BasicWorkset.json

{ "@graph": [
    { "@id": "http://htrc.hathitrust.org/wsid/1616876109a",
      "@type" : [ "http://wcsa.htrc.illinois.edu/Workset" ] ,
      "http://purl.org/dc/terms/created" : [ { "@value" : "2013-05-01" } ] ,
      "http://purl.org/dc/terms/extent" : [ 5 ] ,
      "http://www.europeana.eu/schemas/edm/gathers" : [ { "@id": "http://hdl.handle.net/2027/wu.89054391917"} ,
        { "@id": "http://hdl.handle.net/2027/njp.32101067492643"} ,
        { "@id": "http://hdl.handle.net/2027/hvd.hnr43u"} ,
        { "@id": "http://hdl.handle.net/2027/osu.32435014276414"} ,
        { "@id": "http://hdl.handle.net/2027/wu.89107614968"} ] ,
      "http://purl.org/dc/terms/creator" : [ { "@value" : "Jesse S Cohn" } ] ,
      "http://wcsa.htrc.illinois.edu/intendedForUse" : [ { "@id": "http://example.org/htrc.algorithm"} ] ,
      "http://purl.org/dc/terms/title" : [ { "@value" : "Anarchist literary and cultural criticism" } ] ,
      "http://purl.org/dc/terms/language" : [ { "@value" : "French" } ,
        { "@value" : "Czech" } ] ,
      "http://purl.org/dc/terms/temporal" : [ { "@value" : "19th Century" } ] }
] }

geturls.py

import json
import sys

WORKSET_BASE_URL = 'http://htrc.hathitrust.org/wsid/'
# TODO: Replace with argument parsing
WORKSET_ID = '1616876109'

# open the JSON file or retrieve the URL
with open("BasicWorkset.json") as jsonfile:
    data = json.load(jsonfile)['@graph']

ALL_IDS = []
# Parse each graph
for graph in data:
    gathers = graph.get("http://www.europeana.eu/schemas/edm/gathers", [])
    ids = [entry['@id'].replace('http://hdl.handle.net/2027/', '')
                for entry in gathers]

    if ids:
        ALL_IDS.extend(ids)

for id in ALL_IDS:
    print id