Untitled0.ipynb

untitled0.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled0.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPI9wTSkjW7X+tGON8x3hfB",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/y-o-u/a1b1e4af34a7ea8c6e1eb105a8c65f10/untitled0.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!apt install tesseract-ocr libtesseract-dev poppler-utils tesseract-ocr-jpn"
      ],
      "metadata": {
        "id": "1l_rjgS05wZn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "zeHP-vw-5VZw"
      },
      "outputs": [],
      "source": [
        "pip install pyocr"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pip install pdf2image"
      ],
      "metadata": {
        "id": "1Is7oP3y59Di"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from PIL import Image\n",
        "import sys\n",
        "import pyocr\n",
        "import pyocr.builders\n",
        "import pdf2image\n",
        "\n",
        "tools = pyocr.get_available_tools()\n",
        "if len(tools) == 0:\n",
        "    print(\"No OCR tool found\")\n",
        "    sys.exit(1)\n",
        "\n",
        "# The tools are returned in the recommended order of usage\n",
        "tool = tools[0]\n",
        "\n",
        "images = pdf2image.convert_from_path(\"000667876.pdf\", dpi=200, fmt='jpg')\n",
        "#lang = 'eng'\n",
        "lang = 'jpn'\n",
        "\n",
        "# 画像オブジェクトからテキストに\n",
        "##for image in images:\n",
        "##    txt = tool.image_to_string(\n",
        "##        image,\n",
        "##        lang=lang,\n",
        "##        builder=pyocr.builders.TextBuilder()\n",
        "##    )\n",
        "  \n",
        "txt = tool.image_to_string(\n",
        "        images[3],\n",
        "        lang=lang,\n",
        "        builder=pyocr.builders.TextBuilder()\n",
        "    )\n",
        "\n",
        "print(txt)\n",
        "exit()"
      ],
      "metadata": {
        "id": "W3hZF6Jn6B9z"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}

Thank you