{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c8b3ccce",
   "metadata": {},
   "source": [
    "# [Building a dataset of Python versions with regular expressions](https://www.dataschool.io/web-scraping-with-regex/)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "327aa069",
   "metadata": {},
   "source": [
    "[Python Documentation by Version](https://www.python.org/doc/versions/)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "068029f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "07c1652b",
   "metadata": {},
   "outputs": [],
   "source": [
    "r = requests.get('https://www.python.org/doc/versions/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4872696c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<h1>Python Documentation by Version</h1>\n",
      "<p>Some previous versions of the documentation remain available\n",
      "online.  Use the list below to select a version to view.</p>\n",
      "<p>For unreleased (in development) documentation, see\n",
      "<a class=\"reference internal\" href=\"#in-development-versions\">In Development Versions</a>.</p>\n",
      "<ul class=\"simple\">\n",
      "<li><a class=\"reference external\" href=\"https://docs.python.org/release/3.11.2/\">Python 3.11.2</a>, documentation released on 8 February 2023.</li>\n",
      "<li><a class=\"reference external\" href=\"https://docs.python.org/release/3.11.1/\">Python 3.11.1</a>, documentation released on 6 December 2022.</li>\n",
      "<li><a class=\"reference external\" href=\"https://docs.python.org/release/3.11.0/\">Python 3.11.0</a>, documentation released on 24 October 2022.</li>\n"
     ]
    }
   ],
   "source": [
    "print(r.text[21646:22424])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aaddac57",
   "metadata": {},
   "source": [
    "## Extracting the dates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "bf247f46",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a8d1b84f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['8 February 2023', '6 December 2022', '24 October 2022']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dates = re.findall(r'\\d+ \\w+ \\d{4}', r.text)\n",
    "dates[0:3]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1841112d",
   "metadata": {},
   "source": [
    "## Extracting the version numbers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "324b89f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['3.11.2', '3.11.1', '3.11.0']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "versions = re.findall(r'Python (\\d.+?)<', r.text)\n",
    "versions[0:3]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4a25c479",
   "metadata": {},
   "source": [
    "## Creating the dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fe1231f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "6e291c35",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Version</th>\n",
       "      <th>Date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.11.2</td>\n",
       "      <td>8 February 2023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.11.1</td>\n",
       "      <td>6 December 2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.11.0</td>\n",
       "      <td>24 October 2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3.10.10</td>\n",
       "      <td>8 February 2023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.10.9</td>\n",
       "      <td>6 December 2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>184</th>\n",
       "      <td>1.5.2</td>\n",
       "      <td>30 April 1999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>185</th>\n",
       "      <td>1.5.1p1</td>\n",
       "      <td>6 August 1998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>186</th>\n",
       "      <td>1.5.1</td>\n",
       "      <td>14 April 1998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>187</th>\n",
       "      <td>1.5</td>\n",
       "      <td>17 February 1998</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>188</th>\n",
       "      <td>1.4</td>\n",
       "      <td>25 October 1996</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>189 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Version              Date\n",
       "0     3.11.2   8 February 2023\n",
       "1     3.11.1   6 December 2022\n",
       "2     3.11.0   24 October 2022\n",
       "3    3.10.10   8 February 2023\n",
       "4     3.10.9   6 December 2022\n",
       "..       ...               ...\n",
       "184    1.5.2     30 April 1999\n",
       "185  1.5.1p1     6 August 1998\n",
       "186    1.5.1     14 April 1998\n",
       "187      1.5  17 February 1998\n",
       "188      1.4   25 October 1996\n",
       "\n",
       "[189 rows x 2 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(zip(versions, dates), columns=['Version', 'Date'])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}