morphit/apps/web/static/robots.txt

178 lines
3.9 KiB
Text

# Morphit — robots policy
#
# Per ADR-0003: permissive. Public marketplace; public FAQ; public docs.
# Morphit's content is AGPL-3 and anyone is welcome to quote, archive,
# or index it.
#
# The only paths we ask crawlers to skip are the recovery flow and the
# per-user settings page — both produce no value as indexed results and
# the recovery form's UI copy could look like phishing bait if a user
# lands on it from a SERP.
#
# cp119-A3: locale-prefixed forms (/{lang}/onboarding/import,
# /{lang}/settings) are the real URLs; the bare /onboarding/import
# and /settings forms 404. Both patterns listed (`/path` and `/*path`)
# for defense-in-depth. Major crawlers (Googlebot, Bingbot,
# DuckDuckBot) honor `*` wildcard in robots.txt paths per the
# de-facto extended robots.txt grammar.
User-agent: *
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
# Explicit allowlist for major search and retrieval bots. The
# wildcard above already grants access; these named entries make
# the opt-in unambiguous for crawlers that prefer (or require)
# specifically-named directives.
User-agent: Googlebot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Bingbot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: DuckDuckBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Slurp
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: YandexBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Baiduspider
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Applebot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Twitterbot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: facebookexternalhit
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: LinkedInBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: GPTBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: ChatGPT-User
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: OAI-SearchBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: ClaudeBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Claude-Web
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: PerplexityBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Perplexity-User
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Google-Extended
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: Bytespider
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: CCBot
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
User-agent: ia_archiver
Allow: /
Disallow: /onboarding/import
Disallow: /*/onboarding/import
Disallow: /settings
Disallow: /*/settings
Sitemap: https://morphit.io/sitemap.xml