view workers/bin/count1.sh @ 65:e1f61f94b196

switch to curl->file, enable retries
author Henry S. Thompson <ht@markup.co.uk>
date Thu, 04 Jun 2020 12:08:29 +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"