# HAL robots.txt
# If you want to download lots of metadata, please use our API at https://api.archives-ouvertes.fr/
# The API is far more efficient for metadata harvesting
# To learn more, please contact hal-support@ccsd.cnrs.fr

User-Agent: *
Disallow: /RePEc/
Disallow: /search/
Disallow: /*/search/
Disallow: /*/browse/last
Disallow: /browse/last
Disallow: /*/browse/latest-publications
Disallow: /browse/latest-publications
Disallow: */tei
Disallow: */rdf
Disallow: */bibtex
Disallow: */dc
Disallow: */datacite
Disallow: */openaire
Disallow: */dcterms
Disallow: */endnote
Disallow: */json
Disallow: /ping
Disallow: /login
Disallow: /submit
Disallow: /user
Disallow: /*/user/*
Disallow: /error
Disallow: */preview/*
Disallow: /view/resolver/*

User-agent: SemanticScholarBot
Crawl-delay: 5

User-agent: TurnitinBot
Crawl-delay: 5

User-agent: MegaIndex.ru
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: SemrushBot-SA
Disallow: /

User-agent: Seekport Crawler
Disallow: /

User-agent: ltx71 - (http://ltx71.com/)
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: Riddler
Disallow: /

# Sitemap
Sitemap: http://inria.hal.science/robots/sitemap