Time_Series/Closing_Price_Scraping.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scraping Closing prices with Selenium"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from selenium import webdriver\n",
    "from selenium.webdriver.common.keys import Keys\n",
    "from selenium.webdriver.common.by import By\n",
    "from selenium.webdriver.chrome.options import Options\n",
    "import _pickle as pickle\n",
    "import random\n",
    "import glob\n",
    "import os\n",
    "import pandas as pd\n",
    "import time"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Function to scrape Prices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def closing_prices(stock):\n",
    "    \"\"\"\n",
    "    Using Selenium to scrape the prices from Yahoo Finance\n",
    "    \"\"\"\n",
    "    \n",
    "    # Randomize wait times\n",
    "    seq = [i/10 for i in range(3,12)]\n",
    "    \n",
    "    # Options to help load the page faster\n",
    "    chromeOptions = Options()\n",
    "    prefs = {\"profile.managed_default_content_settings.images\":2,\n",
    "         \"profile.default_content_setting_values.notifications\":2,\n",
    "         \"profile.managed_default_content_settings.stylesheets\":2,\n",
    "         \"profile.managed_default_content_settings.cookies\":1,\n",
    "         \"profile.managed_default_content_settings.javascript\":1,\n",
    "         \"profile.managed_default_content_settings.plugins\":2,\n",
    "         \"profile.managed_default_content_settings.popups\":2,\n",
    "         \"profile.managed_default_content_settings.geolocation\":2,\n",
    "         \"profile.managed_default_content_settings.media_stream\":2}\n",
    "    chromeOptions.add_experimental_option(\"prefs\",prefs)\n",
    "    chromeOptions.add_extension(r\"/Users/flatironschool/Desktop/extension_1_22_4_0.crx\")\n",
    "\n",
    "    # Opening a browser to google search\n",
    "    driver = webdriver.Chrome(options=chromeOptions)\n",
    "    driver.set_window_size(720,720)\n",
    "    driver.implicitly_wait(2)\n",
    "    driver.get(\"https://google.com\")\n",
    "\n",
    "    # Searching for the stock by ticker\n",
    "    search = driver.find_element(By.XPATH, \"//input[@class='gLFyf gsfi']\")\n",
    "    search.send_keys(f\"{stock.upper()} yahoo finance\")\n",
    "    search.send_keys(Keys.RETURN)\n",
    "    \n",
    "    # Clicking the top google result\n",
    "    try:\n",
    "        search_res = driver.find_element(By.XPATH, \"//*[@id='rso']/div/div/div[1]/div/div/div[1]/a/h3\")\n",
    "        search_res.click()\n",
    "    except:\n",
    "        try:\n",
    "            search_res = driver.find_element(By.XPATH, \"//*[@id='rso']/div[1]/div/div/div/div[1]/a/h3\")\n",
    "            search_res.click()\n",
    "        except:\n",
    "            search_res = driver.find_element_by_tag_name('h3')\n",
    "            search_res.click()\n",
    "\n",
    "    # Clicking the historical data\n",
    "    hist_but = driver.find_element(By.XPATH, \"//*[@id='quote-nav']/ul/li[6]/a\")\n",
    "    hist_but.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    # Clicking the date range\n",
    "    date_rg = driver.find_element(By.XPATH, \"//input[@class='C(t) O(n):f Tsh($actionBlueTextShadow) Bd(n) Bgc(t) Fz(14px) Pos(r) T(-1px) Bd(n):f Bxsh(n):f Cur(p) W(190px)']\")\n",
    "    date_rg.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    # Clicking \"Max\", then \"Done\", then \"Apply\"\n",
    "    max_but = driver.find_element(By.XPATH, \"//*[@id='Col1-1-HistoricalDataTable-Proxy']/section/div[1]/div[1]/div[1]/span[2]/div/div[1]/span[8]\")\n",
    "    max_but.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    done = driver.find_element(By.XPATH, \"//*[@id='Col1-1-HistoricalDataTable-Proxy']/section/div[1]/div[1]/div[1]/span[2]/div/div[3]/button[1]\")\n",
    "    done.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    apply = driver.find_element(By.XPATH, \"//*[@id='Col1-1-HistoricalDataTable-Proxy']/section/div[1]/div[1]/button\")\n",
    "    apply.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    # Finally downloading the CSV\n",
    "    download = driver.find_element(By.XPATH, \"//a[@class='Fl(end) Mt(3px) Cur(p)']\")\n",
    "    download.click()\n",
    "    time.sleep(random.choice(seq))\n",
    "\n",
    "    # Closing the window\n",
    "    driver.quit()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## User input for a specific stock\n",
    "User can select any stock desired"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Which stock would you like? f - ford motor\n"
     ]
    }
   ],
   "source": [
    "stock = input(\"Which stock would you like? \")\n",
    "closing_prices(stock)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Small function to retrieve the recently download csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "def grab_csv():\n",
    "    \"\"\"\n",
    "    Loading in the csv file with closing prices downloaded from Yahoo finance\n",
    "    \"\"\"\n",
    "    # File list retrieved from local download folder\n",
    "    list_of_files = glob.glob('../../../Downloads/*.csv') \n",
    "    \n",
    "    # Assigning the most recent file\n",
    "    latest_file = max(list_of_files, key=os.path.getctime)\n",
    "    return pd.read_csv(latest_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Date</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Adj Close</th>\n",
       "      <th>Volume</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>5908</th>\n",
       "      <td>2015-10-30</td>\n",
       "      <td>44.779999</td>\n",
       "      <td>46.619999</td>\n",
       "      <td>44.750000</td>\n",
       "      <td>46.119999</td>\n",
       "      <td>38.084156</td>\n",
       "      <td>3353700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5909</th>\n",
       "      <td>2015-11-02</td>\n",
       "      <td>46.139999</td>\n",
       "      <td>46.779999</td>\n",
       "      <td>44.520000</td>\n",
       "      <td>46.709999</td>\n",
       "      <td>38.571362</td>\n",
       "      <td>3946000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5910</th>\n",
       "      <td>2015-11-03</td>\n",
       "      <td>46.720001</td>\n",
       "      <td>48.160000</td>\n",
       "      <td>46.720001</td>\n",
       "      <td>47.369999</td>\n",
       "      <td>39.116364</td>\n",
       "      <td>3273800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5911</th>\n",
       "      <td>2015-11-04</td>\n",
       "      <td>47.439999</td>\n",
       "      <td>47.590000</td>\n",
       "      <td>45.820000</td>\n",
       "      <td>46.209999</td>\n",
       "      <td>38.158474</td>\n",
       "      <td>2590800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5912</th>\n",
       "      <td>2015-11-05</td>\n",
       "      <td>46.320000</td>\n",
       "      <td>46.759998</td>\n",
       "      <td>45.849998</td>\n",
       "      <td>46.660000</td>\n",
       "      <td>38.530067</td>\n",
       "      <td>2924500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5913</th>\n",
       "      <td>2015-11-06</td>\n",
       "      <td>46.540001</td>\n",
       "      <td>47.200001</td>\n",
       "      <td>46.200001</td>\n",
       "      <td>46.570000</td>\n",
       "      <td>38.455746</td>\n",
       "      <td>4085500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5914</th>\n",
       "      <td>2015-11-09</td>\n",
       "      <td>46.009998</td>\n",
       "      <td>46.200001</td>\n",
       "      <td>43.660000</td>\n",
       "      <td>43.980000</td>\n",
       "      <td>36.317032</td>\n",
       "      <td>6119500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5915</th>\n",
       "      <td>2015-11-10</td>\n",
       "      <td>43.630001</td>\n",
       "      <td>45.750000</td>\n",
       "      <td>43.509998</td>\n",
       "      <td>45.599998</td>\n",
       "      <td>37.654758</td>\n",
       "      <td>6824800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5916</th>\n",
       "      <td>2015-11-11</td>\n",
       "      <td>44.000000</td>\n",
       "      <td>44.040001</td>\n",
       "      <td>42.189999</td>\n",
       "      <td>43.160000</td>\n",
       "      <td>35.639900</td>\n",
       "      <td>9828300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5917</th>\n",
       "      <td>2015-11-12</td>\n",
       "      <td>45.430000</td>\n",
       "      <td>47.240002</td>\n",
       "      <td>45.000000</td>\n",
       "      <td>45.790001</td>\n",
       "      <td>37.811661</td>\n",
       "      <td>19188600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5918</th>\n",
       "      <td>2015-11-13</td>\n",
       "      <td>44.669998</td>\n",
       "      <td>44.669998</td>\n",
       "      <td>41.860001</td>\n",
       "      <td>42.849998</td>\n",
       "      <td>35.383904</td>\n",
       "      <td>9982600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5919</th>\n",
       "      <td>2015-11-16</td>\n",
       "      <td>42.689999</td>\n",
       "      <td>43.990002</td>\n",
       "      <td>42.570000</td>\n",
       "      <td>43.939999</td>\n",
       "      <td>36.284000</td>\n",
       "      <td>4144200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5920</th>\n",
       "      <td>2015-11-17</td>\n",
       "      <td>44.299999</td>\n",
       "      <td>45.169998</td>\n",
       "      <td>43.450001</td>\n",
       "      <td>44.049999</td>\n",
       "      <td>36.374836</td>\n",
       "      <td>4433900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5921</th>\n",
       "      <td>2015-11-18</td>\n",
       "      <td>44.279999</td>\n",
       "      <td>45.310001</td>\n",
       "      <td>43.720001</td>\n",
       "      <td>45.150002</td>\n",
       "      <td>37.283173</td>\n",
       "      <td>4506300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5922</th>\n",
       "      <td>2015-11-19</td>\n",
       "      <td>45.389999</td>\n",
       "      <td>45.770000</td>\n",
       "      <td>44.990002</td>\n",
       "      <td>45.180000</td>\n",
       "      <td>37.307941</td>\n",
       "      <td>2767800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5923</th>\n",
       "      <td>2015-11-20</td>\n",
       "      <td>45.590000</td>\n",
       "      <td>47.090000</td>\n",
       "      <td>45.580002</td>\n",
       "      <td>47.040001</td>\n",
       "      <td>38.843853</td>\n",
       "      <td>5070800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5924</th>\n",
       "      <td>2015-11-23</td>\n",
       "      <td>47.310001</td>\n",
       "      <td>47.970001</td>\n",
       "      <td>47.200001</td>\n",
       "      <td>47.639999</td>\n",
       "      <td>39.339314</td>\n",
       "      <td>3518700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5925</th>\n",
       "      <td>2015-11-24</td>\n",
       "      <td>47.349998</td>\n",
       "      <td>49.060001</td>\n",
       "      <td>47.320000</td>\n",
       "      <td>48.529999</td>\n",
       "      <td>40.074249</td>\n",
       "      <td>3262600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5926</th>\n",
       "      <td>2015-11-25</td>\n",
       "      <td>48.470001</td>\n",
       "      <td>48.930000</td>\n",
       "      <td>48.150002</td>\n",
       "      <td>48.500000</td>\n",
       "      <td>40.049469</td>\n",
       "      <td>2688400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5927</th>\n",
       "      <td>2015-11-27</td>\n",
       "      <td>48.820000</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>47.660000</td>\n",
       "      <td>48.070000</td>\n",
       "      <td>39.694397</td>\n",
       "      <td>1315800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5928</th>\n",
       "      <td>2015-11-30</td>\n",
       "      <td>48.220001</td>\n",
       "      <td>48.439999</td>\n",
       "      <td>46.570000</td>\n",
       "      <td>47.130001</td>\n",
       "      <td>38.918179</td>\n",
       "      <td>4785800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5929</th>\n",
       "      <td>2015-12-01</td>\n",
       "      <td>47.270000</td>\n",
       "      <td>47.910000</td>\n",
       "      <td>46.950001</td>\n",
       "      <td>47.220001</td>\n",
       "      <td>38.992504</td>\n",
       "      <td>3636700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5930</th>\n",
       "      <td>2015-12-02</td>\n",
       "      <td>47.419998</td>\n",
       "      <td>47.720001</td>\n",
       "      <td>46.180000</td>\n",
       "      <td>46.419998</td>\n",
       "      <td>38.331894</td>\n",
       "      <td>3128800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5931</th>\n",
       "      <td>2015-12-03</td>\n",
       "      <td>46.619999</td>\n",
       "      <td>47.419998</td>\n",
       "      <td>45.910000</td>\n",
       "      <td>47.389999</td>\n",
       "      <td>39.132877</td>\n",
       "      <td>5760200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5932</th>\n",
       "      <td>2015-12-04</td>\n",
       "      <td>47.180000</td>\n",
       "      <td>48.119999</td>\n",
       "      <td>46.860001</td>\n",
       "      <td>48.080002</td>\n",
       "      <td>39.702652</td>\n",
       "      <td>4279000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5933</th>\n",
       "      <td>2015-12-07</td>\n",
       "      <td>47.360001</td>\n",
       "      <td>47.770000</td>\n",
       "      <td>46.650002</td>\n",
       "      <td>47.450001</td>\n",
       "      <td>39.552608</td>\n",
       "      <td>4103800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5934</th>\n",
       "      <td>2015-12-08</td>\n",
       "      <td>46.900002</td>\n",
       "      <td>47.849998</td>\n",
       "      <td>46.770000</td>\n",
       "      <td>47.200001</td>\n",
       "      <td>39.344219</td>\n",
       "      <td>2929000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5935</th>\n",
       "      <td>2015-12-09</td>\n",
       "      <td>46.860001</td>\n",
       "      <td>47.990002</td>\n",
       "      <td>46.599998</td>\n",
       "      <td>47.130001</td>\n",
       "      <td>39.285873</td>\n",
       "      <td>2547600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5936</th>\n",
       "      <td>2015-12-10</td>\n",
       "      <td>47.450001</td>\n",
       "      <td>48.669998</td>\n",
       "      <td>47.310001</td>\n",
       "      <td>48.180000</td>\n",
       "      <td>40.161110</td>\n",
       "      <td>4576000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5937</th>\n",
       "      <td>2015-12-11</td>\n",
       "      <td>47.709999</td>\n",
       "      <td>48.049999</td>\n",
       "      <td>46.090000</td>\n",
       "      <td>46.240002</td>\n",
       "      <td>38.543999</td>\n",
       "      <td>4618500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6878</th>\n",
       "      <td>2019-09-10</td>\n",
       "      <td>50.900002</td>\n",
       "      <td>51.459999</td>\n",
       "      <td>49.910000</td>\n",
       "      <td>51.099998</td>\n",
       "      <td>51.099998</td>\n",
       "      <td>4713200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6879</th>\n",
       "      <td>2019-09-11</td>\n",
       "      <td>51.470001</td>\n",
       "      <td>52.770000</td>\n",
       "      <td>50.230000</td>\n",
       "      <td>52.330002</td>\n",
       "      <td>52.330002</td>\n",
       "      <td>3932600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6880</th>\n",
       "      <td>2019-09-12</td>\n",
       "      <td>51.970001</td>\n",
       "      <td>53.200001</td>\n",
       "      <td>50.910000</td>\n",
       "      <td>52.360001</td>\n",
       "      <td>52.360001</td>\n",
       "      <td>4118700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6881</th>\n",
       "      <td>2019-09-13</td>\n",
       "      <td>53.200001</td>\n",
       "      <td>54.200001</td>\n",
       "      <td>52.250000</td>\n",
       "      <td>52.700001</td>\n",
       "      <td>52.700001</td>\n",
       "      <td>2927500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6882</th>\n",
       "      <td>2019-09-16</td>\n",
       "      <td>52.110001</td>\n",
       "      <td>53.220001</td>\n",
       "      <td>52.029999</td>\n",
       "      <td>53.130001</td>\n",
       "      <td>53.130001</td>\n",
       "      <td>2867300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6883</th>\n",
       "      <td>2019-09-17</td>\n",
       "      <td>52.119999</td>\n",
       "      <td>52.150002</td>\n",
       "      <td>50.419998</td>\n",
       "      <td>50.810001</td>\n",
       "      <td>50.810001</td>\n",
       "      <td>4494700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6884</th>\n",
       "      <td>2019-09-18</td>\n",
       "      <td>50.970001</td>\n",
       "      <td>51.240002</td>\n",
       "      <td>49.509998</td>\n",
       "      <td>50.090000</td>\n",
       "      <td>50.090000</td>\n",
       "      <td>2748600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6885</th>\n",
       "      <td>2019-09-19</td>\n",
       "      <td>50.320000</td>\n",
       "      <td>50.529999</td>\n",
       "      <td>48.770000</td>\n",
       "      <td>48.799999</td>\n",
       "      <td>48.799999</td>\n",
       "      <td>2837700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6886</th>\n",
       "      <td>2019-09-20</td>\n",
       "      <td>49.009998</td>\n",
       "      <td>50.230000</td>\n",
       "      <td>48.820000</td>\n",
       "      <td>49.020000</td>\n",
       "      <td>49.020000</td>\n",
       "      <td>3492400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6887</th>\n",
       "      <td>2019-09-23</td>\n",
       "      <td>48.709999</td>\n",
       "      <td>49.250000</td>\n",
       "      <td>48.200001</td>\n",
       "      <td>49.029999</td>\n",
       "      <td>49.029999</td>\n",
       "      <td>2263200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6888</th>\n",
       "      <td>2019-09-24</td>\n",
       "      <td>49.709999</td>\n",
       "      <td>50.189999</td>\n",
       "      <td>48.560001</td>\n",
       "      <td>49.180000</td>\n",
       "      <td>49.180000</td>\n",
       "      <td>2350200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6889</th>\n",
       "      <td>2019-09-25</td>\n",
       "      <td>49.180000</td>\n",
       "      <td>50.180000</td>\n",
       "      <td>49.090000</td>\n",
       "      <td>49.779999</td>\n",
       "      <td>49.779999</td>\n",
       "      <td>1775900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6890</th>\n",
       "      <td>2019-09-26</td>\n",
       "      <td>49.639999</td>\n",
       "      <td>49.880001</td>\n",
       "      <td>48.799999</td>\n",
       "      <td>49.169998</td>\n",
       "      <td>49.169998</td>\n",
       "      <td>1749500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6891</th>\n",
       "      <td>2019-09-27</td>\n",
       "      <td>49.430000</td>\n",
       "      <td>50.070000</td>\n",
       "      <td>49.220001</td>\n",
       "      <td>49.639999</td>\n",
       "      <td>49.639999</td>\n",
       "      <td>1986100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6892</th>\n",
       "      <td>2019-09-30</td>\n",
       "      <td>49.869999</td>\n",
       "      <td>50.450001</td>\n",
       "      <td>49.160000</td>\n",
       "      <td>49.660000</td>\n",
       "      <td>49.660000</td>\n",
       "      <td>2250500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6893</th>\n",
       "      <td>2019-10-01</td>\n",
       "      <td>50.090000</td>\n",
       "      <td>50.540001</td>\n",
       "      <td>48.970001</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>49.000000</td>\n",
       "      <td>3171800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6894</th>\n",
       "      <td>2019-10-02</td>\n",
       "      <td>48.610001</td>\n",
       "      <td>48.680000</td>\n",
       "      <td>45.820000</td>\n",
       "      <td>46.180000</td>\n",
       "      <td>46.180000</td>\n",
       "      <td>5344300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6895</th>\n",
       "      <td>2019-10-03</td>\n",
       "      <td>45.939999</td>\n",
       "      <td>46.639999</td>\n",
       "      <td>44.669998</td>\n",
       "      <td>46.570000</td>\n",
       "      <td>46.570000</td>\n",
       "      <td>4033100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6896</th>\n",
       "      <td>2019-10-04</td>\n",
       "      <td>46.680000</td>\n",
       "      <td>47.230000</td>\n",
       "      <td>46.340000</td>\n",
       "      <td>47.180000</td>\n",
       "      <td>47.180000</td>\n",
       "      <td>2490100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6897</th>\n",
       "      <td>2019-10-07</td>\n",
       "      <td>47.099998</td>\n",
       "      <td>48.930000</td>\n",
       "      <td>46.990002</td>\n",
       "      <td>48.360001</td>\n",
       "      <td>48.360001</td>\n",
       "      <td>3680100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6898</th>\n",
       "      <td>2019-10-08</td>\n",
       "      <td>47.630001</td>\n",
       "      <td>48.990002</td>\n",
       "      <td>46.700001</td>\n",
       "      <td>48.400002</td>\n",
       "      <td>48.400002</td>\n",
       "      <td>2922700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6899</th>\n",
       "      <td>2019-10-09</td>\n",
       "      <td>48.709999</td>\n",
       "      <td>50.180000</td>\n",
       "      <td>48.590000</td>\n",
       "      <td>49.410000</td>\n",
       "      <td>49.410000</td>\n",
       "      <td>3024900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6900</th>\n",
       "      <td>2019-10-10</td>\n",
       "      <td>49.500000</td>\n",
       "      <td>51.189999</td>\n",
       "      <td>49.380001</td>\n",
       "      <td>50.799999</td>\n",
       "      <td>50.799999</td>\n",
       "      <td>4441600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6901</th>\n",
       "      <td>2019-10-11</td>\n",
       "      <td>51.520000</td>\n",
       "      <td>52.130001</td>\n",
       "      <td>50.650002</td>\n",
       "      <td>51.459999</td>\n",
       "      <td>51.459999</td>\n",
       "      <td>3080300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6902</th>\n",
       "      <td>2019-10-14</td>\n",
       "      <td>51.430000</td>\n",
       "      <td>51.430000</td>\n",
       "      <td>50.259998</td>\n",
       "      <td>50.730000</td>\n",
       "      <td>50.730000</td>\n",
       "      <td>2311600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6903</th>\n",
       "      <td>2019-10-15</td>\n",
       "      <td>50.939999</td>\n",
       "      <td>52.080002</td>\n",
       "      <td>50.549999</td>\n",
       "      <td>51.450001</td>\n",
       "      <td>51.450001</td>\n",
       "      <td>2219300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6904</th>\n",
       "      <td>2019-10-16</td>\n",
       "      <td>51.070000</td>\n",
       "      <td>52.070000</td>\n",
       "      <td>50.750000</td>\n",
       "      <td>51.020000</td>\n",
       "      <td>51.020000</td>\n",
       "      <td>2180300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6905</th>\n",
       "      <td>2019-10-17</td>\n",
       "      <td>51.340000</td>\n",
       "      <td>51.910000</td>\n",
       "      <td>50.730000</td>\n",
       "      <td>51.060001</td>\n",
       "      <td>51.060001</td>\n",
       "      <td>2534400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6906</th>\n",
       "      <td>2019-10-18</td>\n",
       "      <td>49.880001</td>\n",
       "      <td>51.369999</td>\n",
       "      <td>49.799999</td>\n",
       "      <td>50.599998</td>\n",
       "      <td>50.599998</td>\n",
       "      <td>2655900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6907</th>\n",
       "      <td>2019-10-21</td>\n",
       "      <td>51.230000</td>\n",
       "      <td>52.070000</td>\n",
       "      <td>50.849998</td>\n",
       "      <td>51.230000</td>\n",
       "      <td>51.230000</td>\n",
       "      <td>2221500</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            Date       Open       High        Low      Close  Adj Close  \\\n",
       "5908  2015-10-30  44.779999  46.619999  44.750000  46.119999  38.084156   \n",
       "5909  2015-11-02  46.139999  46.779999  44.520000  46.709999  38.571362   \n",
       "5910  2015-11-03  46.720001  48.160000  46.720001  47.369999  39.116364   \n",
       "5911  2015-11-04  47.439999  47.590000  45.820000  46.209999  38.158474   \n",
       "5912  2015-11-05  46.320000  46.759998  45.849998  46.660000  38.530067   \n",
       "5913  2015-11-06  46.540001  47.200001  46.200001  46.570000  38.455746   \n",
       "5914  2015-11-09  46.009998  46.200001  43.660000  43.980000  36.317032   \n",
       "5915  2015-11-10  43.630001  45.750000  43.509998  45.599998  37.654758   \n",
       "5916  2015-11-11  44.000000  44.040001  42.189999  43.160000  35.639900   \n",
       "5917  2015-11-12  45.430000  47.240002  45.000000  45.790001  37.811661   \n",
       "5918  2015-11-13  44.669998  44.669998  41.860001  42.849998  35.383904   \n",
       "5919  2015-11-16  42.689999  43.990002  42.570000  43.939999  36.284000   \n",
       "5920  2015-11-17  44.299999  45.169998  43.450001  44.049999  36.374836   \n",
       "5921  2015-11-18  44.279999  45.310001  43.720001  45.150002  37.283173   \n",
       "5922  2015-11-19  45.389999  45.770000  44.990002  45.180000  37.307941   \n",
       "5923  2015-11-20  45.590000  47.090000  45.580002  47.040001  38.843853   \n",
       "5924  2015-11-23  47.310001  47.970001  47.200001  47.639999  39.339314   \n",
       "5925  2015-11-24  47.349998  49.060001  47.320000  48.529999  40.074249   \n",
       "5926  2015-11-25  48.470001  48.930000  48.150002  48.500000  40.049469   \n",
       "5927  2015-11-27  48.820000  49.000000  47.660000  48.070000  39.694397   \n",
       "5928  2015-11-30  48.220001  48.439999  46.570000  47.130001  38.918179   \n",
       "5929  2015-12-01  47.270000  47.910000  46.950001  47.220001  38.992504   \n",
       "5930  2015-12-02  47.419998  47.720001  46.180000  46.419998  38.331894   \n",
       "5931  2015-12-03  46.619999  47.419998  45.910000  47.389999  39.132877   \n",
       "5932  2015-12-04  47.180000  48.119999  46.860001  48.080002  39.702652   \n",
       "5933  2015-12-07  47.360001  47.770000  46.650002  47.450001  39.552608   \n",
       "5934  2015-12-08  46.900002  47.849998  46.770000  47.200001  39.344219   \n",
       "5935  2015-12-09  46.860001  47.990002  46.599998  47.130001  39.285873   \n",
       "5936  2015-12-10  47.450001  48.669998  47.310001  48.180000  40.161110   \n",
       "5937  2015-12-11  47.709999  48.049999  46.090000  46.240002  38.543999   \n",
       "...          ...        ...        ...        ...        ...        ...   \n",
       "6878  2019-09-10  50.900002  51.459999  49.910000  51.099998  51.099998   \n",
       "6879  2019-09-11  51.470001  52.770000  50.230000  52.330002  52.330002   \n",
       "6880  2019-09-12  51.970001  53.200001  50.910000  52.360001  52.360001   \n",
       "6881  2019-09-13  53.200001  54.200001  52.250000  52.700001  52.700001   \n",
       "6882  2019-09-16  52.110001  53.220001  52.029999  53.130001  53.130001   \n",
       "6883  2019-09-17  52.119999  52.150002  50.419998  50.810001  50.810001   \n",
       "6884  2019-09-18  50.970001  51.240002  49.509998  50.090000  50.090000   \n",
       "6885  2019-09-19  50.320000  50.529999  48.770000  48.799999  48.799999   \n",
       "6886  2019-09-20  49.009998  50.230000  48.820000  49.020000  49.020000   \n",
       "6887  2019-09-23  48.709999  49.250000  48.200001  49.029999  49.029999   \n",
       "6888  2019-09-24  49.709999  50.189999  48.560001  49.180000  49.180000   \n",
       "6889  2019-09-25  49.180000  50.180000  49.090000  49.779999  49.779999   \n",
       "6890  2019-09-26  49.639999  49.880001  48.799999  49.169998  49.169998   \n",
       "6891  2019-09-27  49.430000  50.070000  49.220001  49.639999  49.639999   \n",
       "6892  2019-09-30  49.869999  50.450001  49.160000  49.660000  49.660000   \n",
       "6893  2019-10-01  50.090000  50.540001  48.970001  49.000000  49.000000   \n",
       "6894  2019-10-02  48.610001  48.680000  45.820000  46.180000  46.180000   \n",
       "6895  2019-10-03  45.939999  46.639999  44.669998  46.570000  46.570000   \n",
       "6896  2019-10-04  46.680000  47.230000  46.340000  47.180000  47.180000   \n",
       "6897  2019-10-07  47.099998  48.930000  46.990002  48.360001  48.360001   \n",
       "6898  2019-10-08  47.630001  48.990002  46.700001  48.400002  48.400002   \n",
       "6899  2019-10-09  48.709999  50.180000  48.590000  49.410000  49.410000   \n",
       "6900  2019-10-10  49.500000  51.189999  49.380001  50.799999  50.799999   \n",
       "6901  2019-10-11  51.520000  52.130001  50.650002  51.459999  51.459999   \n",
       "6902  2019-10-14  51.430000  51.430000  50.259998  50.730000  50.730000   \n",
       "6903  2019-10-15  50.939999  52.080002  50.549999  51.450001  51.450001   \n",
       "6904  2019-10-16  51.070000  52.070000  50.750000  51.020000  51.020000   \n",
       "6905  2019-10-17  51.340000  51.910000  50.730000  51.060001  51.060001   \n",
       "6906  2019-10-18  49.880001  51.369999  49.799999  50.599998  50.599998   \n",
       "6907  2019-10-21  51.230000  52.070000  50.849998  51.230000  51.230000   \n",
       "\n",
       "        Volume  \n",
       "5908   3353700  \n",
       "5909   3946000  \n",
       "5910   3273800  \n",
       "5911   2590800  \n",
       "5912   2924500  \n",
       "5913   4085500  \n",
       "5914   6119500  \n",
       "5915   6824800  \n",
       "5916   9828300  \n",
       "5917  19188600  \n",
       "5918   9982600  \n",
       "5919   4144200  \n",
       "5920   4433900  \n",
       "5921   4506300  \n",
       "5922   2767800  \n",
       "5923   5070800  \n",
       "5924   3518700  \n",
       "5925   3262600  \n",
       "5926   2688400  \n",
       "5927   1315800  \n",
       "5928   4785800  \n",
       "5929   3636700  \n",
       "5930   3128800  \n",
       "5931   5760200  \n",
       "5932   4279000  \n",
       "5933   4103800  \n",
       "5934   2929000  \n",
       "5935   2547600  \n",
       "5936   4576000  \n",
       "5937   4618500  \n",
       "...        ...  \n",
       "6878   4713200  \n",
       "6879   3932600  \n",
       "6880   4118700  \n",
       "6881   2927500  \n",
       "6882   2867300  \n",
       "6883   4494700  \n",
       "6884   2748600  \n",
       "6885   2837700  \n",
       "6886   3492400  \n",
       "6887   2263200  \n",
       "6888   2350200  \n",
       "6889   1775900  \n",
       "6890   1749500  \n",
       "6891   1986100  \n",
       "6892   2250500  \n",
       "6893   3171800  \n",
       "6894   5344300  \n",
       "6895   4033100  \n",
       "6896   2490100  \n",
       "6897   3680100  \n",
       "6898   2922700  \n",
       "6899   3024900  \n",
       "6900   4441600  \n",
       "6901   3080300  \n",
       "6902   2311600  \n",
       "6903   2219300  \n",
       "6904   2180300  \n",
       "6905   2534400  \n",
       "6906   2655900  \n",
       "6907   2221500  \n",
       "\n",
       "[1000 rows x 7 columns]"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Checking the dataframe\n",
    "df = grab_csv()\n",
    "df.tail(1000)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exporting the newly created DF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"stock_df.pkl\", \"wb\") as fp:\n",
    "    pickle.dump(df, fp)"
   ]
  },
  {
   "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
}