{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 1: define papermill parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": [
     "parameters"
    ]
   },
   "outputs": [],
   "source": [
    "file_path = \"./example.jpg\""
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 2: read file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "\n",
    "img = cv2.imread(file_path)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Step 3: extract text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "tags": [
     "output"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CONSTRUCTION TYPE: VB\n",
      "\n",
      "OCCUPANCY TYPE: R-3\n",
      "\n",
      "APN: 00302030\n",
      "\n",
      "ZONING DISTRICT: R-1\n",
      "\n",
      "CONSTRUCTION LOCATION:\n",
      "\n",
      "775 Hamilton Ave Palo Alto Ca 94301\n",
      "\n",
      "PROJECT OWNER:\n",
      "\n",
      "Michael Asher (650) 520-8509 mike.asher@gmail.com\n",
      "\n",
      "775 Hamilton Ave Palo Alto Ca 94301\n",
      "\n",
      "FIRE SPRINKLERS:\n",
      "\n",
      "N/A (EXISTING PRIMARY HOME IS NOT EQUIPPED WITH\n",
      "\n",
      "FIRE SPRINKLERS)\n",
      "\n",
      "PHOTOVOLTAIC SYSTEM:\n",
      "\n",
      "TO BE FILED AS A DEFERRED SUBMITTAL - SEE CF1R\n",
      "\n",
      "GROSS FLOOR AREA:\n",
      "\n",
      "PROPOSED: 951.62 SQFT\n",
      "\n",
      "AV. BLDG. HEIG!\n",
      "\n",
      "PROPOSED: 12-4\" FT\n",
      "\n",
      "F.AR. CALCS: (800S.F. OF EXEMPT AREA FOR ADU)\n",
      "\n",
      "ALLOWABLE F.A.R. 3,450 SOFT\n",
      "\n",
      "LOT: 9,352 SQFT\n",
      "\n",
      "PRIMARY DWELLING FOOTPRINT: 2.388 SQFT\n",
      "\n",
      "PROPOSED ADU FOOTPRINT: 750 SQFT\n",
      "\n",
      "PROPOSED JADU FOOTPRINT: 350 SQFT\n",
      "\n",
      "RATIO: 29%\n",
      "\n",
      "PROJECT SCOPE:\n",
      "\n",
      "NEW CONSTRUCTION OF ADU & JADU ATTACHED TO\n",
      "\n",
      "EXISTING SINGLE-FAMILY PRIMARY DWELLING UNIT.\n"
     ]
    }
   ],
   "source": [
    "import pytesseract\n",
    "import cv2\n",
    "\n",
    "img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
    "text = pytesseract.image_to_string(img_rgb)\n",
    "\n",
    "lines = [line.strip() for line in text.split(\"\\n\")]\n",
    "lines = [line for line in lines if len(line) > 0]\n",
    "\n",
    "print(\"\\n\\n\".join(lines))"
   ]
  }
 ],
 "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": "3.10.6"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}