diff bin/getidx.aws @ 155:56825fc8459d

moved from /beegfs/common-crawl to get under .hg
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Wed, 11 Oct 2023 12:51:06 +0100
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bin/getidx.aws	Wed Oct 11 12:51:06 2023 +0100
@@ -0,0 +1,35 @@
+# courtesy wwaites
+ARCHIVE="$1"
+shift
+if [ "$1" ]
+then
+ wait="; sleep $1"
+fi
+
+cf=cc-index.paths
+
+CCs=https://data.commoncrawl.org/crawl-data/${ARCHIVE}/cc-index.paths.gz
+
+mkdir -p /beegfs/common_crawl/${ARCHIVE}
+cd /beegfs/common_crawl/${ARCHIVE}
+
+if [ ! -f $cf ]
+then
+ curl --retry 4 -s ${CCs} | gzip -dc > $cf
+fi
+
+# n=$(cat $SEGS | wc -l)
+# m=$((n / 8))
+# split -n l/$m $SEGS segment_
+
+# Export some ENV variables so you don't have to type anything
+export AWS_ACCESS_KEY_ID="AKIAIKBLNO2XNVMWM5JA"
+export AWS_SECRET_ACCESS_KEY="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"
+export PASSPHRASE="annebooththompson"
+
+mkdir -p cdx/warc
+cd cdx/warc
+cat ../../$cf|\
+ parallel --will-cite -j 5 \
+  "f='{}' && aws s3 cp s3://commoncrawl/\$f \${f##*/}  --only-show-errors 2> >( { echo \$(date +%D:%T) '{}' ; cat ; } >>ierrlog) $wait"
+