Update content of the unzipped XML file using ElementTree (part of python standard library)

GIST_Update_XML.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.277587Z",
     "start_time": "2020-11-01T20:42:13.257609Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "from xml.etree import ElementTree as ET"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will use the standard python ElementTree library to parse the xmls\n",
    "https://docs.python.org/3.9/library/xml.etree.elementtree.html#module-xml.etree.ElementTree. We "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.293513Z",
     "start_time": "2020-11-01T20:42:13.279585Z"
    }
   },
   "outputs": [],
   "source": [
    "folder = \"temp\"\n",
    "file = \"a.xml\"\n",
    "\n",
    "# values to which we update\n",
    "new_prefix = \"updated\"\n",
    "new_version = 3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.309473Z",
     "start_time": "2020-11-01T20:42:13.295512Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Element 'data' at 0x0000020CC393C1D8>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# path to the unzipped xml in the temp folder\n",
    "path = os.path.join(folder, file)\n",
    "\n",
    "# load the xml\n",
    "tree = ET.parse(path)\n",
    "root = tree.getroot()\n",
    "\n",
    "# the wrapping tag <data> is the root element of our loaded xml\n",
    "root"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.325429Z",
     "start_time": "2020-11-01T20:42:13.311464Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'updated_003_20201026'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# in the <data> find the <id>...</id> node and show its content (.text)\n",
    "id = root.find(\"id\").text\n",
    "id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.341384Z",
     "start_time": "2020-11-01T20:42:13.327424Z"
    }
   },
   "outputs": [],
   "source": [
    "# split the id by \"_\" underscore\n",
    "split_id = id.split(\"_\")\n",
    "\n",
    "# update the values\n",
    "split_id[0] = new_prefix\n",
    "split_id[1] = \"{:03d}\".format(new_version) # prefix with leading zeros up to 3 position if needed\n",
    "\n",
    "# update the xml content\n",
    "root.find(\"id\").text = \"_\".join(split_id)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-11-01T20:42:13.357343Z",
     "start_time": "2020-11-01T20:42:13.343379Z"
    }
   },
   "outputs": [],
   "source": [
    "# any variable derived from root contains a reference to the original xml\n",
    "# so using tree.write writes the updated contant to the path\n",
    "tree.write(path)"
   ]
  }
 ],
 "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": "3.7.4"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}