Created
June 18, 2015 21:26
-
-
Save samjsharpe/f264d00a8a95d399d2ca to your computer and use it in GitHub Desktop.
Clean up government domain list
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
curl -s https://www.gov.uk/government/uploads/system/uploads/attachment_data/file/362257/List_of_gov_uk_domain_names_as_at_1_October_2014.csv | \ | |
cut -d, -f1 | \ | |
while read line; do | |
whois -h whois.ja.net $line > tempfile; | |
OWNER=`egrep -A1 "(Domain Owner|Registered For)" tempfile | awk 'NR==2 {for (i=1; i<=NF; i++) printf("%s%s", $(i), i<NF ? OFS : "\n");}'`; | |
POSTCODE=`/opt/boxen/homebrew/opt/gnu-sed/libexec/gnubin/sed -rn 's/.*(([A-Z]{1,2}[0-9]{1,2}|[A-Z]{1,2}[0-9][A-Z]) [0-9][A-Z]{2}).*/\1/p' tempfile` ; | |
grep -q "No such domain" tempfile || print $line,$OWNER,$POSTCODE; | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment