{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "621c09fe",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:32.071268Z",
     "start_time": "2024-03-08T19:16:31.275321Z"
    }
   },
   "outputs": [],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "import pandas as pd\n",
    "\n",
    "c = 0\n",
    "\n",
    "df = 0\n",
    "\n",
    "# Read HTML content from the file\n",
    "with open(\"index.html\", \"r\", encoding=\"utf-8\") as file:\n",
    "    html_content = file.read()\n",
    "\n",
    "# Parse the HTML content\n",
    "soup = BeautifulSoup(html_content, \"html.parser\")\n",
    "\n",
    "# Find the table\n",
    "table = soup.find(\"table\")\n",
    "\n",
    "# Extract table data\n",
    "if table:\n",
    "    rows = table.find_all(\"tr\")\n",
    "    data = []\n",
    "    for row in rows:\n",
    "        columns = row.find_all(\"td\")\n",
    "        if columns:  # Ensure it's not a header row or empty row\n",
    "            row_data = [column.text.strip() for column in columns]\n",
    "            data.append(row_data)\n",
    "        c += 1\n",
    "    # Create DataFrame\n",
    "    df = pd.DataFrame(data)\n",
    "    \n",
    "    # Extract first part and last word from the first column\n",
    "    df['Name'] = df[0].str.split().str[:-1].str.join(\" \")\n",
    "    df['Ticker'] = df[0].str.split().str[-1]\n",
    "    df[['Name', 'Ticker']].to_csv(\"CompanyList.csv\")\n",
    "else:\n",
    "    print(\"Table not found in the HTML content.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "38efd2c9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:45.594430Z",
     "start_time": "2024-03-08T19:16:45.591931Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2063\n"
     ]
    }
   ],
   "source": [
    "print(c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6c185203",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:46.502190Z",
     "start_time": "2024-03-08T19:16:46.489733Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "                                0             1           2            3  \\\ncount                        2062          2062        2062         2062   \nunique                       2062          2044        2060         2056   \ntop     20 Microns Ltd. 20MICRONS  ₹1.14 -4.16%  ₹8.8/₹3.79  ₹128.05 Crs   \nfreq                            1             4           2            2   \n\n                      4                 Name     Ticker  \ncount              2062                 2062       2062  \nunique              125                 2061       2062  \ntop     Pharmaceuticals  Gallantt Ispat Ltd.  20MICRONS  \nfreq                105                    2          1  ",
      "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>0</th>\n      <th>1</th>\n      <th>2</th>\n      <th>3</th>\n      <th>4</th>\n      <th>Name</th>\n      <th>Ticker</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>2062</td>\n      <td>2062</td>\n      <td>2062</td>\n      <td>2062</td>\n      <td>2062</td>\n      <td>2062</td>\n      <td>2062</td>\n    </tr>\n    <tr>\n      <th>unique</th>\n      <td>2062</td>\n      <td>2044</td>\n      <td>2060</td>\n      <td>2056</td>\n      <td>125</td>\n      <td>2061</td>\n      <td>2062</td>\n    </tr>\n    <tr>\n      <th>top</th>\n      <td>20 Microns Ltd. 20MICRONS</td>\n      <td>₹1.14 -4.16%</td>\n      <td>₹8.8/₹3.79</td>\n      <td>₹128.05 Crs</td>\n      <td>Pharmaceuticals</td>\n      <td>Gallantt Ispat Ltd.</td>\n      <td>20MICRONS</td>\n    </tr>\n    <tr>\n      <th>freq</th>\n      <td>1</td>\n      <td>4</td>\n      <td>2</td>\n      <td>2</td>\n      <td>105</td>\n      <td>2</td>\n      <td>1</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ebfb97f3",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:48.278807Z",
     "start_time": "2024-03-08T19:16:48.273680Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "2062"
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "70727a81",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:49.269674Z",
     "start_time": "2024-03-08T19:16:49.267266Z"
    }
   },
   "outputs": [],
   "source": [
    "duplicates = df[df.duplicated(subset='Name', keep=False)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "75f68012",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:50.191351Z",
     "start_time": "2024-03-08T19:16:50.186194Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "                                                     0               1  \\\n610  Gallantt Ispat Ltd.\\n                         ...   ₹64.15 -0.77%   \n611  Gallantt Ispat Ltd.\\n                         ...  ₹216.94 +1.33%   \n\n                 2             3             4                 Name     Ticker  \n610     ₹76/₹44.64  ₹1807.11 Crs  Iron & Steel  Gallantt Ispat Ltd.  GALLISPAT  \n611  ₹236.4/₹49.54   ₹5235.8 Crs  Iron & Steel  Gallantt Ispat Ltd.   GALLANTT  ",
      "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>0</th>\n      <th>1</th>\n      <th>2</th>\n      <th>3</th>\n      <th>4</th>\n      <th>Name</th>\n      <th>Ticker</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>610</th>\n      <td>Gallantt Ispat Ltd.\\n                         ...</td>\n      <td>₹64.15 -0.77%</td>\n      <td>₹76/₹44.64</td>\n      <td>₹1807.11 Crs</td>\n      <td>Iron &amp; Steel</td>\n      <td>Gallantt Ispat Ltd.</td>\n      <td>GALLISPAT</td>\n    </tr>\n    <tr>\n      <th>611</th>\n      <td>Gallantt Ispat Ltd.\\n                         ...</td>\n      <td>₹216.94 +1.33%</td>\n      <td>₹236.4/₹49.54</td>\n      <td>₹5235.8 Crs</td>\n      <td>Iron &amp; Steel</td>\n      <td>Gallantt Ispat Ltd.</td>\n      <td>GALLANTT</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "duplicates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a0f8f58d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-08T19:16:59.440812Z",
     "start_time": "2024-03-08T19:16:59.430280Z"
    }
   },
   "outputs": [],
   "source": [
    "df.to_csv(\"CompanyList.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   },
   "id": "e9274e3c3011e6fc"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}