Skip to content

Instantly share code, notes, and snippets.

@snippsat
Created December 26, 2019 22:01
Show Gist options
  • Save snippsat/9766975d246510262eeee5659b58a8b9 to your computer and use it in GitHub Desktop.
Save snippsat/9766975d246510262eeee5659b58a8b9 to your computer and use it in GitHub Desktop.
{
"cells": [
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"FIDE World Rapid Championship\n"
]
},
{
"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>Rank</th>\n",
" <th>Name</th>\n",
" <th>Score</th>\n",
" <th>Rating</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Wang, Hao</td>\n",
" <td>4½/5</td>\n",
" <td>2748.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>Mamedyarov, Shakhriyar</td>\n",
" <td>4½/5</td>\n",
" <td>2752.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Smirin, Ilia</td>\n",
" <td>4½/5</td>\n",
" <td>2584.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>Duda, Jan-Krzysztof</td>\n",
" <td>4½/5</td>\n",
" <td>2751.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>Dominguez Perez, Leinier</td>\n",
" <td>4½/5</td>\n",
" <td>2755.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>Carlsen, Magnus</td>\n",
" <td>4/5</td>\n",
" <td>2886.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>7</td>\n",
" <td>Guseinov, Gadir</td>\n",
" <td>4/5</td>\n",
" <td>2691.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>8</td>\n",
" <td>Le, Quang Liem</td>\n",
" <td>4/5</td>\n",
" <td>2740.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>9</td>\n",
" <td>Zubov, Alexander</td>\n",
" <td>4/5</td>\n",
" <td>2688.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>10</td>\n",
" <td>Dubov, Daniil</td>\n",
" <td>4/5</td>\n",
" <td>2752.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Rank Name Score Rating\n",
"0 1 Wang, Hao 4½/5 2748.0\n",
"1 2 Mamedyarov, Shakhriyar 4½/5 2752.0\n",
"2 3 Smirin, Ilia 4½/5 2584.0\n",
"3 4 Duda, Jan-Krzysztof 4½/5 2751.0\n",
"4 5 Dominguez Perez, Leinier 4½/5 2755.0\n",
"5 6 Carlsen, Magnus 4/5 2886.0\n",
"6 7 Guseinov, Gadir 4/5 2691.0\n",
"7 8 Le, Quang Liem 4/5 2740.0\n",
"8 9 Zubov, Alexander 4/5 2688.0\n",
"9 10 Dubov, Daniil 4/5 2752.0"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from selenium import webdriver\n",
"from bs4 import BeautifulSoup\n",
"from selenium.webdriver.chrome.options import Options\n",
"from selenium.webdriver.common.keys import Keys\n",
"import pandas as pd\n",
"import time\n",
"\n",
"#--| Setup\n",
"options = Options()\n",
"#options.add_argument(\"--headless\")\n",
"browser = webdriver.Chrome(executable_path=r'chromedriver.exe', options=options)\n",
"\n",
"#--| Parse or automation\n",
"browser.get('https://chess24.com/en/watch/live-tournaments/world-rapid-championship-2019/4/1/5')\n",
"soup = BeautifulSoup(browser.page_source, 'lxml')\n",
"#browser.implicitly_wait(5)\n",
"time.sleep(4)\n",
"title = soup.select('h2.title')\n",
"print(title[0].text)\n",
"\n",
"# Get table\n",
"df = pd.read_html(browser.page_source, header=None)\n",
"standings = df[2]\n",
"standings.columns = [\"Rank\", \"Name\", \"Score\", \"Rating\"]\n",
"standings.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"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>Rank</th>\n",
" <th>Name</th>\n",
" <th>Score</th>\n",
" <th>Rating</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>6</td>\n",
" <td>Carlsen, Magnus</td>\n",
" <td>4/5</td>\n",
" <td>2886.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Rank Name Score Rating\n",
"5 6 Carlsen, Magnus 4/5 2886.0"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# We have a okay player in my country \n",
"standings.loc[[5]]"
]
}
],
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment