{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xml.etree.ElementTree as Xet\n",
    "import pandas as pd\n",
    "import os\n",
    "import csv\n",
    "from xml.dom import minidom\n",
    "import sys\n",
    "\n",
    "# Passo al parser i file xml\n",
    "xml_file_name = '/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/XML/SR20OA_Ospedale.xml'\n",
    "tree = Xet.parse(xml_file_name)\n",
    "root = tree.getroot()\n",
    "schede = root.find(\"schede\")\n",
    "schedeM = root.findall(\"schede/scheda\")\n",
    "scheda = schede.find(\"scheda\")\n",
    "\n",
    "OA_data = open('/Users/federicaspinelli/TEAMOVI/Parser/DATA/MPP/CSV/new/OA_Data_Ospedale.csv', 'w')\n",
    "csvwriter = csv.writer(OA_data)\n",
    "\n",
    "\n",
    "def iterate(node, aut, path=\"\"):\n",
    "    if path:\n",
    "        current_path = path + \"/\" + node.tag\n",
    "    else:\n",
    "        current_path = node.tag\n",
    "    path = current_path\n",
    "    for child in node:\n",
    "        iterate(child, aut, path=current_path)\n",
    "    obj = cell(node)\n",
    "    if obj is not None:\n",
    "        aut.append(obj)\n",
    "    return aut\n",
    "\n",
    "\n",
    "def cell(nd):\n",
    "    if nd is not None:\n",
    "        res = nd.text\n",
    "        tag = nd.tag\n",
    "        st = res\n",
    "        if st is not None:\n",
    "            st = res.rstrip()\n",
    "            if st != \"\" :\n",
    "                res = \"\".join(st).splitlines()\n",
    "                #\n",
    "                return [tag, res]\n",
    "\n",
    "\n",
    "def build_row(scheda):\n",
    "    cc = []\n",
    "    iterate(scheda, cc)\n",
    "    seen = dict()\n",
    "    row = dict()\n",
    "    plus_tag = []\n",
    "    for elem in cc:\n",
    "        tag = elem[0]\n",
    "        if tag in seen:\n",
    "            num = seen[tag]\n",
    "            n = num + 1\n",
    "            seen[tag] = n\n",
    "            name = tag + str(n)\n",
    "            row[name] = elem[1]\n",
    "        else:\n",
    "            tag = elem[0]\n",
    "            seen[tag] = 0\n",
    "            row[tag] = elem[1]\n",
    "    return (row)\n",
    "\n",
    "\n",
    "params = []\n",
    "for scheda in schede:\n",
    "    row = build_row(scheda)\n",
    "    for p in row:\n",
    "        if p not in params:\n",
    "            params.append(p)\n",
    "\n",
    "\n",
    "def build_table(schede):\n",
    "    for scheda in schede:\n",
    "        row = build_row(scheda)\n",
    "        ul = []\n",
    "        for x in params:\n",
    "            if row.get(x) is None:\n",
    "                ul.append(\" \")\n",
    "            else:\n",
    "                ul.append(row[x])\n",
    "\n",
    "        csvwriter.writerow(ul)\n",
    "\n",
    "\n",
    "csvwriter.writerow(params)\n",
    "build_table(schede)\n",
    "\n",
    "OA_data.close()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.0 64-bit",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.0"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "397704579725e15f5c7cb49fe5f0341eb7531c82d19f2c29d197e8b64ab5776b"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}