{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exercises\n",
    "#### String Manipulation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import requests\n",
    "from bs4 import BeautifulSoup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "page = requests.get(\"http://www.vatican.va/archive/bible/genesis/documents/bible_genesis_en.html\")\n",
    "soup = BeautifulSoup(page.content, 'html.parser')\n",
    "\n",
    "for script in soup([\"script\", \"style\"]):\n",
    "    script.decompose()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "genesis = soup.get_text()\n",
    "genesis = re.sub(r'[\\n]+','\\n', genesis)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "The Book of Genesis\n",
      "THE BOOK\n",
      "  OF GENESIS\n",
      "1, 2,\n",
      "3, 4, 5,\n",
      "6, 7, 8,\n",
      "9, 10, 11,\n",
      "12, 13, 14,\n",
      "15, 16, 17,\n",
      "18, 19, 20,\n",
      "21, 22, 23,\n",
      "24, 25, 26,\n",
      "27, 28, 29,\n",
      "30, 31, 32,\n",
      "33, 34, 35,\n",
      "36, 37, 38,\n",
      "39, 40, 41,\n",
      "42, 43, 44,\n",
      "45, 46, 47,\n",
      "48, 49, 50 \n",
      "Chapter 1\n",
      "[1:1] In the beginning when God created\n"
     ]
    }
   ],
   "source": [
    "print(genesis[0:300])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Questions:\n",
    "\n",
    "\n",
    "#### 1. How many times the word 'God' appear (as an isolated word)?  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 2. What are the 5 most common words?    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 3. What are the words that appear only once ([hapaxes](https://en.wikipedia.org/wiki/Hapax_legomenon))?  "
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}