Mercurial > hg > cc > valhalla

diff bin/extract.sh @ 0:fdd3f8a16fd4 default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
shared scripts on valhalla cluster
author Henry Thompson <ht@markup.co.uk>
date Sat, 14 Mar 2020 11:00:58 +0000
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bin/extract.sh	Sat Mar 14 11:00:58 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