yyoshiaki/sushida.ipynb

## sushida.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Installation\n",
    "\n",
    "### pyocr\n",
    "\n",
    "[ブログ記事](http://teru0rc4.hatenablog.com/entry/2017/08/09/230046)参照\n",
    "ちょっとめんどくさい。\n",
    "日本語はいらない。\n",
    "\n",
    "### その他\n",
    "\n",
    "Pillow, pyguiをpipで入れる"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ライブラリの動作確認"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Will use tool 'Tesseract (sh)'\n",
      "Available languages: eng, osd\n",
      "Will use lang 'eng'\n"
     ]
    }
   ],
   "source": [
    "from PIL import Image\n",
    "import sys\n",
    "\n",
    "import pyocr\n",
    "import pyocr.builders\n",
    "\n",
    "tools = pyocr.get_available_tools()\n",
    "if len(tools) == 0:\n",
    "    print(\"No OCR tool found\")\n",
    "    sys.exit(1)\n",
    "# The tools are returned in the recommended order of usage\n",
    "tool = tools[0]\n",
    "print(\"Will use tool '%s'\" % (tool.get_name()))\n",
    "# Ex: Will use tool 'libtesseract'\n",
    "\n",
    "langs = tool.get_available_languages()\n",
    "print(\"Available languages: %s\" % \", \".join(langs))\n",
    "lang = langs[0]\n",
    "print(\"Will use lang '%s'\" % (lang))\n",
    "# Ex: Will use lang 'fra'\n",
    "# Note that languages are NOT sorted in any way. Please refer\n",
    "# to the system locale settings for the default language\n",
    "# to use."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from PIL import ImageGrab\n",
    "# 指定した領域内をクリッピング\n",
    "# (x1,y1,x2,y2)\n",
    "ImageGrab.grab(bbox=(1100, 1600, 2700, 1800)).save(\"tmp/cap.png\")"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "import pyautogui as pgui\n",
    "def testKey():\n",
    "#     pgui.click(50,50)\n",
    "    pgui.typewrite('Hello, pyautogui key!')\n",
    "    \n",
    "testKey()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ここから本番"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pyautogui as pgui\n",
    "from PIL import ImageGrab\n",
    "import pyocr\n",
    "import re\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "o-punkyanpasu\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x1182b9320>"
      ]
     },
     "execution_count": 176,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#  調整用（金の皿でまるまる収まるように。空白はできるだけ入れない）\n",
    "# ローマ字がまるまるキャプチャでndomokkouyoubondoきる位置に。\n",
    "# bbox = (1170, 1160, 2120, 1250)\n",
    "bbox = (1080, 1300, 2240, 1430)\n",
    "\n",
    "# ImageGrab.grab(bbox=bbox).save(\"tmp/cap.png\")\n",
    "img = ImageGrab.grab(bbox=bbox)\n",
    "txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "    img,\n",
    "    builder=pyocr.builders.TextBuilder()\n",
    ")\n",
    "txt = txt.replace(\"—\", \"-\")\n",
    "txt = re.sub(r'[A-Z]', \"\", txt)\n",
    "txt = re.sub(r'[0-9]', \"\", txt)\n",
    "txt = txt.replace(\"'\", \"\")\n",
    "txt = txt.replace(\" \", \"\")\n",
    "print(txt)\n",
    "plt.imshow(img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "36180\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x1183d4c88>"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#  調整用（金の皿でまるまる収まるように。空白はできるだけ入れない）\n",
    "# ローマ字がまるまるキャプチャでndomokkouyoubondoきる位置に。\n",
    "# bbox_score = (1155, 820, 1520, 950)\n",
    "bbox_score = (1090, 920, 1520, 1050)\n",
    "\n",
    "# ImageGrab.grab(bbox=bbox).save(\"tmp/cap.png\")\n",
    "img_score = ImageGrab.grab(bbox=bbox_score)\n",
    "txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "    img_score,\n",
    "    builder=pyocr.builders.TextBuilder()\n",
    ")\n",
    "extracted = \"\".join([x for x in txt if x.isdigit()])\n",
    "print(int(extracted))\n",
    "plt.imshow(img_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "60300\n",
      "58020\n",
      "60780\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-179-43e80a26297f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     20\u001b[0m     txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n\u001b[1;32m     21\u001b[0m         \u001b[0mimg\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 22\u001b[0;31m         \u001b[0mbuilder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpyocr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbuilders\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTextBuilder\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     23\u001b[0m     )\n\u001b[1;32m     24\u001b[0m     \u001b[0mtxt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtxt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreplace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"—\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"-\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/pyocr/tesseract.py\u001b[0m in \u001b[0;36mimage_to_string\u001b[0;34m(image, lang, builder)\u001b[0m\n\u001b[1;32m    363\u001b[0m                                          \u001b[0mlang\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mlang\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    364\u001b[0m                                          \u001b[0mflags\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbuilder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtesseract_flags\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 365\u001b[0;31m                                          configs=builder.tesseract_configs)\n\u001b[0m\u001b[1;32m    366\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mstatus\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    367\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mTesseractError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/.pyenv/versions/anaconda3-4.2.0/lib/python3.5/site-packages/pyocr/tesseract.py\u001b[0m in \u001b[0;36mrun_tesseract\u001b[0;34m(input_filename, output_filename_base, cwd, lang, flags, configs)\u001b[0m\n\u001b[1;32m    285\u001b[0m     \u001b[0;31m# In the end, we just have to make sure that proc.stderr.read() is called\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    286\u001b[0m     \u001b[0;31m# before proc.wait()\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 287\u001b[0;31m     \u001b[0merrors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mproc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstdout\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    288\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mproc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwait\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    289\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import time\n",
    "# main\n",
    "# ローマ字がまるまるキャプチャできる位置に。\n",
    "# bbox = (1170, 1160, 2120, 1250)\n",
    "bbox = (1080, 1300, 2240, 1430)\n",
    "# bbox_score = (1155, 820, 1520, 950)\n",
    "bbox_score = (1090, 920, 1520, 1050)\n",
    "\n",
    "pgui.click(50,50)\n",
    "\n",
    "pgui.typewrite(' ')\n",
    "\n",
    "list_score = []\n",
    "count = 0\n",
    "flag = 0\n",
    "num_pic=0\n",
    "ex_img = ImageGrab.grab(bbox=bbox)\n",
    "while True:\n",
    "    img = ImageGrab.grab(bbox=bbox)\n",
    "    txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "        img,\n",
    "        builder=pyocr.builders.TextBuilder()\n",
    "    )\n",
    "    txt = txt.replace(\"—\", \"-\")\n",
    "    txt = re.sub(r'[A-Z]', \"\", txt)\n",
    "    txt = re.sub(r'[0-9]', \"\", txt)\n",
    "    txt = txt.replace(\"'\", \"\")\n",
    "    txt = txt.replace(\" \", \"\")\n",
    "    \n",
    "    pgui.typewrite(txt)\n",
    "    \n",
    "    \n",
    "    if ex_img == img:\n",
    "        count += 1\n",
    "    \n",
    "#     if count == 4 & flag == 0:\n",
    "#         pgui.typewrite('aiueo-,kstnhmyrw')\n",
    "#         pgui.typewrite('aiueo-,kstnhmyrw')\n",
    "#         pgui.typewrite('aiueo-,kstnhmyrw')\n",
    "#         count = 0\n",
    "#         flag = 1\n",
    "#         time.sleep(1.5)\n",
    "        \n",
    "    if count == 20:\n",
    "        flag = 0\n",
    "        # ImageGrab.grab(bbox=bbox).save(\"tmp/cap.png\")\n",
    "        img_score = ImageGrab.grab(bbox=bbox_score)\n",
    "        txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "            img_score,\n",
    "            builder=pyocr.builders.TextBuilder()\n",
    "        )\n",
    "\n",
    "        extracted = \"\".join([x for x in txt if x.isdigit()])\n",
    "#         print(int(extracted))\n",
    "        \n",
    "        if int(extracted) < 90000:\n",
    "            count = 0\n",
    "            if int(extracted) > 80000:\n",
    "                num_pic += 1\n",
    "                img_score.save(\"tmp/screenshot{}.png\".format(num_pic))\n",
    "                \n",
    "            list_score.append(int(extracted))\n",
    "            print(extracted)\n",
    "            pgui.press('escape')\n",
    "            pgui.typewrite(' ')\n",
    "        else:\n",
    "            print(extracted)\n",
    "            break\n",
    "    \n",
    "    ex_img = img"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 高速化用に試行錯誤したが、特に気にしなくて良い"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "metadata": {},
   "outputs": [],
   "source": [
    "builder = pyocr.builders.TextBuilder()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1458600\n",
      "1.05 s ± 16.3 ms per loop (mean ± std. dev. of 10 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -r 10\n",
    "#  調整用（金の皿でまるまる収まるように。空白はできるだけ入れない）\n",
    "# ローマ字がまるまるキャプチャでndomokkouyoubondoきる位置に。\n",
    "# bbox_score = (1155, 820, 1520, 950)\n",
    "bbox_score = (500, 120, 1520, 1550)\n",
    "\n",
    "# ImageGrab.grab(bbox=bbox).save(\"tmp/cap.png\")\n",
    "img_score = ImageGrab.grab(bbox=bbox_score)\n",
    "txt = tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "    img_score,\n",
    "    builder=builder\n",
    ")\n",
    "extracted = \"\".join([x for x in txt if x.isdigit()])\n",
    "# # print(int(extracted))\n",
    "# plt.imshow(img_score)\n",
    "\n",
    "print((bbox_score[2] - bbox_score[0]) * (bbox_score[3] - bbox_score[1]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.imshow(img_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "55900"
      ]
     },
     "execution_count": 187,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(bbox_score[2] - bbox_score[0]) * (bbox_score[3] - bbox_score[1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "metadata": {},
   "outputs": [],
   "source": [
    "area = [886600]\n",
    "t = [1.08]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<PIL.Image.Image image mode=RGBA size=365x130 at 0x11858EA20>"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "img_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2,760'"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tool.image_to_string( # ここでOCRの対象や言語，オプションを指定する\n",
    "    img_score,\n",
    "    builder=pyocr.builders.TextBuilder()\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x1162339b0>"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.imshow(img)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:anaconda3-4.2.0]",
   "language": "python",
   "name": "conda-env-anaconda3-4.2.0-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}