view workers/bin/count1.sh @ 34:ad6eff2bc6f9

fixes to logging and efficiency, see also notes.txt wrt patches to dateparser
author Henry S. Thompson <ht@markup.co.uk>
date Wed, 21 Nov 2018 18:42:56 +0000
parents 36b5d379909a
children
line wrap: on
line source

#!/bin/bash
echo "# $(date) > $ID.$1"
jq '.Envelope|.["WARC-Header-Metadata"]["WARC-Target-URI"]'|cut -f 1 -d ':'|awk '{c[$1]+=1} END {for (k in c) {print k, c[k]}}'
echo "# $(date) < $ID.$1"