diff bin/extract.sh @ 25:a82c325e8b32

(none)
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Wed, 18 Mar 2020 11:08:47 +0000
parents c858a4d4bd4f
children 7a2bc060230d
line wrap: on
line diff
--- a/bin/extract.sh	Wed Mar 18 11:08:23 2020 +0000
+++ b/bin/extract.sh	Wed Mar 18 11:08:47 2020 +0000
@@ -1,11 +1,13 @@
 #!/bin/bash
-me=$$
-SHARED=/home/shared/ht
-cd $SHARED/data/$(hostname)
+# Usage extract.sh ccid segid
+ccid=$1
+segid=$2
+@@me=$$
+@@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
+    unpigz -dp 1 -c /beegfs/common-crawl/CC-MAIN-${ccid}/${segid}/CC-MAIN-${id}.warc.gz|$HOME/lib/valhalla/bin/warc.sh ${id} application/pdf 2>> logs/@@${me}_log
+    echo finished ${id} $(date) >> logs/@@${me}_log
 done