{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scrape data from aon2e and generate csvs to import in to sqlite"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Dependencies\n",
    "import pandas as pd\n",
    "from bs4 import BeautifulSoup as bs\n",
    "import os\n",
    "from splinter import Browser\n",
    "\n",
    "# Setting up Selenium\n",
    "chrome_driver = os.path.join('..', 'chromedriver.exe')\n",
    "executable_path = {'executable_path': chrome_driver}\n",
    "browser = Browser('chrome', **executable_path, headless=False)\n",
    "\n",
    "# Pandas config\n",
    "pd.set_option('display.max_columns', None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# url that contains all the links\n",
    "url_weapon = 'https://2e.aonprd.com/Weapons.aspx?ID='\n",
    "\n",
    "# Number of weapons\n",
    "number_of_weapons = 83\n",
    "\n",
    "# Empty lists to store the scraped values\n",
    "name_list = []\n",
    "description_list = []\n",
    "\n",
    "print(f'Beginning Data Retrieval')\n",
    "print(f'------------------------')\n",
    "\n",
    "# Loop from 1 to the value in weapon_number\n",
    "for weapon in range(1, number_of_weapons+1):\n",
    "    \n",
    "    url = url_weapon + str(weapon)\n",
    "    browser.visit(url)\n",
    "    html = browser.html\n",
    "    soup = bs(html, 'html.parser')\n",
    "\n",
    "    # Select only the content section\n",
    "    content = soup.find(id='ctl00_MainContent_DetailedOutput')\n",
    "\n",
    "    try:\n",
    "        # Store the name and description\n",
    "        name = content.find('a').text.strip()\n",
    "        \n",
    "    except:\n",
    "        name = f'weapon: {weapon}'\n",
    "\n",
    "    try:\n",
    "        description = content.find('hr').next.text.strip()\n",
    "        \n",
    "    except:\n",
    "        description = content.find('hr').next.strip()\n",
    "        \n",
    "    print(f'Processing Weapon {weapon} of {number_of_weapons} | {name}')\n",
    "\n",
    "    # Append values to our empty lists\n",
    "    name_list.append(name)      \n",
    "    description_list.append(description)\n",
    "\n",
    "print(f'------------------------')\n",
    "print(f'Data Retrieval Complete')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Directory of csv files which are taken from https://2e.aonprd.com/Weapons.aspx\n",
    "melee = pd.read_csv('melee.csv')\n",
    "ranged = pd.read_csv('ranged.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = {'Name': name_list, 'description': description_list}\n",
    "scrape = pd.DataFrame(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "melee = melee.merge(scrape, how='left', on='Name')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ranged = ranged.merge(scrape, how='left', on='Name')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "melee.to_csv('melee.csv')\n",
    "ranged.to_csv('ranged.csv')"
   ]
  },
  {
   "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}