XMLXSD.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b5054d07-1454-434b-bce4-0f5d5fe9065f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from lxml import etree"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "1e6b594d-7181-4b82-97ff-dce1e80681ef",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>price</th>\n",
       "      <th>description</th>\n",
       "      <th>calories</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Belgian Waffles</td>\n",
       "      <td>$5.95</td>\n",
       "      <td>Two of our famous Belgian Waffles with plenty ...</td>\n",
       "      <td>650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Strawberry Belgian Waffles</td>\n",
       "      <td>$7.95</td>\n",
       "      <td>Light Belgian waffles covered with strawberrie...</td>\n",
       "      <td>900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Berry-Berry Belgian Waffles</td>\n",
       "      <td>$8.95</td>\n",
       "      <td>Light Belgian waffles covered with an assortme...</td>\n",
       "      <td>900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>French Toast</td>\n",
       "      <td>$4.50</td>\n",
       "      <td>Thick slices made from our homemade sourdough ...</td>\n",
       "      <td>600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Homestyle Breakfast</td>\n",
       "      <td>$6.95</td>\n",
       "      <td>Two eggs, bacon or sausage, toast, and our eve...</td>\n",
       "      <td>950</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          name  price  \\\n",
       "0              Belgian Waffles  $5.95   \n",
       "1   Strawberry Belgian Waffles  $7.95   \n",
       "2  Berry-Berry Belgian Waffles  $8.95   \n",
       "3                 French Toast  $4.50   \n",
       "4          Homestyle Breakfast  $6.95   \n",
       "\n",
       "                                         description  calories  \n",
       "0  Two of our famous Belgian Waffles with plenty ...       650  \n",
       "1  Light Belgian waffles covered with strawberrie...       900  \n",
       "2  Light Belgian waffles covered with an assortme...       900  \n",
       "3  Thick slices made from our homemade sourdough ...       600  \n",
       "4  Two eggs, bacon or sausage, toast, and our eve...       950  "
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_excel('sample.xlsx')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "f29e4e26-c66c-4ae9-8914-881dc6657905",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_xml('out.xml', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "9298e0ae-9473-4fcd-a31c-fe17592fec3b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b'<data>\\n  <row>\\n    <name>Belgian Waffles</name>\\n    <price>$5.95</price>\\n    <description>Two of our famous Belgian Waffles with plenty of real maple syrup</description>\\n    <calories>650</calories>\\n  </row>\\n  <row>\\n    <name>Strawberry Belgian Waffles</name>\\n    <price>$7.95</price>\\n    <description>Light Belgian waffles covered with strawberries and whipped cream</description>\\n    <calories>900</calories>\\n  </row>\\n  <row>\\n    <name>Berry-Berry Belgian Waffles</name>\\n    <price>$8.95</price>\\n    <description>Light Belgian waffles covered with an assortment of fresh berries and whipped cream</description>\\n    <calories>900</calories>\\n  </row>\\n  <row>\\n    <name>French Toast</name>\\n    <price>$4.50</price>\\n    <description>Thick slices made from our homemade sourdough bread</description>\\n    <calories>600</calories>\\n  </row>\\n  <row>\\n    <name>Homestyle Breakfast</name>\\n    <price>$6.95</price>\\n    <description>Two eggs, bacon or sausage, toast, and our ever-popular hash browns</description>\\n    <calories>950</calories>\\n  </row>\\n</data>\\n'"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xml = etree.parse('out.xml')\n",
    "etree.tostring(xml, pretty_print=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "6ed993b5-3253-40fe-aa4c-da2bb3320e2f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validator = etree.XMLSchema(file=\"sample.xsd\")\n",
    "validator.validate(xml)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "highwire-stats-venv",
   "language": "python",
   "name": "highwire-stats-venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}

The XSD document is here.