archives.gov

mx

us.etp.fireeyegov.com

ns

ns2.fedmettel.net

ns1.fedmettel.net

caa

letsencrypt.org

awstrust.com

entrust.net

txt

google-site-verification=vzFoKGZ49s-tl4Mw26kJfVRiYukV0lHmZlbG0iAYYMk

v=spf1 -all

dmarc

v=DMARC1;p=reject;pct=100;fo=1;ri=86400;adkim=r;aspf=r;rua=mailto:reports@dmarc.cyber.dhs.gov;ruf=mailto:reports@dmarc.cyber.dhs.gov;

#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html

User-agent: *
Crawl-delay: 10

Sitemap: https://www.archives.gov/sitemap.xml
Sitemap: https://www.archives.gov/files/sitemap.xml
Sitemap: https://www.archives.gov/research/native-americans/bia/photos/sitemap.xml
Sitemap: https://www.archives.gov/files/sitemap-other.xml

Disallow: /citizen-archivist/history-hub/hh-test
Disallow: /developer/artificial-intelligence-and-machine-learning-datasets
Disallow: /developer/1940-census
Disallow: /developer/national-archives-catalog-dataset

User-agent: usasearch
Crawl-delay: 2