scrap FIFA rating.ipynb

Untitled1.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = pd.read_html(\"http://www.championat.com/football/fifa/2013/12\", \n                  header=0, thousands=\" \")[0].rename(columns={'Unnamed: 3': 'team',\n                   'Очки': 'score'})[['team', 'score']]",
      "execution_count": 33,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df",
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 34,
          "data": {
            "text/plain": "                                team  score\n0                            Испания   1507\n1                           Германия   1318\n2                          Аргентина   1251\n3                           Колумбия   1200\n4                         Португалия   1172\n5                            Уругвай   1132\n6                             Италия   1120\n7                          Швейцария   1113\n8                         Нидерланды   1106\n9                           Бразилия   1102\n10                           Бельгия   1098\n11                            Греция   1055\n12                            Англия   1041\n13                               США   1019\n14                              Чили   1014\n15                          Хорватия    971\n16                       Кот-д'Ивуар    918\n17                           Украина    907\n18              Босния и Герцеговина    899\n19                           Франция    893\n20                           Мексика    892\n21                            Россия    870\n22                           Эквадор    852\n23                              Гана    849\n24                             Дания    831\n25                             Алжир    800\n26                            Швеция    793\n27                             Чехия    766\n28                          Словения    762\n29                            Сербия    752\n..                               ...    ...\n179                          Вануату     53\n180                         Монголия     49\n181                            Фиджи     47\n182                            Самоа     45\n183                    Гвинея-Биссау     42\n184                Багамские острова     40\n185                        Свазиленд     37\n186                       Монтсеррат     33\n187                       Мадагаскар     33\n188                         Камбоджа     28\n189                           Бруней     26\n190                            Тонга     26\n191                  Восточный Тимор     26\n192  Американские Виргинские острова     23\n193             Папуа - Новая Гвинея     21\n194                Каймановы острова     21\n195               Американское Самоа     18\n196    Британские Виргинские острова     18\n197                          Андорра     17\n198                Коморские острова     17\n199                          Эритрея     11\n200                      Южный Судан     10\n201                            Макао     10\n202                           Сомали      8\n203                          Джибути      6\n204                     Острова Кука      5\n205                          Ангилья      3\n206                            Бутан      0\n207                   Тёркс и Кайкос      0\n208                       Сан-Марино      0\n\n[209 rows x 2 columns]",
            "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>team</th>\n      <th>score</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>Испания</td>\n      <td>1507</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>Германия</td>\n      <td>1318</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>Аргентина</td>\n      <td>1251</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>Колумбия</td>\n      <td>1200</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>Португалия</td>\n      <td>1172</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>Уругвай</td>\n      <td>1132</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>Италия</td>\n      <td>1120</td>\n    </tr>\n    <tr>\n      <th>7</th>\n      <td>Швейцария</td>\n      <td>1113</td>\n    </tr>\n    <tr>\n      <th>8</th>\n      <td>Нидерланды</td>\n      <td>1106</td>\n    </tr>\n    <tr>\n      <th>9</th>\n      <td>Бразилия</td>\n      <td>1102</td>\n    </tr>\n    <tr>\n      <th>10</th>\n      <td>Бельгия</td>\n      <td>1098</td>\n    </tr>\n    <tr>\n      <th>11</th>\n      <td>Греция</td>\n      <td>1055</td>\n    </tr>\n    <tr>\n      <th>12</th>\n      <td>Англия</td>\n      <td>1041</td>\n    </tr>\n    <tr>\n      <th>13</th>\n      <td>США</td>\n      <td>1019</td>\n    </tr>\n    <tr>\n      <th>14</th>\n      <td>Чили</td>\n      <td>1014</td>\n    </tr>\n    <tr>\n      <th>15</th>\n      <td>Хорватия</td>\n      <td>971</td>\n    </tr>\n    <tr>\n      <th>16</th>\n      <td>Кот-д'Ивуар</td>\n      <td>918</td>\n    </tr>\n    <tr>\n      <th>17</th>\n      <td>Украина</td>\n      <td>907</td>\n    </tr>\n    <tr>\n      <th>18</th>\n      <td>Босния и Герцеговина</td>\n      <td>899</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>Франция</td>\n      <td>893</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>Мексика</td>\n      <td>892</td>\n    </tr>\n    <tr>\n      <th>21</th>\n      <td>Россия</td>\n      <td>870</td>\n    </tr>\n    <tr>\n      <th>22</th>\n      <td>Эквадор</td>\n      <td>852</td>\n    </tr>\n    <tr>\n      <th>23</th>\n      <td>Гана</td>\n      <td>849</td>\n    </tr>\n    <tr>\n      <th>24</th>\n      <td>Дания</td>\n      <td>831</td>\n    </tr>\n    <tr>\n      <th>25</th>\n      <td>Алжир</td>\n      <td>800</td>\n    </tr>\n    <tr>\n      <th>26</th>\n      <td>Швеция</td>\n      <td>793</td>\n    </tr>\n    <tr>\n      <th>27</th>\n      <td>Чехия</td>\n      <td>766</td>\n    </tr>\n    <tr>\n      <th>28</th>\n      <td>Словения</td>\n      <td>762</td>\n    </tr>\n    <tr>\n      <th>29</th>\n      <td>Сербия</td>\n      <td>752</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>179</th>\n      <td>Вануату</td>\n      <td>53</td>\n    </tr>\n    <tr>\n      <th>180</th>\n      <td>Монголия</td>\n      <td>49</td>\n    </tr>\n    <tr>\n      <th>181</th>\n      <td>Фиджи</td>\n      <td>47</td>\n    </tr>\n    <tr>\n      <th>182</th>\n      <td>Самоа</td>\n      <td>45</td>\n    </tr>\n    <tr>\n      <th>183</th>\n      <td>Гвинея-Биссау</td>\n      <td>42</td>\n    </tr>\n    <tr>\n      <th>184</th>\n      <td>Багамские острова</td>\n      <td>40</td>\n    </tr>\n    <tr>\n      <th>185</th>\n      <td>Свазиленд</td>\n      <td>37</td>\n    </tr>\n    <tr>\n      <th>186</th>\n      <td>Монтсеррат</td>\n      <td>33</td>\n    </tr>\n    <tr>\n      <th>187</th>\n      <td>Мадагаскар</td>\n      <td>33</td>\n    </tr>\n    <tr>\n      <th>188</th>\n      <td>Камбоджа</td>\n      <td>28</td>\n    </tr>\n    <tr>\n      <th>189</th>\n      <td>Бруней</td>\n      <td>26</td>\n    </tr>\n    <tr>\n      <th>190</th>\n      <td>Тонга</td>\n      <td>26</td>\n    </tr>\n    <tr>\n      <th>191</th>\n      <td>Восточный Тимор</td>\n      <td>26</td>\n    </tr>\n    <tr>\n      <th>192</th>\n      <td>Американские Виргинские острова</td>\n      <td>23</td>\n    </tr>\n    <tr>\n      <th>193</th>\n      <td>Папуа - Новая Гвинея</td>\n      <td>21</td>\n    </tr>\n    <tr>\n      <th>194</th>\n      <td>Каймановы острова</td>\n      <td>21</td>\n    </tr>\n    <tr>\n      <th>195</th>\n      <td>Американское Самоа</td>\n      <td>18</td>\n    </tr>\n    <tr>\n      <th>196</th>\n      <td>Британские Виргинские острова</td>\n      <td>18</td>\n    </tr>\n    <tr>\n      <th>197</th>\n      <td>Андорра</td>\n      <td>17</td>\n    </tr>\n    <tr>\n      <th>198</th>\n      <td>Коморские острова</td>\n      <td>17</td>\n    </tr>\n    <tr>\n      <th>199</th>\n      <td>Эритрея</td>\n      <td>11</td>\n    </tr>\n    <tr>\n      <th>200</th>\n      <td>Южный Судан</td>\n      <td>10</td>\n    </tr>\n    <tr>\n      <th>201</th>\n      <td>Макао</td>\n      <td>10</td>\n    </tr>\n    <tr>\n      <th>202</th>\n      <td>Сомали</td>\n      <td>8</td>\n    </tr>\n    <tr>\n      <th>203</th>\n      <td>Джибути</td>\n      <td>6</td>\n    </tr>\n    <tr>\n      <th>204</th>\n      <td>Острова Кука</td>\n      <td>5</td>\n    </tr>\n    <tr>\n      <th>205</th>\n      <td>Ангилья</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>206</th>\n      <td>Бутан</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>207</th>\n      <td>Тёркс и Кайкос</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>208</th>\n      <td>Сан-Марино</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>209 rows × 2 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def get_score(year, month, team):\n  df = (pd.read_html(f\"http://www.championat.com/football/fifa/{year}/{month}\", \n                     header=0, thousands=\" \")[0]\n        .rename(columns={'Unnamed: 3': 'team', 'Очки': 'score'})\n        [['team', 'score']])\n  return int(df.loc[df['team'] == team, 'score'])",
      "execution_count": 31,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "queries = [(2013, 9, 'Нидерланды'), (2014, 10, 'Германия')]\nresults = []\nfor year, month, team in queries:\n  results.append(get_score(year, month, team))",
      "execution_count": 38,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "results",
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 39,
          "data": {
            "text/plain": "[1058, 1669]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.7.0",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "scrap FIFA rating.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}