{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "\n",
    "def clean_text(text):\n",
    "    \"\"\"\n",
    "    Applies some pre-processing on the given text.\n",
    "\n",
    "    Steps :\n",
    "    - Removing HTML tags\n",
    "    - Removing punctuation\n",
    "    - Lowering text\n",
    "    \"\"\"\n",
    "    \n",
    "    # remove HTML tags\n",
    "    text = re.sub(r'<.*?>', '', text)\n",
    "    \n",
    "    # remove the characters [\\], ['] and [\"]\n",
    "    text = re.sub(r\"\\\\\", \"\", text)    \n",
    "    text = re.sub(r\"\\'\", \"\", text)    \n",
    "    text = re.sub(r\"\\\"\", \"\", text)    \n",
    "    \n",
    "    # convert text to lowercase\n",
    "    text = text.strip().lower()\n",
    "    \n",
    "    # replace punctuation characters with spaces\n",
    "    filters='!\"\\'#$%&()*+,-./:;<=>?@[\\\\]^_`{|}~\\t\\n'\n",
    "    translate_dict = dict((c, \" \") for c in filters)\n",
    "    translate_map = str.maketrans(translate_dict)\n",
    "    text = text.translate(translate_map)\n",
    "\n",
    "    return text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['this', 'is', 'not', 'a', 'sentence']"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clean_text(\"<div>This is not a sentence.<\\div>\").split()"
   ]
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}