{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from bs4 import BeautifulSoup\n",
    "import urllib\n",
    "from urllib import request\n",
    "import re\n",
    "import json\n",
    "from datetime import datetime\n",
    "import os\n",
    "import boto3\n",
    "import time\n",
    "import sys\n",
    "import plotly.offline as py\n",
    "import plotly.graph_objs as go\n",
    "import plotly.tools as tls\n",
    "import matplotlib\n",
    "from random import shuffle\n",
    "\n",
    "py.init_notebook_mode(connected=True)\n",
    "\n",
    "client_id = \"sYcWggwUdtmXwGqUrzzN\"\n",
    "client_secret = \"oxUqDSa22I\"\n",
    "\n",
    "link = \"https://openapi.naver.com/v1/datalab/search\"\n",
    "requested = request.Request(link)\n",
    "requested.add_header(\"X-Naver-Client-Id\",client_id)\n",
    "requested.add_header(\"X-Naver-Client-Secret\",client_secret)\n",
    "requested.add_header(\"Content-Type\",\"application/json\")\n",
    "\n",
    "df = pd.read_excel(\"index.xls\")\n",
    "names = df.회사명.values\n",
    "\n",
    "now = datetime.now().strftime(\"%Y-%m-%d\")\n",
    "body_dict = {\"startDate\":\"2017-01-01\", \n",
    "               \"endDate\":\"2020-05-07\",\n",
    "               \"timeUnit\":\"date\"}\n",
    "v_list = [{\"groupName\" : i, \"keywords\" : [i]} for i in names]\n",
    "df[\"대표자명\"] = df[\"대표자명\"].apply(lambda x: re.sub(r'\\(.*\\)', '', x))\n",
    "df[\"대표자명\"]  = df[\"대표자명\"].apply(lambda x: [re.compile('[^ㄱ-ㅣ가-힣]+').sub(\"\",x)] if len(re.compile('[^ㄱ-ㅣ가-힣]+').sub(\"\",x)) < 5 else re.findall(r\"[\\w']+\", x))\n",
    "\n",
    "for i in range(0, df.shape[0]):\n",
    "    for j in df[\"대표자명\"].values[i]:\n",
    "        if \"대표\" not in j and j!= \"\":\n",
    "            v_list[i][\"keywords\"].append(j) \n",
    "    \n",
    "shuffle(v_list)\n",
    "standard = v_list[0]\n",
    "standard_keyword = standard[\"groupName\"]\n",
    "list_use = v_list[1:]\n",
    "\n",
    "split_list = [list_use[i:i+4] for i in range(0, len(list_use), 4)]\n",
    "\n",
    "for i in split_list:\n",
    "    i.append(standard)\n",
    "\n",
    "sample_body = body_dict\n",
    "sample_body[\"keywordGroups\"] = split_list[0]\n",
    "sample_body = json.dumps(sample_body, ensure_ascii=False)\n",
    "sample_response = request.urlopen(requested, data=sample_body.encode(\"utf-8\"))\n",
    "\n",
    "code = sample_response.getcode() \n",
    "if code == 200: \n",
    "    sample_response_body = sample_response.read()\n",
    "    sample_scraped = sample_response_body.decode(\"utf-8\")\n",
    "else: \n",
    "    print (\"Error Code:\", code)\n",
    "\n",
    "sample_result = json.loads(sample_scraped)\n",
    "\n",
    "for i in sample_result[\"results\"] :\n",
    "    if i[\"title\"] == standard_keyword:\n",
    "        sample_standard = i[\"data\"]\n",
    "scale = sample_standard[0][\"ratio\"]\n",
    "\n",
    "df = {}\n",
    "\n",
    "df[standard_keyword] = np.array([i[\"ratio\"] for i in sample_standard])\n",
    "length = len(df[standard_keyword])\n",
    "date = np.array([i[\"period\"] for i in sample_standard])\n",
    "for i in split_list:\n",
    "\n",
    "    body_dict[\"keywordGroups\"] = i\n",
    "    body = json.dumps(body_dict, ensure_ascii=False)\n",
    "    \n",
    "    print(i)\n",
    "    response = request.urlopen(requested, data=body.encode(\"utf-8\"))\n",
    "    \n",
    "    code = response.getcode() \n",
    "    if code == 200: \n",
    "        response_body = response.read()\n",
    "        scraped = response_body.decode(\"utf-8\")\n",
    "    else: \n",
    "        print (\"Error Code:\", code)\n",
    "    \n",
    "    \n",
    "    \n",
    "    result = json.loads(scraped)\n",
    "    \n",
    "    for i in result[\"results\"]:\n",
    "        if i[\"title\"] == standard_keyword:\n",
    "            compare = i[\"data\"]\n",
    "    compare = compare[0][\"ratio\"]\n",
    "    \n",
    "    scaling = scale/compare\n",
    "    \n",
    "    for i in result[\"results\"]:\n",
    "        if i[\"title\"]!=standard_keyword:\n",
    "            value = [j[\"ratio\"]*scaling for j in i[\"data\"]]\n",
    "            if len(value)!=length:\n",
    "                value+=np.abs(length-len(value)) * [value[-1]]\n",
    "            df[i[\"title\"]] = np.array(value)\n",
    "\n",
    "df = pd.DataFrame(df)\n",
    "df[\"date\"] = date\n",
    "df = df.set_index(\"date\")\n",
    "df.to_csv(\"trend.xls\", encoding = \"utf-8\")\n",
    "\n",
    "df.plot(title = \"Naver Trend - Stock-Daily\", figsize = (20, 10), legend = False)\n",
    "\n"
   ]
  }
 ],
 "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": "3.6.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}