| var csv = require("fast-csv"), | |
| fs = require("fs"), | |
| readable = require('stream').Readable, | |
| jsonStream = require('JSONStream'), | |
| viaf = require("viaf-wrapper"); | |
| var stream = fs.createReadStream("perscorp-collection.csv"); | |
| var line = 0 |
| import csv | |
| #ask the CSV file to be opened | |
| csv_file = csv.reader(open("Art Donahue data set - Sheet1.csv"), delimiter=",") | |
| #skip the header | |
| next(csv_file, None) | |
| #loop over each line and read each field | |
| for a_row in csv_file: |
| import csv | |
| from rdflib import Graph, URIRef, Literal | |
| #ask the CSV file to be opened | |
| csv_file = csv.reader(open("Art Donahue data set - Sheet1.csv"), delimiter=",") | |
| #skip the header | |
| next(csv_file, None) |
| import xml.etree.ElementTree as ET | |
| from xml.dom.minidom import parseString | |
| pretty_print = lambda data: '\n'.join([line for line in parseString(data).toprettyxml(indent=' '*2).split('\n') if line.strip()]) | |
| def remove_namespace(doc, namespace): | |
| """Remove namespace in the passed document in place.""" | |
| ns = u'{%s}' % namespace | |
| nsl = len(ns) | |
| for elem in doc.getiterator(): |
| { | |
| "author": "Klopstock, Friedrich Gottlieb, 1724-1803.", | |
| "bibLevel": { | |
| "code": "m", | |
| "value": "MONOGRAPH" | |
| }, | |
| "catalogDate": "2000-12-13", | |
| "country": { | |
| "code": "gw ", | |
| "name": "Germany" |
| [ | |
| { | |
| "_id": 10067442, | |
| "id": 10067442, | |
| "updatedDate": "2014-08-13T18:36:09Z", | |
| "createdDate": "2009-02-03T01:48:48Z", | |
| "deleted": false, | |
| "bibIds": [ | |
| 10291849 | |
| ], |
| { | |
| "_id": "569f4bfb9923be304b6d3045", | |
| "classify:holdings": [ | |
| { | |
| "objectLiteral": 1404, | |
| "objectLiteralType": "xsd:integer", | |
| "objectUri": null, | |
| "provo": { | |
| "created": "2016-01-20T08:57:23.668Z", | |
| "creator": "RI", |
| { | |
| "@context": { | |
| "agents": "http://data.nypl.org/agents/", | |
| "bf": "http://bibframe.org/vocab/", | |
| "classify": "http://purl.org/library/", | |
| "data": "http://data.nypl.org/datasets/", | |
| "db": "https://NEEDTOFIX.org/what-is-db/", | |
| "dbo": "http://www.dbpedia.org/ontology/", | |
| "dbr": "http://www.dbpedia.org/resource/", | |
| "dcterms": "http://purl.org/dc/terms/", |
| { | |
| "@context": "http://data.nypl.org/context_all.jsonld", | |
| "@type": "itemList", | |
| "itemListElement": [ | |
| { | |
| "@type": "searchResult", | |
| "result": { | |
| "@type": [ | |
| "edm:Agent", | |
| "foaf:Person" |
To run the script:
It will create a file in the same directory converted with the same filename and "_converted.xml" appended.