select * from "ccindex"."ccindex" limit 100;

#                            2
url_surtkey                  org,whwheelers)/robots.txt
url                          https://whwheelers.org/robots.txt
url_host_name                whwheelers.org
url_host_tld                 org
url_host_2nd_last_part       whwheelers
url_host_3rd_last_part
url_host_4th_last_part
url_host_5th_last_part
url_host_registry_suffix     org
url_host_registered_domain   whwheelers.org
url_host_private_suffix      org
url_host_private_domain      whwheelers.org
url_host_name_reversed
url_protocol                 https
url_port
url_path                     /robots.txt
url_query
fetch_time                   2021-06-22 16:36:50.000
fetch_status                 301
fetch_redirect               https://www.whwheelers.org/robots.txt
content_digest               3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ
content_mime_type            text/html
content_mime_detected        text/html
content_charset
content_languages
content_truncated
warc_filename                crawl-data/CC-MAIN-2021-25/segments/1623488519183.85/robotstxt/CC-MAIN-20210622155328-20210622185328-00312.warc.gz
warc_record_offset           1854030
warc_record_length           639
warc_segment                 1623488519183.85
crawl                        CC-MAIN-2021-25
subset                       robotstxt

select * from "ccindex"."ccindex" where url_host_registered_domain = 'conquermstoday.com' limit 100;

select * from "ccindex"."ccindex" where
  fetch_time < TIMESTAMP '2014-01-01 00:00:00' AND
  url_host_registered_domain IN (
   'activegaminginfo.com',
   'altworldnews.com',
   ...
   'topbillingsite.com',
   'worldwildlifeadventure.com'
 )

select * from "ccindex"."ccindex" WHERE
  crawl = 'CC-MAIN-2013-20' AND
  subset = 'warc' AND
  url_host_registered_domain IN (
   'google.com',
   'amazon.com'
 )

select * from "ccindex"."ccindex" WHERE
  crawl IN (
    'CC-MAIN-2013-20',
    'CC-MAIN-2013-48',
    'CC-MAIN-2014-10'
  ) AND
  subset = 'warc' AND
  url_host_registered_domain IN (
    'activegaminginfo.com',
    'altworldnews.com',
    ...
    'worldnewsandent.com',
    'worldwildlifeadventure.com'
 )

jq -r '.[].host' ../media/cia-2010-covert-communication-websites/hits.json ) | xargs -I{} sqlite3 aiddcu.sqlite "select * from t where d = '{}'"