{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9bdb1960-15f6-4273-9c17-671608373885",
   "metadata": {},
   "source": [
    "Importación de archivos XML --- 5:29 min\n",
    "===\n",
    "\n",
    "* 5:29 min | Última modificación: Octubre 13, 2021 | [YouTube](https://youtu.be/mPm-fwomas0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "72feeac4-e01a-46e3-aecb-9f399d0e724c",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Overwriting /tmp/core-site.xml\n"
     ]
    }
   ],
   "source": [
    "%%writefile /tmp/core-site.xml\n",
    "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n",
    "<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>\n",
    "<configuration>\n",
    "    <property>\n",
    "        <name>fs.defaultFS</name>\n",
    "        <value>hdfs://0.0.0.0:9000</value>\n",
    "    </property>\n",
    "</configuration>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09db2f00-1cd8-4236-861d-f5fa4d6c3ea2",
   "metadata": {},
   "source": [
    "Interpretación\n",
    "    \n",
    "    {\n",
    "        \"root\": {\n",
    "            \"tag\": \"configuration\",\n",
    "            \"children\": [\n",
    "                {\n",
    "                    \"tag\": \"property\",\n",
    "                    \"children\": [\n",
    "                        {\n",
    "                            \"tag\": \"name\",\n",
    "                            \"text\": \"fs.defaultFS\",\n",
    "                        },\n",
    "                        {\n",
    "                            \"tag\": \"vaalue\",\n",
    "                            \"text\": \"hdfs://0.0.0.0:9000\",\n",
    "                        }\n",
    "                    ]\n",
    "                }\n",
    "            ]\n",
    "        }\n",
    "    }\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2ca262f9-cfdf-41b2-aa5e-c3c3586ff62b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'configuration'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Ingestión del archivo\n",
    "# ===============================================\n",
    "#\n",
    "import xml.etree.ElementTree as ET\n",
    "\n",
    "tree = ET.parse(\"/tmp/core-site.xml\")\n",
    "root = tree.getroot()\n",
    "root.tag"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "46c55c80-a5b4-42f2-8e6f-841d842d826a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<Element 'property' at 0x7fd56c0fe3b8>]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Lista de hijos del nodo raiz\n",
    "#\n",
    "root.getchildren()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b616042e-b7f7-4f72-a053-41021f22ea13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Cantidad de hijos del nodo raiz\n",
    "#\n",
    "len(root.getchildren())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "03dfb0ff-7ab7-4d57-925e-278a4e2de6d9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'property'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# tag del primer nodo hijo\n",
    "#\n",
    "root[0].tag"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8adc78e4-3b0a-474c-a994-240aad04a3fe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'name'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Primer tag del primer hijo\n",
    "#\n",
    "root[0][0].tag"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "8dd82ad1-e7c7-4495-915b-e8bd24b81520",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'fs.defaultFS'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Contenido de la propiedad text\n",
    "# del primer hijo\n",
    "#\n",
    "root[0][0].text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "c01c809a-1a61-406d-9563-d83c623e01b0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'hdfs://0.0.0.0:9000'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#\n",
    "# Contenido de la propiedad text\n",
    "# del segundo hijo\n",
    "#\n",
    "root[0][1].text"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}