# robots.txt for rev.com — corrected by CrawlCheck, 2026-11-03
# Source: the file the site served at the time. Every change is listed here; nothing else was touched.
# Changes:
#   - Read from https://www.rev.com/robots.txt (the apex redirected there); publish at the host you serve.
#   - 2 named groups lacked Disallow lines the * group carries. A crawler obeys only its own most specific group and ignores *, so those rules never applied to it. Copied in.
# Verify after publishing: curl -sI https://rev.com/robots.txt must show text/plain, on the bare URL, with no cache-buster.

Sitemap: https://www.rev.com/sitemap.xml

User-agent: *
Disallow: /captions-editor/
Noindex: /captions-editor/
Disallow: /tc-editor/
Noindex: /tc-editor/
Disallow: /transcript-editor/
Noindex: /transcript-editor/
Disallow: /blog/wp-content/plugins/
Disallow: /blog/wp-admin/

User-agent: Mediapartners-Google
Disallow:
Disallow: /captions-editor/
Disallow: /tc-editor/
Disallow: /transcript-editor/
Disallow: /blog/wp-content/plugins/
Disallow: /blog/wp-admin/

# Termly cookie scanner
User-agent: TermlyBot
Allow: /
Disallow: /captions-editor/
Disallow: /tc-editor/
Disallow: /transcript-editor/
Disallow: /blog/wp-content/plugins/
Disallow: /blog/wp-admin/