SGU SciFi Scraper and Analysis

gistfile1.txt

{
 "metadata": {
  "name": "",
  "signature": "sha256:5ebf3464516b6c384c231f91063b0c33b4e7a9311d5657d3c8e8fdb387ce1acd"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "\"\"\" Get 'Science or Fiction' data from The Skeptics' Guide to the Universe website. \"\"\"\n",
      "import urllib2\n",
      "import contextlib\n",
      "from time import sleep\n",
      "\n",
      "from bs4 import BeautifulSoup\n",
      "\n",
      "# put data in dictionary, counts = {episode_num: fiction_num, ...}\n",
      "counts = {}\n",
      "\n",
      "# first episode with science or fiction info is episode 43.\n",
      "for i in range(43,481):\n",
      "    url = \"http://www.theskepticsguide.org/podcast/sgu/%s\" % i\n",
      "    \n",
      "    with contextlib.closing(urllib2.urlopen(url)) as response:\n",
      "        html = response.read()\n",
      "\n",
      "    soup = BeautifulSoup(html)\n",
      "    scifi_title = None\n",
      "    \n",
      "    # find the 'Science or Fiction' section of the page\n",
      "    for title in soup.find('div', {'class': 'podcast-detail'}).find_all('h3'):\n",
      "        if 'Science or Fiction' in title.text:\n",
      "            scifi_title = title\n",
      "\n",
      "    # not all episodes have a round of scifi\n",
      "    if scifi_title:\n",
      "        # get the list of news items from section\n",
      "        scifi_items = scifi_title.find_next('ul').select('li')\n",
      "\n",
      "        # only want to look at scifis with 3 items.\n",
      "        if len(scifi_items) == 3:\n",
      "            \n",
      "            for item in scifi_items:\n",
      "                split_item = item.select('span')\n",
      "\n",
      "                # get the item that is fiction and increment number\n",
      "                if split_item[1].text.strip().lower() == 'fiction':\n",
      "                    item_number = split_item[0].text.split('#')[1].strip()\n",
      "                    \n",
      "                    try:\n",
      "                        item_number = int(item_number)\n",
      "                        counts[i] = item_number\n",
      "                    except ValueError:\n",
      "                        print \"ValueError with episode %s!\" % i\n",
      "                        continue\n",
      "\n",
      "    # be very gentle on the website\n",
      "    sleep(5)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "ValueError with episode 247!\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# count the number of times items 1, 2 and 3 were fiction.\n",
      "values = counts.values()\n",
      "n1 = values.count(1)\n",
      "n2 = values.count(2)\n",
      "n3 = values.count(3)\n",
      "\n",
      "# probability\n",
      "total = float(len(values))\n",
      "p1 = n1 / total\n",
      "p2 = n2 / total\n",
      "p3 = n3 / total\n",
      "\n",
      "print n1, n2, n3\n",
      "print p1, p2, p3"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "128 119 133\n",
        "0.336842105263 0.313157894737 0.35\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# make a little plot\n",
      "import matplotlib as mpl\n",
      "import matplotlib.pyplot as plt\n",
      "\n",
      "%matplotlib inline\n",
      "\n",
      "mpl.rcParams['savefig.dpi'] = 100 # make the graph display nicer\n",
      "\n",
      "ind = [0]\n",
      "\n",
      "plt.figure(figsize=(2.5,5))\n",
      "plot1 = plt.bar(ind, p1, 0.2, color='#66c2a5') # colors from http://colorbrewer2.org/\n",
      "plot2 = plt.bar(ind, p2, 0.2, color='#fc8d62', bottom=p1)\n",
      "plot3 = plt.bar(ind, p3, 0.2, color='#8da0cb', bottom=p1+p2)\n",
      "\n",
      "# remove x ticks\n",
      "plt.tick_params(axis='x',which='both',bottom='off',top='off',labelbottom='off')\n",
      "\n",
      "plt.ylabel('Distribution of Fiction')\n",
      "plt.legend((plot3, plot2, plot1), ('Item 3', 'Item 2', 'Item 1'))\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAQQAAAGlCAYAAAAcSIhBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSZIkSZIkSZIkSZIkSZIkSVI+/H/N6SzRNzAOlQAAAABJRU5ErkJggg==\n",
       "text": [
        "<matplotlib.figure.Figure at 0x7fcd44053a10>"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# yeah, that plot isn't useful at all\n",
      "\n",
      "# do a chi squared test to see if the differences are actually significant\n",
      "from scipy import stats\n",
      "\n",
      "observations = [n1, n2, n3]\n",
      "chisq, p = stats.chisquare(observations)\n",
      "\n",
      "print \"ChiSq: %s \\n    P: %s\" % (chisq, p)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "ChiSq: 0.794736842105 \n",
        "    P: 0.672086369247\n"
       ]
      }
     ],
     "prompt_number": 4
    }
   ],
   "metadata": {}
  }
 ]
}