Tesseract IPython Notebook

README.md

apt.txt

tesseract-ocr
tesseract-ocr-deu
tesseract-ocr-script-latn
tesseract-ocr-script-frak
libtesseract-dev
ocrmypdf

pytesseract-example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "try:\n",
    "    from PIL import Image\n",
    "except ImportError:\n",
    "    import Image\n",
    "\n",
    "import pytesseract"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LooseVersion ('4.0.0-beta.1')"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pytesseract.get_tesseract_version()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(pytesseract.image_to_string(Image.open('test.png')))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Usage:\r\n",
      "  tesseract --help | --help-extra | --version\r\n",
      "  tesseract --list-langs\r\n",
      "  tesseract imagename outputbase [options...] [configfile...]\r\n",
      "\r\n",
      "OCR options:\r\n",
      "  -l LANG[+LANG]        Specify language(s) used for OCR.\r\n",
      "NOTE: These options must occur before any configfile.\r\n",
      "\r\n",
      "Single options:\r\n",
      "  --help                Show this help message.\r\n",
      "  --help-extra          Show extra help for advanced users.\r\n",
      "  --version             Show version information.\r\n",
      "  --list-langs          List available languages for tesseract engine.\r\n"
     ]
    }
   ],
   "source": [
    "!tesseract -h"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "List of available languages (2):\r\n",
      "osd\r\n",
      "eng\r\n"
     ]
    }
   ],
   "source": [
    "!tesseract --list-langs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

requirements.txt

pytesseract

test.png