scrape_it.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>retailer</th>\n",
       "      <th>units_sold</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [date, retailer, units_sold]\n",
       "Index: []"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import time\n",
    "today = time.strftime(\"%Y-%m-%d %H:%M\")\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "%pylab inline\n",
    "df = pd.DataFrame({'retailer' : [], 'date' : [], 'units_sold': []})\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'bs4.BeautifulSoup'>\n"
     ]
    }
   ],
   "source": [
    "from bs4 import BeautifulSoup\n",
    "import urllib\n",
    "r = urllib.urlopen('http://www.readymaderc.com/store/index.php?main_page=product_info&cPath=505_778_779&products_id=5763').read()\n",
    "soup = BeautifulSoup(r)\n",
    "print type(soup)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe src=http://www.readymaderc.com/store/index.php?main_page=product_info&cPath=505_778_779&products_id=5763 width=700 height=500></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.display import HTML\n",
    "HTML('<iframe src=http://www.readymaderc.com/store/index.php?main_page=product_info&cPath=505_778_779&products_id=5763 width=700 height=500></iframe>')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>retailer</th>\n",
       "      <th>units_sold</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-08-26 10:45</td>\n",
       "      <td>readymaderc</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               date     retailer units_sold\n",
       "0  2016-08-26 10:45  readymaderc         96"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "unit = soup.find_all(\"ul\", id=\"productDetailsList\")[0]\n",
    "\n",
    "#letters = soup.find_all(\"div\", class_=\"ec_statements\")\n",
    "#soup.findAll(\"ul\" )\n",
    "rmrc = unit.getText().split(\"\\n\")[-2].split()[0]\n",
    "rmrc_df = pd.DataFrame({'retailer' : ['readymaderc'], 'date' : [today], 'units_sold': [rmrc]})\n",
    "rmrc_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>retailer</th>\n",
       "      <th>units_sold</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016-08-26 10:45</td>\n",
       "      <td>readymaderc</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016-08-26 10:45</td>\n",
       "      <td>readymaderc</td>\n",
       "      <td>96</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               date     retailer units_sold\n",
       "0  2016-08-26 10:45  readymaderc         96\n",
       "1  2016-08-26 10:45  readymaderc         96"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#appending it to master df\n",
    "df = df.append(rmrc_df, ignore_index=True)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}