comparison bin/extract.sh @ 19:c858a4d4bd4f

copied from valhalla/bin
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Mon, 16 Mar 2020 15:57:23 +0000
parents
children a82c325e8b32
comparison
equal deleted inserted replaced
18:6662a353379a 19:c858a4d4bd4f
1 #!/bin/bash
2 me=$$
3 SHARED=/home/shared/ht
4 cd $SHARED/data/$(hostname)
5 mkdir -p logs
6 while read id
7 do
8 echo starting ${id} $(date) >> logs/${me}_log
9 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
10 echo finished ${id} $(date) >> logs/${me}_log
11 done