# 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 WIPP - Cloudflare Pages
# Last updated: 2026-02-04

# DEFAULT RULES FOR ALL CRAWLERS
User-agent: *

# ALLOW: Public Pages Only
Allow: /
Allow: /about
Allow: /contact
Allow: /feedback
Allow: /explore
Allow: /c/
Allow: /post/$
Allow: /project/
Allow: /profile/
Allow: /communities

# DISALLOW: Private/Protected Pages
Disallow: /login
Disallow: /signup
Disallow: /settings
Disallow: /inbox
Disallow: /admin
Disallow: /admin/
Disallow: /api/
Disallow: /auth
Disallow: /auth/
Disallow: /oauth
Disallow: /oauth-

# DISALLOW: Utility/Debug Pages
Disallow: /debug-
Disallow: /test-
Disallow: /coming-soon

# DISALLOW: Password/Email Reset (Sensitive)
Disallow: /forgot-password
Disallow: /device-password-reset
Disallow: /reset-password-confirm
Disallow: /confirm-email

# DISALLOW: Query Parameters for Internal Routes
Disallow: /?error=
Disallow: /?message=
Disallow: /?welcome=
Disallow: /?utm_
Disallow: /?ref=
Disallow: /?redirect=

# ALLOW: Sitemap
Allow: /sitemap.xml

# CRAWL SETTINGS
# Removed Crawl-delay — Googlebot ignores it; for other bots, it can unnecessarily slow crawling
# Use Google Search Console to control crawl rate if needed

# GOOGLE-SPECIFIC RULES
User-agent: Googlebot
Allow: /
Allow: /about
Allow: /contact
Allow: /feedback
Allow: /explore
Allow: /c/
Allow: /post/$
Allow: /project/
Allow: /profile/
Allow: /communities
Disallow: /login
Disallow: /signup
Disallow: /settings
Disallow: /inbox
Disallow: /admin
Disallow: /api/
Disallow: /auth
Disallow: /oauth
Disallow: /debug-
Disallow: /test-
Disallow: /?utm_
# Removed per-bot Crawl-delay

# SITEMAP DECLARATIONS
Sitemap: https://wipp.site/sitemap.xml