# Hello friends!
# If you are considering large or automated crawling, you may want to look at
# our catalog API (https://api.fatcat.wiki) or bulk database snapshots instead.

# large-scale bots should not index search pages
User-agent: SemrushBot
User-agent: YandexBot
User-agent: bingbot
User-agent: Googlebot
User-agent: SemanticScholarBot
User-agent: yacybot
User-agent: PetalBot
User-agent: Yeti
User-agent: Riddler
Disallow: /search

# crawling search result pages is expensive, so we do specify a long crawl
# delay for those (for bots other than the above broad search bots)
# UPDATE: actually, just block all robots from search page, we are overwhelmed
# as of 2022-10-31
User-agent: *
Disallow: /search
#Allow: /search
#Crawl-delay: 5

# by default, can crawl anything on this domain. HTTP 429 ("backoff") status
# codes are used for rate-limiting instead of any crawl delay specified here.
# Up to a handful concurrent requests should be fine.
User-Agent: *
Allow: /

Sitemap: https://scholar.archive.org/sitemap.xml
Sitemap: https://scholar.archive.org/sitemap-index-works.xml

# same info as sitemap-index-works.xml plus following citation_pdf_url
#Sitemap: https://scholar.archive.org/sitemap-index-access.xml