EAD_to_CSV_datini_titolimancanti.ipynb 82 KB
Inizio radunando tutti gli **IMPORT** necessari per girare il notebook, per chiarezza.
# IMPORT ESSENZIALI
# Per il parsing dell'XML -- questo pacchetto è incluso anche nel più generale lxml
import xml.etree.ElementTree as ET
# Utilities per leggere/scrivere files csv
import csv
# Utilities per gestire i character encodings
import unicodedata
# Dizionari ordinati
from collections import OrderedDict
# IMPORT OPZIONALI
# Per fare un stima della velocità delle varie istruzioni
from datetime import datetime
# Generatore di numeri casuali -- può sempre servire in fase di testing
from random import *
# Può servire per alcuni test
import sys# FUNZIONI
**ElementTree** ha una funzione built-in, **iter**, che scorre (molto velocemente) su tutti i 'nodi' dell'albero di dati che rappresenta l'XML. La funzione *iter* purtroppo però non traccia i nodi 'parents'.
Ho esteso quindi la libreria scrivendo una mia versione di *iter*, **'traceElems'**, che dovrebbe riuscire a fornirci tutto quello di cui abbiamo bisogno.
*traceElems* traccia tutti i nodi nell'albero tenendo conto dei 'parents', e restituisce tutti quelli per cui la funzione-argomento 'condition' ritorna True. **NON** indaga i nodi **figli** di quelli che sono restituiti.
# La funzione BASE: traceElems
def traceElems(node: ET.Element, condition, parents: list = [], coords: list = []):
res = []
jj = 0
for child in node:
if condition(child):
res.append({'a_par': parents+[node],
'coords': coords+[jj], 'child': child})
else:
res = res + traceElems(child, condition, parents+[node], coords+[jj])
jj = jj+1
return res
# Funzione-base per stoppare traceElems
def isLeafOrC(aa: ET.Element):
if(aa.tag=='c' or len(aa)==0):
return True
else:
return False# Funzioni-utilità che servono solo a visualizzare meglio i dati sul notebook.
def shownode(node: ET.Element):
return (node.tag, node.attrib, node.text.replace('\t','').replace('n','').strip() \
if type(node.text) is str else '')
def shownodelist(el: ET.Element):
return list(map(shownode, el))
# Utility copiata da INTERNEZZ -- versione 'multipla' del metodo str.index:
def indices(lst, element):
result = []
offset = -1
while True:
try:
offset = lst.index(element, offset+1)
except ValueError:
return result
result.append(offset)# AL LAVORO
**DA CAMBIARE A SECONDA DEL COMPUTER**: directory di input e output
import_dir = '/Users/federicaspinelli/Google Drive/OVI:CNR/LAVORO 2020/SELEZIONE CONTENUTI/01_ASPO/XDAMS/'
export_dir = '/Users/federicaspinelli/Google Drive/OVI:CNR/CSV/ASPO/datini/'Importo il file XML del Datini, tracciando il tempo necessario
ts1 = datetime.timestamp(datetime.now())
treeDatini = ET.parse(import_dir + 'export_aspoSt001--datini.xml')
rootDatini = treeDatini.getroot()
ts2 = datetime.timestamp(datetime.now())
print(ts2 - ts1)165.66787719726562
Uso *iter* per trovare tutti i nodi con label **'c'** nel file Datini, e mi faccio restituire il
valore dell'attributo **'level'**; salvo tutti i *levels* nella variabile **cLevs**
cLevs = set(map(lambda a : a.attrib['level'], rootDatini.iter('c')))
print(cLevs){'subseries', 'series', 'item', 'collection', 'file', 'otherlevel', 'subfonds', 'fonds'}
A questo punto metto al lavoro la funzione **traceElems**: registro TUTTI i nodi **'c'** dividendoli in base all'attributo **'level'**; mi faccio stampare il numero di elementi per ogni livello ed il tempo trascorso.
**OCCHIO:** per come è costruita, questa routine non va ad investigare dentro i livelli restituiti -- quindi si perde eventuali sotto-livelli con la stessa label di quelli che trova durante il primo scan. La presenza di sotto-livelli di questo tipo va controllata separatamente.
ts1 = datetime.timestamp(datetime.now())
allCs = {}
for label in cLevs:
def tempFilt(aa: ET.Element):
if(aa.tag=='c' and aa.attrib['level']==label):
return True
else:
return False
allCs[label] = traceElems(rootDatini, tempFilt);
print('# di tag "c", livello ' + label + ', primo passaggio:', len(allCs[label]))
print()
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)# di tag "c", livello subseries, primo passaggio: 1365 # di tag "c", livello series, primo passaggio: 35 # di tag "c", livello item, primo passaggio: 149085 # di tag "c", livello collection, primo passaggio: 1 # di tag "c", livello file, primo passaggio: 15449 # di tag "c", livello otherlevel, primo passaggio: 10 # di tag "c", livello subfonds, primo passaggio: 14 # di tag "c", livello fonds, primo passaggio: 1 Tempo trascorso: 12.193603038787842
Notare che l'elaborazione è piuttosto veloce (sul mio laptop) malgrado la dimensione del file.
Rimane il problema dei livelli dentro a livelli omonimi. Vediamo di affrontarlo.
ts1 = datetime.timestamp(datetime.now())
allCs2 = {}
for label in cLevs:
partial = allCs[label]
print('# di tag "c", livello ' + label + ', primo passaggio:', len(partial))
allCs2[label] = partial
partialUpdate = []
while True:
def tempFilt(aa: ET.Element):
if(aa.tag=='c' and aa.attrib['level']==label):
return True
else:
return False
for node in partial:
partialUpdate = partialUpdate + traceElems(node['child'], tempFilt)
#print(len(partialUpdate))
partial = partialUpdate
if(len(partialUpdate)==0):
break
allCs2[label] = allCs2[label] + partial
partialUpdate = []
print('# di tag "c", livello ' + label + ', totali:', len(allCs2[label]))
print()
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)# di tag "c", livello subseries, primo passaggio: 1365 # di tag "c", livello subseries, totali: 1477 # di tag "c", livello series, primo passaggio: 35 # di tag "c", livello series, totali: 61 # di tag "c", livello item, primo passaggio: 149085 # di tag "c", livello item, totali: 149085 # di tag "c", livello collection, primo passaggio: 1 # di tag "c", livello collection, totali: 4 # di tag "c", livello file, primo passaggio: 15449 # di tag "c", livello file, totali: 15449 # di tag "c", livello otherlevel, primo passaggio: 10 # di tag "c", livello otherlevel, totali: 10 # di tag "c", livello subfonds, primo passaggio: 14 # di tag "c", livello subfonds, totali: 14 # di tag "c", livello fonds, primo passaggio: 1 # di tag "c", livello fonds, totali: 1 Tempo trascorso: 28.464100122451782
A questo punto diventa facile visualizzare tutti i dettagli dei vari elementi **'c'**, di qualunque livello; un esempio è fornito nella prossima cella. Si può cambiare l'elemento da visualizzare cambiando il valore delle variabili *ii* e *level*
ii = 1
level = 'otherlevel'
test = allCs2[level][ii]
toProc = traceElems(test['child'], isLeafOrC)
# Commentare/scommentare per stampare qui / su file
# (vedi anche in fondo alla cella)
#provaFileName = 'out.txt'
#orig_stdout = sys.stdout
#fp = open(export_dir + provaFileName, 'w')
#sys.stdout = fp
# fino qui + in fondo
print()
print()
print('Level:', level)
print('#:', ii)
print()
for node in toProc:
print(shownodelist(node['a_par']))
print(node['coords'])
print(shownode(node['child']))
print('# of children:', len(node['child']))
print()
# Commentare/scommentare per stampare qui / su file
#sys.stdout = orig_stdout
#fp.close()
Level: otherlevel
#: 1
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('did', {}, '')]
[0, 0]
('unittitle', {'encodinganalog': 'ISAD 1 - 2 title'}, 'Busta 1167')
# of children: 0
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('processinfo', {}, ''), ('list', {}, ''), ('item', {}, '')]
[1, 0, 0, 0]
('date', {}, '19/03/2013')
# of children: 0
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('processinfo', {}, ''), ('list', {}, ''), ('item', {}, '')]
[1, 0, 0, 1]
('persname', {}, 'Admi xDams - ope source')
# of children: 0
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 0]
('c', {'audience': 'internal', 'id': 'ASPO00164307', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 1]
('c', {'audience': 'internal', 'id': 'ASPO00164308', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 2]
('c', {'audience': 'internal', 'id': 'ASPO00164309', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 3]
('c', {'audience': 'internal', 'id': 'ASPO00164310', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 4]
('c', {'audience': 'internal', 'id': 'ASPO00164311', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 5]
('c', {'audience': 'internal', 'id': 'ASPO00164312', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 6]
('c', {'audience': 'internal', 'id': 'ASPO00164313', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 7]
('c', {'audience': 'internal', 'id': 'ASPO00164314', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 8]
('c', {'audience': 'internal', 'id': 'ASPO00164315', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 9]
('c', {'audience': 'internal', 'id': 'ASPO00164316', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 10]
('c', {'audience': 'internal', 'id': 'ASPO00164317', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 11]
('c', {'audience': 'internal', 'id': 'ASPO00164318', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 12]
('c', {'audience': 'internal', 'id': 'ASPO00164319', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 13]
('c', {'audience': 'internal', 'id': 'ASPO00164320', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 14]
('c', {'audience': 'internal', 'id': 'ASPO00164321', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 15]
('c', {'audience': 'internal', 'id': 'ASPO00164322', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 16]
('c', {'audience': 'internal', 'id': 'ASPO00164323', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 17]
('c', {'audience': 'internal', 'id': 'ASPO00164324', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 18]
('c', {'audience': 'internal', 'id': 'ASPO00164325', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 19]
('c', {'audience': 'internal', 'id': 'ASPO00164326', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 20]
('c', {'audience': 'internal', 'id': 'ASPO00164327', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 21]
('c', {'audience': 'internal', 'id': 'ASPO00164328', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 22]
('c', {'audience': 'internal', 'id': 'ASPO00164329', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 23]
('c', {'audience': 'internal', 'id': 'ASPO00164330', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 24]
('c', {'audience': 'internal', 'id': 'ASPO00164331', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 25]
('c', {'audience': 'internal', 'id': 'ASPO00164332', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 26]
('c', {'audience': 'internal', 'id': 'ASPO00164333', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 27]
('c', {'audience': 'internal', 'id': 'ASPO00164334', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 28]
('c', {'audience': 'internal', 'id': 'ASPO00164335', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 29]
('c', {'audience': 'internal', 'id': 'ASPO00164336', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 30]
('c', {'audience': 'internal', 'id': 'ASPO00164337', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 31]
('c', {'audience': 'internal', 'id': 'ASPO00164338', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 32]
('c', {'audience': 'internal', 'id': 'ASPO00164339', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 33]
('c', {'audience': 'internal', 'id': 'ASPO00164340', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 34]
('c', {'audience': 'internal', 'id': 'ASPO00164341', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 35]
('c', {'audience': 'internal', 'id': 'ASPO00164342', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 36]
('c', {'audience': 'internal', 'id': 'ASPO00164343', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 37]
('c', {'audience': 'internal', 'id': 'ASPO00164344', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 38]
('c', {'audience': 'internal', 'id': 'ASPO00164345', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 39]
('c', {'audience': 'internal', 'id': 'ASPO00164346', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 40]
('c', {'audience': 'internal', 'id': 'ASPO00164347', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 41]
('c', {'audience': 'internal', 'id': 'ASPO00164348', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 42]
('c', {'audience': 'internal', 'id': 'ASPO00164349', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 43]
('c', {'audience': 'internal', 'id': 'ASPO00164350', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 44]
('c', {'audience': 'internal', 'id': 'ASPO00164351', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 45]
('c', {'audience': 'internal', 'id': 'ASPO00164352', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 46]
('c', {'audience': 'internal', 'id': 'ASPO00164353', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 47]
('c', {'audience': 'internal', 'id': 'ASPO00164354', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 48]
('c', {'audience': 'internal', 'id': 'ASPO00164355', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 49]
('c', {'audience': 'internal', 'id': 'ASPO00164356', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 50]
('c', {'audience': 'internal', 'id': 'ASPO00164357', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 51]
('c', {'audience': 'internal', 'id': 'ASPO00164358', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 52]
('c', {'audience': 'internal', 'id': 'ASPO00164359', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 53]
('c', {'audience': 'internal', 'id': 'ASPO00164360', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 54]
('c', {'audience': 'internal', 'id': 'ASPO00164361', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 55]
('c', {'audience': 'internal', 'id': 'ASPO00164362', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 56]
('c', {'audience': 'internal', 'id': 'ASPO00164363', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 57]
('c', {'audience': 'internal', 'id': 'ASPO00164364', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 58]
('c', {'audience': 'internal', 'id': 'ASPO00164365', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 59]
('c', {'audience': 'internal', 'id': 'ASPO00164366', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 60]
('c', {'audience': 'internal', 'id': 'ASPO00164367', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 61]
('c', {'audience': 'internal', 'id': 'ASPO00164368', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 62]
('c', {'audience': 'internal', 'id': 'ASPO00164369', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 63]
('c', {'audience': 'internal', 'id': 'ASPO00164370', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 64]
('c', {'audience': 'internal', 'id': 'ASPO00164371', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 65]
('c', {'audience': 'internal', 'id': 'ASPO00164372', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 66]
('c', {'audience': 'internal', 'id': 'ASPO00164373', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 67]
('c', {'audience': 'internal', 'id': 'ASPO00164374', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 68]
('c', {'audience': 'internal', 'id': 'ASPO00164375', 'level': 'item'}, '')
# of children: 3
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 69]
('c', {'audience': 'internal', 'id': 'ASPO00164376', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 70]
('c', {'audience': 'internal', 'id': 'ASPO00164377', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 71]
('c', {'audience': 'internal', 'id': 'ASPO00164378', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 72]
('c', {'audience': 'internal', 'id': 'ASPO00164379', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 73]
('c', {'audience': 'internal', 'id': 'ASPO00164380', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 74]
('c', {'audience': 'internal', 'id': 'ASPO00164381', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 75]
('c', {'audience': 'internal', 'id': 'ASPO00164382', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 76]
('c', {'audience': 'internal', 'id': 'ASPO00164383', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 77]
('c', {'audience': 'internal', 'id': 'ASPO00164384', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 78]
('c', {'audience': 'internal', 'id': 'ASPO00164385', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 79]
('c', {'audience': 'internal', 'id': 'ASPO00164386', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 80]
('c', {'audience': 'internal', 'id': 'ASPO00164387', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 81]
('c', {'audience': 'internal', 'id': 'ASPO00164388', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 82]
('c', {'audience': 'internal', 'id': 'ASPO00164389', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 83]
('c', {'audience': 'internal', 'id': 'ASPO00164390', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 84]
('c', {'audience': 'internal', 'id': 'ASPO00164391', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 85]
('c', {'audience': 'internal', 'id': 'ASPO00164392', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 86]
('c', {'audience': 'internal', 'id': 'ASPO00164393', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 87]
('c', {'audience': 'internal', 'id': 'ASPO00164394', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 88]
('c', {'audience': 'internal', 'id': 'ASPO00164395', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 89]
('c', {'audience': 'internal', 'id': 'ASPO00164396', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 90]
('c', {'audience': 'internal', 'id': 'ASPO00164397', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 91]
('c', {'audience': 'internal', 'id': 'ASPO00164398', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 92]
('c', {'audience': 'internal', 'id': 'ASPO00164399', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 93]
('c', {'audience': 'internal', 'id': 'ASPO00164400', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 94]
('c', {'audience': 'internal', 'id': 'ASPO00164401', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 95]
('c', {'audience': 'internal', 'id': 'ASPO00164402', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 96]
('c', {'audience': 'internal', 'id': 'ASPO00164403', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 97]
('c', {'audience': 'internal', 'id': 'ASPO00164404', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 98]
('c', {'audience': 'internal', 'id': 'ASPO00164405', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 99]
('c', {'audience': 'internal', 'id': 'ASPO00164406', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 100]
('c', {'audience': 'internal', 'id': 'ASPO00164407', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 101]
('c', {'audience': 'internal', 'id': 'ASPO00164408', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 102]
('c', {'audience': 'internal', 'id': 'ASPO00164409', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 103]
('c', {'audience': 'internal', 'id': 'ASPO00164410', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 104]
('c', {'audience': 'internal', 'id': 'ASPO00164411', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 105]
('c', {'audience': 'internal', 'id': 'ASPO00164412', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 106]
('c', {'audience': 'internal', 'id': 'ASPO00164413', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 107]
('c', {'audience': 'internal', 'id': 'ASPO00164414', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 108]
('c', {'audience': 'internal', 'id': 'ASPO00164415', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 109]
('c', {'audience': 'internal', 'id': 'ASPO00164416', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 110]
('c', {'audience': 'internal', 'id': 'ASPO00164417', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 111]
('c', {'audience': 'internal', 'id': 'ASPO00164418', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 112]
('c', {'audience': 'internal', 'id': 'ASPO00164419', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 113]
('c', {'audience': 'internal', 'id': 'ASPO00164420', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 114]
('c', {'audience': 'internal', 'id': 'ASPO00164421', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 115]
('c', {'audience': 'internal', 'id': 'ASPO00164422', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 116]
('c', {'audience': 'internal', 'id': 'ASPO00164423', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 117]
('c', {'audience': 'internal', 'id': 'ASPO00164424', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 118]
('c', {'audience': 'internal', 'id': 'ASPO00164425', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 119]
('c', {'audience': 'internal', 'id': 'ASPO00164426', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 120]
('c', {'audience': 'internal', 'id': 'ASPO00164427', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 121]
('c', {'audience': 'internal', 'id': 'ASPO00164428', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 122]
('c', {'audience': 'internal', 'id': 'ASPO00164429', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 123]
('c', {'audience': 'internal', 'id': 'ASPO00164430', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 124]
('c', {'audience': 'internal', 'id': 'ASPO00164431', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 125]
('c', {'audience': 'internal', 'id': 'ASPO00164432', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 126]
('c', {'audience': 'internal', 'id': 'ASPO00164433', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 127]
('c', {'audience': 'internal', 'id': 'ASPO00164434', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 128]
('c', {'audience': 'internal', 'id': 'ASPO00164435', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 129]
('c', {'audience': 'internal', 'id': 'ASPO00164436', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 130]
('c', {'audience': 'internal', 'id': 'ASPO00164437', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 131]
('c', {'audience': 'internal', 'id': 'ASPO00164438', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 132]
('c', {'audience': 'internal', 'id': 'ASPO00164439', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 133]
('c', {'audience': 'internal', 'id': 'ASPO00164440', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 134]
('c', {'audience': 'internal', 'id': 'ASPO00164441', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 135]
('c', {'audience': 'internal', 'id': 'ASPO00164442', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 136]
('c', {'audience': 'internal', 'id': 'ASPO00164443', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 137]
('c', {'audience': 'internal', 'id': 'ASPO00164444', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 138]
('c', {'audience': 'internal', 'id': 'ASPO00164445', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 139]
('c', {'audience': 'internal', 'id': 'ASPO00164446', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 140]
('c', {'audience': 'internal', 'id': 'ASPO00164447', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 141]
('c', {'audience': 'internal', 'id': 'ASPO00164448', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 142]
('c', {'audience': 'internal', 'id': 'ASPO00164449', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 143]
('c', {'audience': 'internal', 'id': 'ASPO00164450', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 144]
('c', {'audience': 'internal', 'id': 'ASPO00164451', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 145]
('c', {'audience': 'internal', 'id': 'ASPO00164452', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 146]
('c', {'audience': 'internal', 'id': 'ASPO00164453', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 147]
('c', {'audience': 'internal', 'id': 'ASPO00164454', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 148]
('c', {'audience': 'internal', 'id': 'ASPO00164455', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 149]
('c', {'audience': 'internal', 'id': 'ASPO00164456', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 150]
('c', {'audience': 'internal', 'id': 'ASPO00164457', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 151]
('c', {'audience': 'internal', 'id': 'ASPO00164458', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 152]
('c', {'audience': 'internal', 'id': 'ASPO00164459', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 153]
('c', {'audience': 'internal', 'id': 'ASPO00164460', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 154]
('c', {'audience': 'internal', 'id': 'ASPO00164461', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 155]
('c', {'audience': 'internal', 'id': 'ASPO00164462', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 156]
('c', {'audience': 'internal', 'id': 'ASPO00164463', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 157]
('c', {'audience': 'internal', 'id': 'ASPO00164464', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 158]
('c', {'audience': 'internal', 'id': 'ASPO00164465', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 159]
('c', {'audience': 'internal', 'id': 'ASPO00164466', 'level': 'item'}, '')
# of children: 5
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 160]
('c', {'audience': 'internal', 'id': 'ASPO00164467', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 161]
('c', {'audience': 'internal', 'id': 'ASPO00164468', 'level': 'item'}, '')
# of children: 4
[('c', {'audience': 'internal', 'id': 'ASPO00164306', 'level': 'otherlevel', 'otherlevel': 'container'}, ''), ('dsc', {}, '')]
[2, 162]
('c', {'audience': 'internal', 'id': 'ASPO00164469', 'level': 'item'}, '')
# of children: 5
(*NOTA X ME:* **'did' = 'Descriptive IDentification'**)
A questo punto, quello che devo fare è scrivere un **traduttore** -- una funzione che scorra l'output degli elementi esaminati e trasformi le info in modo da poterle esportare in formato csv (o in qualunque altro formato vogliamo).
La mia attuale versione di **traduttore per gli item** è data nella prossima cella; accetta come argomento un nodo (che è supposto essere di tipo item) e restituisce un dict.
def traduttoreItem(elem):
# Variabile che contiene l'output della traduzione:
csvProt = {}
# Processo i nodi-parent di 'elem'
par_tags = list(map(lambda a: a.tag, elem['a_par']))
par_attributes = list(map(lambda a: a.attrib, elem['a_par']))
# e0: Le varie id dei nodi parent
for ii in indices(par_tags, 'c'):
key = 'id_' + par_attributes[ii]['level']
csvProt[key] = par_attributes[ii]['id']
# Processo i nodi-child di 'elem'
toProc = traceElems(elem['child'], isLeafOrC)
first = True
for node in toProc:
tags = list(map(lambda a: a.tag, node['a_par'])) + [node['child'].tag]
attributes = list(map(lambda a: a.attrib, node['a_par'])) + [node['child'].attrib]
content = node['child'].text
# Da controllare solo per il primo nodo
# (informazioni a livello del nodo, uguali per tutti i figli)
if(first):
# e1 ID della item
csvProt['id'] = attributes[tags.index('c')]['id']
# e2 Audience: external o internal
try:
csvProt['audience'] = attributes[tags.index('c')]['audience']
except:
pass
# e3 Otherlevel
try:
csvProt['altro_livello'] = attributes[tags.index('c')]['otherlevel']
except:
pass
first = False
# La 'ciccia': si processa il contenuto vero e proprio
# e4 Repository (qui dovrebbe essere sempre l'Archivio di Prato)
if('repository' in tags):
csvProt['repository'] = content
# e5 Bioghits
if('bioghist' in tags):
csvProt['bioghist'] = content
# e6 Arrangement
elif('arrangement' in tags):
csvProt['arrangement'] = content
# e7 Related Material
elif('relatedmaterial' in tags):
csvProt['relatedmaterial'] = content
# e8 Tipologia
try:
ii = tags.index('materialspec')
if(attributes[ii]['label']=='tipologia'):
csvProt['tipologia'] = content
except:
pass
# e9 Segnature buste e registri Datini
try:
ii = tags.index('container')
type1 = attributes[ii]['type']
if(type1.find('numero un')>=0):
csvProt['segnatura_registri_1'] = content
elif(type1.find('numero sott')>=0):
csvProt['segnatura_registri_2'] = content
elif(type1=='busta'):
csvProt['segnatura_busta'] = content
elif(type1=='inserto'):
csvProt['segnatura_inserto'] = content
except:
pass
# e9 Segnatura codice
try:
ii = tags.index('num')
type1 = attributes[ii]['type']
if(type1=='chiave'):
csvProt['segnatura_codice'] = content
except:
pass
# e9 Segnature subseries
if (attributes[tags.index('c')]['level']=='subseries' or attributes[tags.index('c')]['level']=='file'):
try:
ii = tags.index('unitid')
if(attributes[ii]['type']=='segnatura'):
csvProt['segnatura_parent'] = content
except:
pass
# e10 Titolo
elif('title' in tags):
csvProt['titolo_originale'] = content
# e11 Il titolo da unittitle
#m = re.search('AAA(.+?)ZZZ', text)
#if m:
#found = m.group(1)
try:
aa = csvProt['titolo_aspo']
except:
try:
ii = tags.index('unittitle')
try:
for chi in node['a_par'][ii]:
tails = "" + chi.tail
csvProt['titolo_aspo'] = (node['a_par'][ii].text + tails).replace('\t','').replace('\n','').strip()
except:
pass
except:
pass
# e12 Scope-content head & body
if('scopecontent' in tags):
if('list' not in tags and 'head' in tags):
csvProt['scope-content_head'] = content
else:
if('p' in tags and 'num' not in tags):
csvProt['scope-content_body'] = content
if('num' in tags):
try:
ii = tags.index('num')
if(attributes[ii]['type']):
key = 'num_'+ attributes[ii]['type']
csvProt[key] = content
except:
pass
# e12 lista merci
if('scopecontent' in tags):
if('list' in tags):
try:
ii = tags.index('list')
try:
csvProt['lista'] = csvProt['lista'] + ' | ' + content
except:
csvProt['lista'] = content
except:
pass
# e13 Origine
try:
ii = tags.index('origination')
csvProt['origine'] = attributes[ii]['label'] + ': ' + content
except:
pass
# e14 Nome della compagnia
if ('unittitle' in tags):
if ('corpname' in tags):
try:
ii = tags.index('corpname')
if (attributes[ii]['authfilenumber'] or attributes[ii]['role']=='compagnia'):
try:
authId = attributes[ii]['authfilenumber']
csvProt['compagnia'] = '{nome: ' + content + ', authID: ' + authId + '}'
except:
csvProt['compagnia'] = '{nome: ' + content + '}'
except:
pass
# e15 Soggetto
try:
aa = csvProt['soggetto']
except:
try:
ii = tags.index('subject')
try:
csvProt['soggetto'] = str(node['a_par'][ii].text).replace('\t','').replace('\n','').strip()
except:
csvProt['soggetto'] = str(content).replace('\t','').replace('\n','').strip()
except:
pass
# e15 tipologia soggetto
if('subject' in tags):
if ('emph' in tags):
csvProt['tipologia_soggetto'] = content
# e16 Persona + ruolo
try:
ii = tags.index('persname')
key = 'persona_' + attributes[ii]['role']
try:
authId = attributes[ii]['authfilenumber']
csvProt[key] = '{"nome": ' + "\"" + content + "\"" + ', "authID": ' + "\"" + authId + "\"" + '}'
except:
csvProt[key] = '{"nome": ' + "\"" + content + "\"" + '}'
except:
pass
# e17 Date varie: tutte quelle con 'type' definito + note
if ('unittitle' in tags):
try:
ii = tags.index('date')
key = 'data_' + attributes[ii]['type']
aa = csvProt[key]
except:
try:
ii = tags.index('date')
try:
csvProt[key] = str(node['a_par'][ii].text).replace('\t','').replace('\n','').strip()
try:
ii = tags.index('emph')
csvProt[key+'_note'] = content
except:
pass
except:
csvProt[key] = str(content).replace('\t','').replace('\n','').strip()
except:
pass
# e18 Data 1: periodo + note
if('unitdate' in tags):
csvProt['data_periodo'] = str(content).replace('\t','').replace('\n','').strip()
try:
ii = tags.index('emph')
csvProt['data_periodo_note'] = content
except:
pass
# e19 Luogo + 'ruolo'
try:
ii = tags.index('geogname')
key = 'luogo_' + attributes[ii]['role']
try:
authId = attributes[ii]['authfilenumber']
csvProt[key] = '{luogo: ' + content + ', authID: ' + authId + '}'
except:
csvProt[key] = '{luogo: ' + content + '}'
except:
pass
# e20 Supporto fisico
try:
ii = tags.index('physfacet')
if(attributes[ii]['type']=='supporto'):
csvProt['supporto'] = content
except:
pass
# e21 Physdesc
if (attributes[tags.index('c')]['level']!='subfonds'):
if('physdesc' in tags):
if('extent' not in tags and 'physfacet' not in tags):
csvProt['descrizione_fisica'] = content
if('extent' in tags):
csvProt['numero'] = content
if('genreform' in tags):
csvProt['genere'] = content
# e21 Physdesc per subfonds
if (attributes[tags.index('c')]['level']=='subfonds'):
try:
ii = tags.index('extent')
try:
csvProt['numero'] = csvProt['numero'] + ' | ' + content
except:
csvProt['numero'] = content
except:
pass
try:
ii = tags.index('genreform')
try:
csvProt['genere'] = csvProt['genere'] + ' | ' + content
except:
csvProt['genere'] = content
except:
pass
# e21 Container (solo per subseries vale come extent)
if (attributes[tags.index('c')]['level']=='subseries'):
try:
ii = tags.index('container')
csvProt['extent'] = content
except:
pass
# e22 Phystech
try:
ii = tags.index('phystech')
try:
csvProt['conservazione'] = csvProt['conservazione'] + ' | ' + content
except:
csvProt['conservazione'] = content
except:
pass
# e23 Consistenza
try:
ii = tags.index('extent')
type1 = attributes[ii]['unit']
cvsProt['consistenza'] = type1 + ': ' + content
except:
pass
# e24 Note
if('note' in tags):
if('p' in tags):
try:
aa = csvProt['nota']
except:
try:
ii = tags.index('p')
try:
csvProt['nota'] = str(node['a_par'][ii].text).replace('\t','').replace('\n','').strip()
except:
csvProt['nota'] = str(content).replace('\t','').replace('\n','').strip()
except:
pass
# e25 Odd
if('odd' in tags):
csvProt['altre_informazioni'] = content
# e26 Oggetto digitale allegato (nome)
# Questo è un campo multiplo; per il momento, salviamo tutto
# su una cella concatenando e separando i campi con una pipe
# '| '
try:
ii = tags.index('daoloc')
out = attributes[ii]['title']
try:
csvProt['oggetto_digitale'] = csvProt['oggetto_digitale'] + ' | ' + out
except:
csvProt['oggetto_digitale'] = out
except:
pass
return csvProt
# Di pari passo alla funzione, definisco un dict contenente tutti gli header;
# servirà per il CSV.
itemHeader = OrderedDict()
# e1 ID dell'entità
itemHeader.update({'id': '<c level="X" id=#>'})
# e2 Audience: external o internal
itemHeader.update({'audience': '<c level="item" audience=#>'})
# e3 Otherlevel
itemHeader.update({'altro_livello': '<c otherlevel=#>'})
# e4 Repository (qui dovrebbe essere sempre l'Archivio di Prato)
itemHeader.update({'repository': '<repository>#'})
# e5 Bioghist
itemHeader.update({'bioghist': '<bioghist=#>'})
# e6 Arrangement
itemHeader.update({'arrangement': '<arrangement=#>'})
# e7 Related Material
itemHeader.update({'relatedmaterial': '<relatedmaterial=#>'})
# e8 Tipologia
itemHeader.update({'tipologia': '<materialspec label="tipologia">#'})
# e9 Segnature buste e registri Datini
itemHeader.update(
{'segnatura_registri_1': '<container type="%numero un%">#',
'segnatura_registri_2': '<container type="%numero sott%">#',
'segnatura_inserto': '<container type="inserto">#',
'segnatura_busta': '<container type="busta">#'})
# e9 Segnatura codice
itemHeader.update({'segnatura_codice': '<num type="chiave">#'})
# e9 segnatura subseries
itemHeader.update(
{'segnatura_parent': '<unitid type="segnatura">#'})
# e10 Titolo originale
itemHeader.update({'titolo_originale': '<title>#'})
# e11 Titolo ASPO
itemHeader.update({'titolo_aspo': '<unittitle>#'})
# e12 Scope content, head & body, e num allegati
itemHeader.update(
{'scope-content_head': '<scopecontent><head>#',
'scope-content_body': '<scopecontent><p>#',
'num_allegati': '<num>#'})
# e12 lista merci
itemHeader.update({'lista': '<list>#'})
# e13 Origine
itemHeader.update({'origine': '<origination label=#1>#2, #1 - #2'})
# e14 Nome della compagnia
itemHeader.update({'compagnia': '<corpname>#'})
# e15 Soggetto
itemHeader.update({'soggetto': '<subject>#'})
itemHeader.update({'tipologia_soggetto': '<emph>#'})
# e16 Persona + ruolo
itemHeader.update(
{'persona_tenutario': '<persname role="tenutario">#',
'persona_destinatario': '<persname role="destinatario">#',
'persona_mittente': '<persname role="mittente">#',
'persona_indirizzata': '<persname role="indirizzata">#',
'persona_mano': '<persname role="mano">#',})
# e17 Date varie: tutte quelle con 'type' definito + note
itemHeader.update(
{'data_inizio': '<date type="inizio">#', 'data_inizio_note': '<emph>#',
'data_fine': '<date type="fine">#', 'data_fine_note': '<emph>#',
'data_chiusura': '<date type="chiusura">#', 'data_chiusura_note': '<emph>#'})
# e18 Data 1: periodo
itemHeader.update({'data_periodo': '<unitdate>#' , 'data_periodo_note': '<unitdate>#'})
# e19 Luogo + 'ruolo'
itemHeader.update(
{"luogo_partenza": '<geogname role="partenza">#',
"luogo_arrivo": '<geogname role="arrivo">#',
"luogo_luogo": '<geogname role="luogo">#'})
# e20 Supporto fisico
itemHeader.update({'supporto': '<physfacet type="supporto">#'})
# e21 descrizione fisica
itemHeader.update({'descrizione_fisica': '<physdesc>#'})
itemHeader.update({'numero': '<extent>#'})
# container vale extent solo per subseries
itemHeader.update({'extent': '<container>#'})
itemHeader.update({'genere': '<genreform>#'})
# e22 phystech
itemHeader.update({'conservazione': '<phystech>#'})
# e23 Consistenza
itemHeader.update({'consistenza': '<extent unit=#1>#2, #1: #2'})
# e24 Note
itemHeader.update({'nota': '<note>#'})
# e25 Odd
itemHeader.update({'altre_informazioni': '<odd>#'})
# e26 Oggetto digitale allegato (nome)
itemHeader.update({'oggetto_digitale': '<daoloc title=#>'})
# e0: Le varie id dei nodi parent
itemHeader.update(
{'id_subfonds': '<c level="subfonds" id=#>',
'id_fonds': '<c level="fonds" id=#>',
'id_series': '<c level="series" id=#>',
'id_subseries': '<c level="subseries" id=#>',
'id_file': '<c level="file" id=#>',
'id_otherlevel': '<c level="otherlevel" id=#>',
'id_collection': '<c level="collection" id=#>'})Test della funzione traduttore
**NB:** l'ho definita basandomi sugli item, ma sembra funzionare decentemente anche sugli altri livelli!
jj = randint(0, len(allCs2['item']))
jj = 0
print(jj)
print()
test = allCs2['item'][248]
toShow = traduttoreItem(test)
for key in toShow.keys():
print(key + ': ' + str(toShow[key]))
print()0
id_fonds: ASPO00000000
id_subfonds: ASPO00000001
id_series: ASPO00000016
id_subseries: ASPO00001817
id: ASPO00001828
audience: external
origine: Fondaco: AVIGNONE
tipologia: libro
repository: Archivio di Stato di Prato
titolo_aspo: QUADERNO DI RAGIONE
compagnia: {nome: COMP. TORO DI BERTO, FRANCESCO DI MARCO DATINI E TUCCIO LAMBERTUCCI NELL'ARTE DELLE MERCI, authID: IT-ASPO-AU00003-0005916}
soggetto: FINANZIARIO-MERCANTILE
data_inizio: 1368
data_fine: 1368
data_periodo: 1368-1368
segnatura_registri_1: 177
descrizione_fisica: FORMATO MEZZANO; NUMERAZ. MODERNA CC. 34; NUMERAZ. ORIG. FINO A C. 21; COPERTA CARTACEA
(SALDO AL 17.09.1368 DI MERCANZIE, MASSERIZIE: CC. 4-30, 1368)
altre_informazioni: Copia del n. 197 (n.v. 177/04).
# Export
Produciamo il CSV per gli item tracciando, al solito, il tempo impiegato.
# Do it! Export del CSV - items.
ts1 = datetime.timestamp(datetime.now())
# Apro il file per l'export
with open(export_dir + "data_item.csv", "w", newline="") as csv_file:
# Definisco la classe-motore per l'export
writer = csv.DictWriter(csv_file, fieldnames=list(itemHeader.keys()))
# Scrivo l'intestazione
writer.writeheader()
# Scrivo la seconda riga, esplicativa
writer.writerow(itemHeader)
# Scrivo gli item tradotti, uno a uno
for ii in range(len(allCs2['item'])):
test = allCs2['item'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 76.27489900588989
# Altri livelli
Definisco un dizionario ridotto per l'header delle *subseries*, poi esporto -- per il momento con lo stesso traduttore usato per gli *item*
ts1 = datetime.timestamp(datetime.now())
subSeriesKeys = set()
for ii in range(len(allCs2['subseries'])):
test = allCs2['subseries'][ii]
subSeriesKeys = subSeriesKeys.union( traduttoreItem(test).keys() )
subSeriesHeader = OrderedDict()
for key in itemHeader:
if(key in subSeriesKeys):
subSeriesHeader[key] = itemHeader[key]
with open(export_dir + "data_subseries.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(subSeriesHeader.keys()))
writer.writeheader()
writer.writerow(subSeriesHeader)
for ii in range(len(allCs2['subseries'])):
test = allCs2['subseries'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 1.3703911304473877
*Rinse & Repeat* con i livelli *series*, *subfonds* e *fonds*
ts1 = datetime.timestamp(datetime.now())
seriesKeys = set()
for ii in range(len(allCs2['series'])):
test = allCs2['series'][ii]
seriesKeys = seriesKeys.union( traduttoreItem(test).keys() )
seriesHeader = OrderedDict()
for key in itemHeader:
if(key in seriesKeys):
seriesHeader[key] = itemHeader[key]
with open(export_dir + "data_series.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(seriesHeader.keys()))
writer.writeheader()
writer.writerow(seriesHeader)
for ii in range(len(allCs2['series'])):
test = allCs2['series'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 0.11757516860961914
ts1 = datetime.timestamp(datetime.now())
subfondsKeys = set()
for ii in range(len(allCs2['subfonds'])):
test = allCs2['subfonds'][ii]
subfondsKeys = subfondsKeys.union( traduttoreItem(test).keys() )
subfondsHeader = OrderedDict()
for key in itemHeader:
if(key in subfondsKeys):
subfondsHeader[key] = itemHeader[key]
with open(export_dir + "data_subfonds.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(subfondsHeader.keys()))
writer.writeheader()
writer.writerow(subfondsHeader)
for ii in range(len(allCs2['subfonds'])):
test = allCs2['subfonds'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 0.024317026138305664
ts1 = datetime.timestamp(datetime.now())
fondsKeys = set()
for ii in range(len(allCs2['fonds'])):
test = allCs2['fonds'][ii]
fondsKeys = fondsKeys.union( traduttoreItem(test).keys() )
fondsHeader = OrderedDict()
for key in itemHeader:
if(key in fondsKeys):
fondsHeader[key] = itemHeader[key]
with open(export_dir + "data_fonds.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(fondsHeader.keys()))
writer.writeheader()
writer.writerow(fondsHeader)
for ii in range(len(allCs2['fonds'])):
test = allCs2['fonds'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 0.002727985382080078
ts1 = datetime.timestamp(datetime.now())
fileKeys = set()
for ii in range(len(allCs2['file'])):
test = allCs2['file'][ii]
fileKeys = fileKeys.union( traduttoreItem(test).keys() )
fileHeader = OrderedDict()
for key in itemHeader:
if(key in fileKeys):
fileHeader[key] = itemHeader[key]
with open(export_dir + "data_file.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(fileHeader.keys()))
writer.writeheader()
writer.writerow(fileHeader)
for ii in range(len(allCs2['file'])):
test = allCs2['file'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 9.000669002532959
ts1 = datetime.timestamp(datetime.now())
collectionKeys = set()
for ii in range(len(allCs2['collection'])):
test = allCs2['collection'][ii]
collectionKeys = collectionKeys.union( traduttoreItem(test).keys() )
collectionHeader = OrderedDict()
for key in itemHeader:
if(key in collectionKeys):
collectionHeader[key] = itemHeader[key]
with open(export_dir + "data_collection.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(collectionHeader.keys()))
writer.writeheader()
writer.writerow(collectionHeader)
for ii in range(len(allCs2['collection'])):
test = allCs2['collection'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 0.0027909278869628906
ts1 = datetime.timestamp(datetime.now())
otherlevelKeys = set()
for ii in range(len(allCs2['otherlevel'])):
test = allCs2['otherlevel'][ii]
otherlevelKeys = otherlevelKeys.union( traduttoreItem(test).keys() )
otherlevelHeader = OrderedDict()
for key in itemHeader:
if(key in otherlevelKeys):
otherlevelHeader[key] = itemHeader[key]
with open(export_dir + "data_otherlevel.csv", "w", newline="") as csv_file:
writer = csv.DictWriter(csv_file, fieldnames=list(otherlevelHeader.keys()))
writer.writeheader()
writer.writerow(otherlevelHeader)
for ii in range(len(allCs2['otherlevel'])):
test = allCs2['otherlevel'][ii]
writer.writerow(traduttoreItem(test))
print('Tempo trascorso:', datetime.timestamp(datetime.now()) - ts1)Tempo trascorso: 0.134688138961792