# 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
# robots.txt for walljm.com
# Search engines - allowed
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
# Archiver - allowed (Internet Archive/Wayback Machine)
User-agent: archive.org_bot
Allow: /
# Default: allow all, block non-content paths
User-agent: *
Allow: /
Disallow: /search.json
Disallow: /feed.xml
Disallow: /css/
Disallow: /js/
# AI Crawlers - blocked (training data collection)
User-agent: GPTBot
Disallow: /
User-agent: CCBot
Disallow: /
User-agent: Google-Extended
Disallow: /
User-agent: Google-CloudVertexBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-SearchBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Bytespider
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: Meta-ExternalAgent
Disallow: /
User-agent: FacebookBot
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: Cohere-ai
Disallow: /
User-agent: Omgilibot
Disallow: /
User-agent: Timpibot
Disallow: /
User-agent: ProRataInc
Disallow: /
User-agent: Novellum
Disallow: /
User-agent: Anchor
Disallow: /
# AI Search - blocked (answer engines that replace traffic)
User-agent: Applebot
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: PerplexityBot
Disallow: /
User-agent: YouBot
Disallow: /
# AI Assistants - blocked (real-time fetching)
User-agent: ChatGPT-User
Disallow: /
User-agent: Meta-ExternalFetcher
Disallow: /
User-agent: MistralAI-User
Disallow: /
User-agent: DuckAssistBot
Disallow: /
User-agent: Perplexity-User
Disallow: /
# Sitemap location
Sitemap: https://walljm.com/sitemap.xml