pdfTable-to-csv.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tabula-py in c:\\programdata\\anaconda3\\lib\\site-packages (2.2.0)\n",
      "Requirement already satisfied: distro in c:\\programdata\\anaconda3\\lib\\site-packages (from tabula-py) (1.5.0)\n",
      "Requirement already satisfied: pandas>=0.25.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from tabula-py) (1.1.0)\n",
      "Requirement already satisfied: numpy in c:\\programdata\\anaconda3\\lib\\site-packages (from tabula-py) (1.19.1)\n",
      "Requirement already satisfied: python-dateutil>=2.7.3 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas>=0.25.3->tabula-py) (2.8.1)\n",
      "Requirement already satisfied: pytz>=2017.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas>=0.25.3->tabula-py) (2018.4)\n",
      "Requirement already satisfied: six>=1.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from python-dateutil>=2.7.3->pandas>=0.25.3->tabula-py) (1.11.0)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: You are using pip version 19.2.3, however version 21.1.2 is available.\n",
      "You should consider upgrading via the 'python -m pip install --upgrade pip' command.\n"
     ]
    }
   ],
   "source": [
    "!pip install tabula-py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tabula import read_pdf\n",
    "\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "frames = []\n",
    "pages = 2\n",
    "for page in range(1,pages+1):\n",
    "    content = read_pdf('C:/Users/Rishiraj/Desktop/AQI_Bulletin_20210107.pdf', pages=page)\n",
    "    df = content[0][::2] #skip Nan rows\n",
    "    df = df.iloc[1:] #skip first row\n",
    "    frames.append(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "finalDf = pd.concat(frames)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "finalDf.columns = ['index','city', 'air quality','index value','pollutant','monitoring stations']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "finalDf.to_csv('C:/Users/Rishiraj/Desktop/AQI_Bulletin_20210107.csv')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## pdftables_api\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pdftables_api\n",
    "\n",
    "#paid tool, but useless\n",
    "  \n",
    "# API KEY VERIFICATION\n",
    "conversion = pdftables_api.Client('')\n",
    "  \n",
    "# PDf to CSV \n",
    "# (Hello.pdf, Hello)\n",
    "conversion.csv('C:/Users/Rishiraj/Desktop/AQI_Bulletin_20210107.pdf', 'C:/Users/Rishiraj/Desktop/AQI_Bulletin_20210107_Paid.csv')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}