#!/bin/bash
me=$$
SHARED=/home/shared/ht
cd $SHARED/data/$(hostname)
mkdir -p logs
while read id
do
    echo starting ${id} $(date) >> logs/${me}_log
    unpigz -dp 1 -c /data/common_crawl/CC-MAIN-2019-35/CC-MAIN-${id}.warc.gz|$SHARED/bin/warc.sh ${id} application/pdf 2>> logs/${me}_log
    echo finished ${id} $(date) >> logs/${me}_log
done
