Last active
August 5, 2020 09:04
-
-
Save carwash/ecc888f2a273715d21119a6c70710b76 to your computer and use it in GitHub Desktop.
Minimal OAI-PMH harvester, for testing in bash. Uses curl, tee, and xmlstarlet for resumption token support. Usage: `$ oai-pmh-test.sh example.com`
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#/usr/bin/env bash | |
fetch_token() { | |
file=$1 ; count=$2 | |
tee >(xmlstarlet fo - > "$file-$(printf "%04d" $count).xml") | xmlstarlet sel -N oai="http://www.openarchives.org/OAI/2.0/" --template --match "/oai:OAI-PMH/oai:ListRecords/oai:resumptionToken" --value-of "." | |
} | |
server=$1 | |
file=$(echo $server | sed -E 's/^https?:\/\///; s/[\.:\/]/-/g') | |
count=1 | |
token=$(curl -s -g "$server?verb=ListRecords" -H 'Accept: application/xml' | fetch_token $file $count) | |
#token=$(curl -s -g "$server?verb=ListRecords" | fetch_token $file $count) | |
while [ $token ] ; do | |
((count++)) | |
token=$(curl -s -g "$server?verb=ListRecords&resumptionToken=$token" -H 'Accept: application/xml' | fetch_token $file $count) | |
# token=$(curl -s -g "$server?verb=ListRecords&resumptionToken=$token" | fetch_token $file $count) | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment