Parser/Museo/ICCD_to_CSV/ICCDtoCSV.py

import xml.etree.ElementTree as Xet
import pandas as pd
import os
import csv
from xml.dom import minidom
import sys

# Passo al parser i file xml
xml_file_name = '/Users/alessiaspadi/Documents/RESTORE/temp_MPP/SR20OA_Datini.xml'
tree = Xet.parse(xml_file_name)
root = tree.getroot()
schede = root.find("schede")
schedeM = root.findall("schede/scheda")
scheda = schede.find("scheda")

OA_data = open('OA_Data.csv', 'w')
csvwriter = csv.writer(OA_data)


def iterate(node, aut, path=""):
    if path:
        current_path = path + "/" + node.tag
    else:
        current_path = node.tag
    path = current_path
    for child in node:
        iterate(child, aut, path=current_path)
    obj = cell(node)
    if obj is not None:
        aut.append(obj)
    return aut


def cell(nd):
    if nd is not None:
        res = nd.text
        tag = nd.tag
        st = res.rstrip()
        if st != "":
            res = "".join(st.splitlines())
            return [tag, res]


def build_row(scheda):
    cc = []
    iterate(scheda, cc)
    seen = dict()
    row = dict()
    plus_tag = []
    for elem in cc:
        tag = elem[0]
        if tag in seen:
            num = seen[tag]
            n = num + 1
            seen[tag] = n
            name = tag + str(n)
            row[name] = elem[1]
        else:
            tag = elem[0]
            seen[tag] = 0
            row[tag] = elem[1]
    return (row)


params = []
for scheda in schede:
    row = build_row(scheda)
    for p in row:
        if p not in params:
            params.append(p)


def build_table(schede):
    for scheda in schede:
        row = build_row(scheda)
        ul = []
        for x in params:
            if row.get(x) is None:
                ul.append(" ")
            else:
                ul.append(row[x])

        csvwriter.writerow(ul)


csvwriter.writerow(params)
build_table(schede)

OA_data.close()