Pinterestbot
Allow: /
Allow: /api/og
Allow: /rss.xml
Allow: /feed.xml
Allow: /rss/pinterest
Allow: /feed/pinterest

User-Agent: Twitterbot
Allow: /
Allow: /api/og

User-Agent: facebookexternalhit
Allow: /
Allow: /api/og

User-Agent: LinkedInBot
Allow: /
Allow: /api/og

# Google AdSense & Search Crawlers (Explicitly Allowed)
User-Agent: Mediapartners-Google
Allow: /

User-Agent: Googlebot
Allow: /
Allow: /api/og

User-Agent: Googlebot-Image
Allow: /
Allow: /api/og

# Good AI/LLM Search Crawlers (Allowed for Citations & Discovery)
User-Agent: GPTBot
Allow: /

User-Agent: OAI-SearchBot
Allow: /

User-Agent: PerplexityBot
Allow: /

User-Agent: ClaudeBot
Allow: /

User-Agent: Google-Extended
Allow: /

User-Agent: anthropic-ai
Allow: /

User-Agent: Applebot
Allow: /

# Scraper Farms & Unlicensed LLM-Training Crawlers (Blocked)
User-Agent: CCBot
Disallow: /

User-Agent: FacebookBot
Disallow: /

User-Agent: Meta-ExternalAgent
Disallow: /

User-Agent: Bytespider
Disallow: /

User-Agent: Amazonbot
Disallow: /

User-Agent: Applebot-Extended
Disallow: /

User-Agent: cohere-ai
Disallow: /

User-Agent: DotBot
Disallow: /

User-Agent: PetalBot
Disallow: /

User-Agent: DeepSeekBot
Disallow: /

User-Agent: AI2Bot
Disallow: /

User-Agent: ChatGLM-Spider
Disallow: /

User-Agent: TikTokSpider
Disallow: /

User-Agent: Scrapy
Disallow: /

# Sitemaps
Sitemap: https://gworky.com/sitemap.xml
Sitemap: https://gworky.com/news-sitemap.xml