User-agent: *

Disallow: /*.pdf$
Disallow: /*.xlsx$

Disallow: /api/
Disallow: /admin/
Disallow: /operator/
Disallow: /profile/
Disallow: /investor-cabinet/
Disallow: /founder-cabinet/
Disallow: /documents/
Disallow: /outside-document-sign/
Disallow: /confirm/email
Disallow: /auth/realms/

Allow: /api/files/

Request-rate: 1/3               # maximum rate is one page every 3 second
Crawl-delay: 3                  # 3 seconds between page requests
# Visit-time: 0400-0845           # only visit between 04:00 and 08:45 UTC

# Allow search crawlers to discover the sitemap
Host: https://crowdfin.ru/
Sitemap: https://crowdfin.ru/sitemap.xml

# Block CazoodleBot as it does not present correct accept content headers
User-agent: CazoodleBot
Disallow: /

# Block MJ12bot as it is just noise
User-agent: MJ12bot
Disallow: /

# Block dotbot as it cannot parse base urls properly
User-agent: dotbot/1.0
Disallow: /

# Block Gigabot
User-agent: Gigabot
Disallow: /