# www is the canonical host — the apex 302s here, and every rel=canonical the
# app emits uses www. These must agree or they undercut the canonicals.
Host: https://www.weekday.works
Sitemap: https://www.weekday.works/sitemap.xml

# Default: allow all well-behaved bots
User-agent: *
Allow: /
# Private candidate-share and search-result pages — not for indexing
Disallow: /drops/
Disallow: /searches/
# Internal admin tooling: live, crawlable and title-less, deliberately NOT
# Disallowed here yet — see next.config.js for the X-Robots-Tag on this path.
# A Disallow would stop Google from ever re-fetching it, which stops it from
# ever reading the noindex header, which freezes any already-indexed URL here
# as "Indexed, though blocked by robots.txt" instead of actually dropping it.
# Add the Disallow back once Search Console confirms these URLs are out of
# the index — crawl-budget hardening at that point, not before.
Crawl-delay: 1

# Block known scraper / SEO-data / content-harvesting bots
User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: SeznamBot
Disallow: /

User-agent: serpstatbot
Disallow: /

User-agent: MegaIndex.ru
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: Barkrowler
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: SiteAuditBot
Disallow: /

User-agent: SplitSignalBot
Disallow: /