summaryrefslogtreecommitdiff
path: root/ia-upload-gs.sh
blob: 1d5b397b323bf2784f090245ff2c7bf8f7f32003 (plain)
1
2
3
4
5
6
7
8
9
10
11
#!/bin/sh

title="$(echo $1 | sed 's/\(-[0-9][0-9][0-9][0-9]-[0-9]\+-[0-9]\+.*\)//g')"
date="$(echo $1 | sed -n 's/.*\([0-9][0-9][0-9][0-9]-[0-9]\+-[0-9]\+\).*/\1/p')"
id=$title-$date
start_url="$(cat $1/start_url)"

ia upload $id $1/*.gz $1/*.cdx --metadata="mediatype:web" \
--metadata="date:$date" --metadata="title:$title" \
--metadata="description:recursive crawl of $start_url using grab-site/wpull, \
taken on $date" --metadata="source:$title"