User-agent: *
# Apply the repository's crawl exclusions at the domain root. Crawlers do not
# consult /dspace/robots.txt for URLs under /dspace/.
Disallow: /dspace/search
Disallow: /dspace/admin
Disallow: /dspace/processes
Disallow: /dspace/submit
Disallow: /dspace/workspaceitems
Disallow: /dspace/profile
Disallow: /dspace/workflowitems
Disallow: /dspace/entities/*?f

# The main website and the repository maintain separate sitemap inventories.
Sitemap: https://clarin-pl.eu/sitemap.xml
Sitemap: https://clarin-pl.eu/dspace/sitemap_index.xml