Parser/MPP/CSV_to_RDF/CSV_to_RDF_OA_BIB_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:')
schemaCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')
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:')
rdfsCoords = RDFcoords('<http://www.w3.org/2000/01/rdf-schema#>', 'rdfs:')
nsCoords = RDFcoords('<http://www.w3.org/1999/02/22-rdf-syntax-ns#>', 'rdf:')
schemaCoords = RDFcoords('<http://www.schema.org/>', 'schema:')
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 ' + rdfsCoords.prefix + ' ' + rdfsCoords.uri + closeLine)
    
    output.write('\n')


filePrefix = 'OA_BIB_'
fileType = 'IMG'
max_entries = 1000000000

with open(import_dir + filePrefix + fileType + '.csv', newline="") as csv_file, open(
        export_dir + filePrefix + fileType + '.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)
        

        # placeHolders
        pp = row['NCT']
        if row['BIBN-SO-1']!= '':
            e73placeHolderEDPP = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + pp + ">"
            id = row['BIBN-SO-1'].replace(".jpg", "")
            e36placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + ">"
            e36e42placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + '_E36_E42>'
            line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', e73placeHolderEDPP) + 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', '\"Scheda Opera\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder, cidocCoords.prefix + 'P2_has_type', '\"Scheda Opera\"') + 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['BIBN-SO-1']+ '\"') + closeLine
            output.write(line)
        if row['BIBN-SO-2']!= '':
            e73placeHolderEDPP = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + pp + ">"
            id = row['BIBN-SO-2'].replace(".jpg", "")
            e36placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + ">"
            e36e42placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + '_E36_E42>'
            line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', e73placeHolderEDPP) + 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', '\"Scheda Opera\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder, cidocCoords.prefix + 'P2_has_type', '\"Scheda Opera\"') + 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['BIBN-SO-2']+ '\"') + closeLine
            output.write(line)
        if row['BIBN-SO-3']!= '':
            e73placeHolderEDPP = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + pp + ">"
            id = row['BIBN-SO-3'].replace(".jpg", "")
            e36placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + ">"
            e36e42placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + '_E36_E42>'
            line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', e73placeHolderEDPP) + 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', '\"Scheda Opera\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder, cidocCoords.prefix + 'P2_has_type', '\"Scheda Opera\"') + 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['BIBN-SO-3']+ '\"') + closeLine
            output.write(line)
        if row['FNTI-SS']!= '':
            e73placeHolder = "<"+ row['ID OPERA'].replace(" ","")+ "_E73>" 
            id = row['FNTI-SS'].replace(".pdf", "")
            e36placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + ">"
            e36e42placeHolder = "<https://palazzopretorio.prato.it/it/bib/" + row['BIBH'] + "/E73" + "_ED_" + id + "_E36_E42>"
            line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', e73placeHolder) + 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', '\"Scheda Storica\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder, cidocCoords.prefix + 'P2_has_type', '\"Scheda Storica\"') + 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['FNTI-SS'].replace("pdf","jpg")+ '\"') + closeLine
            output.write(line)

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