{
  "cells": [
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2019-02-20T09:27:15.757201Z",
          "start_time": "2019-02-20T09:27:15.753197Z"
        }
      },
      "cell_type": "markdown",
      "source": "# Tesseract Basic Example"
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2019-02-20T09:10:45.913853Z",
          "start_time": "2019-02-20T09:10:42.459611Z"
        },
        "trusted": true
      },
      "cell_type": "code",
      "source": "try:\n    from PIL import Image\nexcept ImportError:\n    import Image\nimport pytesseract\n\n# If you don't have tesseract executable in your PATH, include the following:\npytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract'\n# Example tesseract_cmd = r'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract'\n\n# Simple image to string\nprint(pytesseract.image_to_string(Image.open('test.png')))\n\n# # French text image to string\n# print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))\n\n# Get bounding box estimates\nprint(pytesseract.image_to_boxes(Image.open('test.png')))\n\n# Get verbose data including boxes, confidences, line and page numbers\nprint(pytesseract.image_to_data(Image.open('test.png')))\n\n# Get information about orientation and script detection\n# print(pytesseract.image_to_osd(Image.open('test.png')))\n\n# In order to bypass the internal image conversions, just use relative or absolute image path\n# NOTE: If you don't use supported images, tesseract will return error\nprint(pytesseract.image_to_string('test.png'))\n\n# get a searchable PDF\n# pdf = pytesseract.image_to_pdf_or_hocr('test.png', extension='pdf')\n\n# get HOCR output\n# hocr = pytesseract.image_to_pdf_or_hocr('test.png', extension='hocr')",
      "execution_count": 4,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "QGphJT\nQ 2 35 59 107 0\nG 68 52 113 120 0\np 131 34 168 100 0\nh 191 49 237 120 0\nJ 254 49 270 112 0\nT 270 49 316 112 0\nlevel\tpage_num\tblock_num\tpar_num\tline_num\tword_num\tleft\ttop\twidth\theight\tconf\ttext\n1\t1\t0\t0\t0\t0\t0\t0\t316\t159\t-1\t\n2\t1\t1\t0\t0\t0\t2\t39\t314\t86\t-1\t\n3\t1\t1\t1\t0\t0\t2\t39\t314\t86\t-1\t\n4\t1\t1\t1\t1\t0\t2\t39\t314\t86\t-1\t\n5\t1\t1\t1\t1\t1\t2\t39\t314\t86\t21\tQGphJT\nQGphJ\nHello\n"
        }
      ]
    },
    {
      "metadata": {
        "ExecuteTime": {
          "end_time": "2019-02-20T11:04:51.259163Z",
          "start_time": "2019-02-20T11:04:51.255161Z"
        }
      },
      "cell_type": "markdown",
      "source": "# Python Example 1"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "gist": {
      "id": "",
      "data": {
        "description": "MyNotebook.ipynb",
        "public": true
      }
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.8",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "notify_time": "5",
    "toc": {
      "nav_menu": {
        "height": "114px",
        "width": "276px"
      },
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "base_numbering": "1",
      "title_cell": "Tesseract Basic Example",
      "title_sidebar": "Python Example",
      "toc_cell": false,
      "toc_position": {
        "height": "calc(100% - 180px)",
        "left": "10px",
        "top": "150px",
        "width": "209.188px"
      },
      "toc_section_display": true,
      "toc_window_display": true
    },
    "varInspector": {
      "window_display": false,
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "library": "var_list.py",
          "delete_cmd_prefix": "del ",
          "delete_cmd_postfix": "",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "library": "var_list.r",
          "delete_cmd_prefix": "rm(",
          "delete_cmd_postfix": ") ",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ]
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "state": {},
        "version_major": 2,
        "version_minor": 0
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}