Facebook word cloud

facebook_cloud.ipynb

{
 "cells": [
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "<h1>Facebook tag cloud with BeautifulSoup</h1>"
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "These few lines will list all the words in your facebook wall. From facebook you have to download your data."
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "from bs4 import BeautifulSoup\nfrom collections import Counter",
   "execution_count": null,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": true,
    "trusted": true
   },
   "cell_type": "code",
   "source": "filename = \"/home/turra/Scaricati/html/wall.htm\"",
   "execution_count": null,
   "outputs": []
  },
  {
   "metadata": {
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "comments = BeautifulSoup(open(filename)).find_all('div', {\"class\" : \"comment\"})\ncomments = ' '.join(set([div.text for div in comments]))\n\nto_remove = ('di', 'no', 'all', 'proprio', 'Un', 'b', 'from', 'che', 'd', 'v', 'Le', 'La', 'a', u'è', 'And', 'non', 'il', 'la', 'un', 'e', 'in', 'per', 'the', 'Non', 'dell', '-', u'–', 'get', 'una', u'più', 'sta', 'Per', 'ha', 'sono', 'i', 'le', 'Ruggero', 'Turra', 'mi', 'is', 'su', 'si', 'ci', 'to', 'al', 'ma', 'del', 'da', 'se', 'of', 'con', 'fa', 'gli', 'o', 'anche', 'and', 'ho', 'lo', 'dei', 'questo', 'della', 'for', 'questa', 'po\\'', 'come', u'perché', 'uno', 'mai', 'ti', 'Mi', 'va', 'about', u'c\\'è', 'mia', 'hanno', 'cosa', 'at', 'Tanti', 'ne', 'Il', 'ce', 'ad', 'by', 'nel', 'it', 'Ma', 'not', 'this', 'that', 'sul', 'La', 'E', 's', 'c', 'l', 't', 'or', 'tra', 'A', 'era', 'on', 'as', u'può')\nfor tr in to_remove:\n    comments = comments.replace(\" %s \" % tr, \" \")\ncomments = comments.replace(u\"'\", ' ').replace(',', ' ').replace(u\"’\", \" \").replace(\"?\", \" \").replace(\"!\", \" \").replace('\"', \" \").replace('.', ' ')\ncounter = Counter(comments.split())",
   "execution_count": null,
   "outputs": []
  },
  {
   "metadata": {
    "scrolled": false,
    "collapsed": false,
    "trusted": true
   },
   "cell_type": "code",
   "source": "for c in counter.most_common():\n    if c[0] in to_remove: continue\n    print \"%s: %d\" % c",
   "execution_count": null,
   "outputs": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "name": "python2",
   "display_name": "Python 2",
   "language": "python"
  },
  "language_info": {
   "mimetype": "text/x-python",
   "nbconvert_exporter": "python",
   "name": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.5",
   "file_extension": ".py",
   "codemirror_mode": {
    "version": 2,
    "name": "ipython"
   }
  },
  "gist_id": "fa16452e8c12540e3663"
 },
 "nbformat": 4,
 "nbformat_minor": 0
}