Parser/MPP/CSV_to_RDF/CSV_to_RDF_cataloghi.py

# Utilities to read/write csv files
import csv
# Utilities to handle character encodings
import unicodedata
# Ordered Dicts
from collections import OrderedDict

from urllib.request import urlopen
from bs4 import BeautifulSoup

import json

# 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/'
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('<http://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/>', 'mpp:')
autCoords = RDFcoords('<http://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:')
foafCoords = RDFcoords('<http://xmlns.com/foaf/0.1/>', 'foaf:')
owlCoords = RDFcoords('<http://www.w3.org/2002/07/owl#>', 'owl:')


# 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 ' + nsCoords.prefix + ' ' + nsCoords.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 ' + owlCoords.prefix + ' ' + owlCoords.uri + closeLine)
    output.write('@prefix ' + foafCoords.prefix + ' ' + foafCoords.uri + closeLine)

    output.write('\n')


filePrefix = 'OA'
fileType = '_catalogo'
max_entries = 1000000000

def get_aut_url(code):
    aut_file = open(import_dir + 'AR20AUT_' + fileType + '.csv', newline="")
    reader = csv.DictReader(aut_file)
    for row in reader:
        auth = int(row['AUTH'])
        cod = int(code)
        role = ''
        if row['AUTQ'] != '':
            role = row['AUTQ']
        else:
            role = ''
        if auth == cod:
            return [row['URL'], role]

def get_role(role):
    role_file = open('/Users/federicaspinelli/Google Drive/OVI-CNR/CSV/MPP/AAT_RUOLI.csv', newline="")
    reader = csv.DictReader(role_file)
    for row in reader:
        if row['Label'] == role:
            return row['AAT']

def get_elem(mtc):
    mtc_file = open('/Users/federicaspinelli/Google Drive/OVI-CNR/CSV/MPP/AAT_MTC.csv', newline="")
    reader = csv.DictReader(mtc_file)
    for row in reader:
        if row['MTC'] == mtc:
            return [row['AAT'], row['Type']]

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
    e55invplaceHolder = "<https://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/INV1979>"
    line = triple(e55invplaceHolder, schemaCoords.prefix + 'label', '\"Inventario 1970\"') + closeLine
    output.write(line)
    e55AplaceHolder = "<https://palazzopretorio.prato.it/it/le-opere/alcuni-capolavori/ARCHIVE>"
    line = triple(e55AplaceHolder, schemaCoords.prefix + 'label', '\"Riferimento bibliografico\"') + closeLine
    output.write(line)
    for row in reader:
        # The index ii is used to process a limited number of entries for testing purposes
        ii = ii + 1

        # placeHolders
        urlplaceHolder = '<' + row['Url OPERA'] + '>'
        e36placeHolder = '<' + row['Url OPERA'] + '_E36>'
        e36e42placeHolder = '<' + row['Url OPERA'] + '_E36_E42>'
        e36placeHolder2 = '<' + row['Url OPERA'] + '_E36_2>'
        e36e42placeHolder2 = '<' + row['Url OPERA'] + '_E36_2_E42>'
        e36placeHolder3 = '<' + row['Url OPERA'] + '_E36_3>'
        e36e42placeHolder3 = '<' + row['Url OPERA'] + '_E36_3_E42>'
        e31placeHolder = '<' + row['Url OPERA'] + '_E31>'
        e3142placeHolder = '<' + row['Url OPERA'] + '_E31_E42>'
        e31e36rplaceHolder = '<' + row['Url OPERA'] + '_E31_E36_r>'
        e31e36re42placeHolder = '<' + row['Url OPERA'] + '_E31_E36_r_E42>'
        e31e36vplaceHolder = '<' + row['Url OPERA'] + '_E31_E36_v>'
        e31e36ve42placeHolder = '<' + row['Url OPERA'] + '_E31_E36_v_E42>'
        e31AplaceHolder = '<' + row['LINK ARCHIVE.org'] + '>'
        e31Ae42placeHolder = '<' + row['LINK ARCHIVE.org'] + '_E42>'
        e13placeHolder = '<' + row['Url OPERA'] + '_E13_FA>'
        e31Ae55placeHolder = '<' + row['AAT (Attribution)'] + '_E31_E55>'
        e12placeHolder = '<' + row['Url OPERA'] + '_E12>'
        e12FplaceHolder = '<' + row['Url OPERA'] + '_E12F>'
        
        line = triple(e36placeHolder, cidocCoords.prefix + 'P138_represents', urlplaceHolder) + closeLine
        output.write(line)
        line = triple(e36placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
        output.write(line)
        line = triple(e36placeHolder, schemaCoords.prefix + 'label', '\"Immagine digitale dell\'Opera ' + '\'' + row['NOME 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, schemaCoords.prefix + 'label', '\"'+row['ID Immagine opera 1']+ '\"') + closeLine
        output.write(line)
        
        if (row['ID Immagine opera 2']!= ''):
            line = triple(e36placeHolder2, cidocCoords.prefix + 'P138_represents', urlplaceHolder) + closeLine
            output.write(line)
            line = triple(e36placeHolder2, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
            output.write(line)
            line = triple(e36placeHolder2, schemaCoords.prefix + 'label', '\"Immagine digitale dell\'Opera ' + '\'' + row['NOME OPERA'] + '\''+'\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder2, cidocCoords.prefix + 'P1_is_identified_by', e36e42placeHolder2) + closeLine
            output.write(line)
            line = triple(e36e42placeHolder2, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e36e42placeHolder2, schemaCoords.prefix + 'label', '\"'+row['ID Immagine opera 2']+ '\"') + closeLine
            output.write(line)

        if (row['ID Immagine opera 3']!= ''):
            line = triple(e36placeHolder3, cidocCoords.prefix + 'P138_represents', urlplaceHolder) + closeLine
            output.write(line)
            line = triple(e36placeHolder3, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
            output.write(line)
            line = triple(e36placeHolder3, schemaCoords.prefix + 'label', '\"Immagine digitale dell\'Opera ' + '\'' + row['NOME OPERA'] + '\''+'\"') + closeLine
            output.write(line)
            line = triple(e36placeHolder3, cidocCoords.prefix + 'P1_is_identified_by', e36e42placeHolder3) + closeLine
            output.write(line)
            line = triple(e36e42placeHolder3, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e36e42placeHolder3, schemaCoords.prefix + 'label', '\"'+row['ID Immagine opera 3']+ '\"') + closeLine
            output.write(line)
        
        if (row['ID Inventario 1970']!= ''):
            line = triple(e31placeHolder, cidocCoords.prefix + 'P70_documents', urlplaceHolder) + closeLine
            output.write(line)
            line = triple(e31placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E31_Document') + closeLine
            output.write(line)
            line = triple(e31placeHolder, schemaCoords.prefix + 'label', '\"Inventario 1970\"') + closeLine
            output.write(line)
            line = triple(e31placeHolder, cidocCoords.prefix + 'P2_has_type', e55invplaceHolder) + closeLine
            output.write(line)
            line = triple(e31placeHolder, cidocCoords.prefix + 'P1_is_identified_by', e3142placeHolder) + closeLine
            output.write(line)
            line = triple(e3142placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e3142placeHolder, schemaCoords.prefix + 'label', '\"'+row['ID Inventario 1970']+ '\"') + closeLine
            output.write(line)

        if (row['ID Immagine Inventario 1970 recto']!= ''):
            line = triple(e31e36rplaceHolder, cidocCoords.prefix + 'P138_represents', e31placeHolder) + closeLine
            output.write(line)
            line = triple(e31e36rplaceHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
            output.write(line)
            line = triple(e31e36rplaceHolder, schemaCoords.prefix + 'label', '\"Rappresentazione digitale della scheda opera d\'arte su ' + "\'Inventario 1970\' - recto" + '\"' ) + closeLine
            output.write(line)
            line = triple(e31e36rplaceHolder, cidocCoords.prefix + 'P1_is_identified_by', e31e36re42placeHolder) + closeLine
            output.write(line)
            line = triple(e31e36re42placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e31e36re42placeHolder, schemaCoords.prefix + 'label', '\"'+row['ID Immagine Inventario 1970 recto']+ '\"') + closeLine
            output.write(line)

        if (row['ID Immagine Inventario 1970 verso']!= ''):
            line = triple(e31e36vplaceHolder, cidocCoords.prefix + 'P138_represents', e31placeHolder) + closeLine
            output.write(line)
            line = triple(e31e36vplaceHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E36_Visual_Item') + closeLine
            output.write(line)
            line = triple(e31e36vplaceHolder, schemaCoords.prefix + 'label', '\"Rappresentazione digitale della scheda opera d\'arte su ' + "\'Inventario 1970\' - verso" + '\"' ) + closeLine
            output.write(line)
            line = triple(e31e36vplaceHolder, cidocCoords.prefix + 'P1_is_identified_by', e31e36ve42placeHolder) + closeLine
            output.write(line)
            line = triple(e31e36ve42placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e31e36ve42placeHolder, schemaCoords.prefix + 'label', '\"'+row['ID Immagine Inventario 1970 verso']+ '\"') + closeLine
            output.write(line)
        
        if (row['LINK ARCHIVE.org']!= ''):
            line = triple(e31AplaceHolder, cidocCoords.prefix + 'P70_documents', urlplaceHolder) + closeLine
            output.write(line)
            line = triple(e31AplaceHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E31_Document') + closeLine
            output.write(line)
            line = triple(e31AplaceHolder, schemaCoords.prefix + 'label', '\"Riferimento bibliografico della scheda opera d\'arte su ARCHIVE.org\"') + closeLine
            output.write(line)
            line = triple(e31AplaceHolder, cidocCoords.prefix + 'P2_has_type', e55AplaceHolder) + closeLine
            output.write(line)
            line = triple(e31AplaceHolder, cidocCoords.prefix + 'P1_is_identified_by', e31Ae42placeHolder) + closeLine
            output.write(line)
            line = triple(e31Ae42placeHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E42_Identifier') + closeLine
            output.write(line)
            line = triple(e31Ae42placeHolder, schemaCoords.prefix + 'label', '\"'+row['BIBH']+ '\"') + closeLine
            output.write(line)

        if (row['FORMER ATTRIBUTION']!= '' and row['FORMER ATTRIBUTION']!= ' ' and row['FORMER ATTRIBUTION'] is not None):
            line = triple(e12placeHolder, cidocCoords.prefix + 'P141_assigned', e13placeHolder) + closeLine
            output.write(line)
            line = triple(e12FplaceHolder, cidocCoords.prefix + 'P141_assigned', e13placeHolder) + closeLine
            output.write(line)
            if (row['LINK ARCHIVE.org']!= ''):
                line = triple(e13placeHolder, cidocCoords.prefix + 'P42_assigned', e31AplaceHolder) + closeLine
                output.write(line)
            line = triple(e13placeHolder, cidocCoords.prefix + 'P2_has_type', e31Ae55placeHolder) + closeLine
            output.write(line)
            line = triple(e31Ae55placeHolder, schemaCoords.prefix + 'label', '\"AAT Attribution\"') + closeLine
            output.write(line)
            line = triple(e13placeHolder, schemaCoords.prefix + 'label', '\"Former Attribution dell\'Opera ' + '\'' + row['NOME OPERA'] + '\''+'\"') + closeLine
            output.write(line)
            e21ULANplaceHolder = '<'+row['ULAN']+'>'
            if (row['LINK SCHEDA AUT']!= ''):
                e21AUTplaceHolder = '<'+row['LINK SCHEDA AUT']+'>'
                line = triple(e13placeHolder, cidocCoords.prefix + 'P141_assigned', e21AUTplaceHolder) + closeLine
                output.write(line)
                if (row['ULAN']!= ''):
                    line = triple(e21AUTplaceHolder, owlCoords.prefix + 'sameAs', e21ULANplaceHolder) + closeLine
                    output.write(line)
                if (row['VIAF']!= ''):
                    e21VIAFplaceHolder = '<'+row['VIAF']+'>'
                    line = triple(e21AUTplaceHolder, owlCoords.prefix + 'sameAs', e21VIAFplaceHolder) + closeLine
                    output.write(line)
            else:
                line = triple(e13placeHolder, cidocCoords.prefix + 'P141_assigned', e21ULANplaceHolder) + closeLine
                output.write(line)
                line = triple(e21ULANplaceHolder, schemaCoords.prefix + 'label', '\"' + row['FORMER ATTRIBUTION']+ '\"') + closeLine
                output.write(line)
                line = triple(e21ULANplaceHolder, nsCoords.prefix + 'type', cidocCoords.prefix + 'E21_Person') + closeLine
                output.write(line)
                line = triple(e21ULANplaceHolder, nsCoords.prefix + 'type', foafCoords.prefix + 'person') + closeLine
                output.write(line)
                if (row['VIAF']!= ''):
                    e21VIAFplaceHolder = '<'+row['VIAF']+'>'
                    line = triple(e21ULANplaceHolder, owlCoords.prefix + 'sameAs', e21VIAFplaceHolder) + closeLine
                    output.write(line)
            
        output.write('\n')
        #
        #
        # Limit number of entries processed (if desired)
        if (ii > max_entries):
            break