/src/Web_Scraping.ipynb

{
 "metadata": {
  "name": "Web_Scraping"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Grab data from a webpage and extract desired information\n",
      "-----"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from urllib import urlopen\n",
      "from BeautifulSoup import BeautifulStoneSoup"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Copy all content from the provided web page\n",
      "LLY_RSS = urlopen( \"http://apps.shareholder.com/rss/rss.aspx?channels=2886&companyid=LLY\" ).read()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Use BeautifulStoneSoup to parse webpage elements using XML tags\n",
      "soup = BeautifulStoneSoup(LLY_RSS)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Read the contents of each of the XML tags into a Python list\n",
      "title = soup.findAll('title')\n",
      "link = soup.findAll('link')\n",
      "pubDate = soup.findAll('pubDate')\n",
      "description = soup.findAll('description')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Print title and link for each news story on Lilly RSS feed\n",
      "for i in range(10):\n",
      "    print title[i]\n",
      "    print link[i]\n",
      "    print \"\\n\"\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Remove XML tags for prettier printing\n",
      "for i in range(10):\n",
      "    print \"Title:\", str(title[i]).strip('<title>').strip('</title>')\n",
      "    print \"Link: \" + str(link[i]).strip('<link>').strip('</link>')\n",
      "    print \"\\n\""
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}