Parser/MPP/CSV_to_RDF/CSV_to_RDF_OA_IMG.py

    # Utilities to read/write csv files
import csv
    # Utilities to handle character encodings
import unicodedata
    # Ordered Dicts
from collections import OrderedDict
from http.cookiejar import CookieJar
from urllib.request import urlopen
    #from bs4 import BeautifulSoup
import urllib
import json
from socket import error as SocketError
import html.parser

# OPZIONAL IMPORTS
# For timestamping/simple speed tests
from datetime import datetime
# Random number generator
from random import *
# System & command line utilities
import sys
# Json for the dictionary
import json

import_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/CSV/corretti/'
export_dir = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/RDF/'


    # Custom class to store URIs + related infos for the ontologies/repositories

class RDFcoords:
    def __init__(self, uri, prefix, code=None):
            self.uri = uri
            self.prefix = prefix
            self.code = code


    # Repositories
museoCoords = RDFcoords('<https://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/>', 'mpp:')
autCoords = RDFcoords('<https://palazzopretorio.prato.it/it/opere/autori/>', 'aut:')
cidocCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/>', 'crm:')
aatCoords = RDFcoords('<http://vocab.getty.edu/aat/>', 'aat:')
nsCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#>', 'rdf:')
xsdCoords = RDFcoords('<http://www.w3.org/2001/XMLSchema#>', 'xsd:')
iconCoords = RDFcoords('<http://iconclass.org/>', 'ico:')
documentsCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/P70_documents>', 'ds:')
schemaCoords = RDFcoords('<http://www.schema.org/>', 'schema:')
rdfCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdf:')
hasNoteCoords = RDFcoords('<http://www.cidoc-crm.org/cidoc-crm/P3_has_note>', 'no:')
rdfsCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')

    # Basic functions for triples / shortened triples in TTL format

def triple(subject, predicate, object1):
        line = subject + ' ' + predicate + ' ' + object1
        return line


def doublet(predicate, object1):
        line = '    ' + predicate + ' ' + object1
        return line


def singlet(object1):
        line = '        ' + object1
        return line


    # Line endings in TTL format
continueLine1 = ' ;\n'
continueLine2 = ' ,\n'
closeLine = ' .\n'


def writeTTLHeader(output):
    output.write('@prefix ' + museoCoords.prefix + ' ' + museoCoords.uri + closeLine)
    output.write('@prefix ' + cidocCoords.prefix + ' ' + cidocCoords.uri + closeLine)
    output.write('@prefix ' + aatCoords.prefix + ' ' + aatCoords.uri + closeLine)
    output.write('@prefix ' + schemaCoords.prefix + ' ' + schemaCoords.uri + closeLine)
    output.write('@prefix ' + autCoords.prefix + ' ' + autCoords.uri + closeLine)
    output.write('@prefix ' + xsdCoords.prefix + ' ' + xsdCoords.uri + closeLine)
    output.write('@prefix ' + iconCoords.prefix + ' ' + iconCoords.uri + closeLine)
    output.write('@prefix ' + documentsCoords.prefix + ' ' + documentsCoords.uri + closeLine)
    output.write('@prefix ' + nsCoords.prefix + ' ' + nsCoords.uri + closeLine)
    output.write('@prefix ' + hasNoteCoords.prefix + ' ' + hasNoteCoords.uri + closeLine)
    output.write('@prefix ' + rdfsCoords.prefix + ' ' + rdfsCoords.uri + closeLine)

    output.write('\n')


filePrefix = 'AR20IMR'
fileType = '_Ospedale'
max_entries = 1000000000

with open(import_dir + filePrefix + fileType + '.csv', newline="") as csv_file, open(
        export_dir + filePrefix + fileType + '_LICENZA.ttl', 'w') as output:
        reader = csv.DictReader(csv_file)
        writeTTLHeader(output)
        first = True
        ii = 0
        for row in reader:
            # The index ii is used to process a limited number of entries for testing purposes
            ii = ii + 1
            # columnName = list(row)
            
            url = row['URL']
            # placeHolders
            
            # if row['FTA0']!= '': 
            #     datplaceHolder = museoCoords.prefix + url
            id = row['FTA0'].replace(".jpeg","")
            e36placeHolder = museoCoords.prefix + url + "_" + id
            #     e36e42placeHolder = museoCoords.prefix + url + "_"  + id + "_E36_E42"
            #     line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', datplaceHolder) + closeLine
            #     output.write(line)
            #     line = triple(e36placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
            #     output.write(line)
            #     line = triple(e36placeHolder, rdfsCoords.prefix + 'label', '\"Tavola\"') + closeLine
            #     output.write(line)
                
            #     line = triple(e36placeHolder, cidocCoords.prefix + 'P2_has_type', '\"Tavola\"') + closeLine
            #     output.write(line)
            #     line = triple(e36placeHolder, cidocCoords.prefix + 'P1_is_identified_by', e36e42placeHolder) + closeLine
            #     output.write(line)
            #     line = triple(e36e42placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            #     output.write(line)
            #     line = triple(e36e42placeHolder, rdfsCoords.prefix + 'label', '\"'+row['FTA0']+ '\"') + closeLine
            #     output.write(line)
            #     if row['NOTE']!= '':
            #         line = triple(e36placeHolder, hasNoteCoords.prefix, '\"'+ row['NOTE']+'"') + closeLine
            #         output.write(line)

            e62placeHolder = museoCoords.prefix + url + "_" + id + "_E36_E62"
            e62e42placeHolder = museoCoords.prefix + url + "_" + id + "_E62_E42"
            e36e30placeHolder = "<https://creativecommons.org/licenses/by-nc-sa/4.0/deed.it>"
            e36e30e42placeHolder = "<https://mirrors.creativecommons.org/presskit/buttons/88x31/png/by-nc-sa.png>"

            line = triple(e36placeHolder, cidocCoords.prefix + 'P3_has_note',
                        e62placeHolder) + closeLine
            output.write(line)
            line = triple(e62placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E62_String') + closeLine
            output.write(line)
            line = triple(e62placeHolder, rdfsCoords.prefix + 'label',
                        '\"Museo di Palazzo Pretorio di Prato\"') + closeLine
            output.write(line)
            line = triple(e62placeHolder, cidocCoords.prefix + 'P2_has_type',
                        '\"Provenienza immagine\"') + closeLine
            output.write(line)
            line = triple(e62placeHolder, cidocCoords.prefix + 'P1_is_identified_by',
                        "<https://palazzopretorio.prato.it/>") + closeLine
            output.write(line)
            line = triple(e62e42placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e36placeHolder, cidocCoords.prefix + 'P104_is_subject_to',
                        e36e30placeHolder) + closeLine
            output.write(line)
            line = triple(e36e30placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E30_Right') + closeLine
            output.write(line)
            line = triple(e36e30placeHolder, rdfsCoords.prefix + 'label',
                        '\"CC BY NC SA\"') + closeLine
            output.write(line)
            line = triple(e36e30placeHolder, cidocCoords.prefix + 'P1_is_identified_by',
                       e36e30e42placeHolder) + closeLine
            output.write(line)
            line = triple(e36e30e42placeHolder, nsCoords.prefix + 'type',
                        cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e36e30e42placeHolder, rdfsCoords.prefix + 'label',
                        '\"CC BY NC SA\"') + closeLine
            output.write(line)

            output.write('\n')
            #
            #
            # Limit number of entries processed (if desired)
            if (ii > max_entries):
                break