# HG changeset patch # User Henry S. Thompson # Date 1584374243 0 # Node ID c858a4d4bd4fa9e8770a6c65a0a08ce368be32f5 # Parent 6662a353379a150ee2afe5a917cfea47e2d51e2c copied from valhalla/bin diff -r 6662a353379a -r c858a4d4bd4f bin/extract.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bin/extract.sh Mon Mar 16 15:57:23 2020 +0000 @@ -0,0 +1,11 @@ +#!/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