# WuJie Search (wujiesearch.com)
#
# NOTE: the old domain s.wu-jie.com still resolves, but every request is
# 301-redirected to this new domain (see ws_domain_redirect in inc/config.php).
# We intentionally keep it crawlable: a crawler blocked by robots.txt never
# sees that 301 and won't learn the site moved.
#
# NOTE: we deliberately do NOT write "Disallow: /*?q=" even though the biggest
# crawl waste is there. Result pages already emit
# <meta name="robots" content="noindex,follow"> (only when q is present), which
# marks them noindex. Google's rule: a URL blocked by robots.txt can't be read,
# so its noindex is never seen -> contradictory signals and a useless noindex.
# So we pick one: meta (more accurate, works for every meta-respecting engine)
# handles result pages; robots.txt only blocks paths with no noindex value
# (saving bandwidth).

User-agent: *
Allow: /

# APIs and admin: crawling them only yields 401/400
Disallow: /api/
Disallow: /admin.php

# Login / auth: /login/ 302s to the main site; no point following
Disallow: /login/
Disallow: /logout/
Disallow: /sso/

# Runtime data dir (the .php suffix is deliberate; double protection here)
Disallow: /data.php/

Sitemap: https://wujiesearch.com/sitemap.xml