basketball-reference-webscrapper 0.1.3__tar.gz

basketball_reference_webscrapper-0.1.3/PKG-INFO

@@ -0,0 +1,21 @@
+Metadata-Version: 2.1
+Name: basketball-reference-webscrapper
+Version: 0.1.3
+Summary: Python package for Basketball Reference that gathers data by scraping the website
+Author: Yannick Flores
+Author-email: yannick.flores1992@gmail.com
+Requires-Python: >=3.11,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: beautifulsoup4 (==4.12.*)
+Requires-Dist: numpy (==1.26.*)
+Requires-Dist: pandas (==2.*)
+Requires-Dist: pylint (>=2.15.10,<3.0.0)
+Requires-Dist: pytest
+Requires-Dist: requests (==2.32.*)
+Description-Content-Type: text/markdown
+
+# basketball-reference-webscrapper
+A python package for Basketball Reference that gathers data by scraping the website.
+

basketball_reference_webscrapper-0.1.3/README.md

@@ -0,0 +1,2 @@
+# basketball-reference-webscrapper
+A python package for Basketball Reference that gathers data by scraping the website.

basketball_reference_webscrapper-0.1.3/basketball_reference_webscrapper/constants/team_city_refdata.csv

@@ -0,0 +1,38 @@
+team_abrev;city;team_name
+ATL;Atlanta;Atlanta Hawks
+BOS;Boston;Boston Celtics
+BRK;Brooklyn;Brooklyn Nets
+CHA;Charlotte;Charlotte Bobcats
+CHH;Charlotte;Charlotte Hornets
+CHI;Chicago;Chicago Bulls
+CHO;Charlotte;Charlotte Hornets
+CLE;Cleveland;Cleveland Cavaliers
+DAL;Dallas;Dallas Mavericks
+DEN;Denver;Denver Nuggets
+DET;Detroit;Detroit Pistons
+GSW;Golden State;Golden State Warriors
+HOU;Houston;Houston Rockets
+IND;Indiana;Indiana Pacers
+LAC;Los Angeles;Los Angeles Clippers
+LAL;Los Angeles;Los Angeles Lakers
+MEM;Memphis;Memphis Grizzlies
+MIA;Miami;Miami Heat
+MIL;Milwaukee;Milwaukee Bucks
+MIN;Minnesota;Minnesota Timberwolves
+NJN;New Jersey;New Jersey Nets
+NOH;New Orleans;New Orleans Hornets
+NOK;New Orleans;New Orleans/Oklahoma City Hornets
+NOP;New Orleans;New Orleans Pelicans
+NYK;New York;New York Knicks
+OKC;Oklahoma;Oklahoma City Thunder
+ORL;Orlando;Orlando Magic
+PHI;Philadelphie;Philadelphia 76ers
+PHO;Phoenix;Phoenix Suns
+POR;Portland;Portland Trail Blazers
+SAC;Sacramento;Sacramento Kings
+SAS;San Antonio;San Antonio Spurs
+SEA;Seattle;Seattle SuperSonics
+TOR;Toronto;Toronto Raptors
+UTA;Utah;Utah Jazz
+VAN;Vancover;Vancouver Grizzlies
+WAS;Washington D.C;Washington Wizards

basketball_reference_webscrapper-0.1.3/basketball_reference_webscrapper/utils/logs.py

@@ -0,0 +1,44 @@
+"""Provides functions to create loggers."""
+
+import logging
+from typing import Text, Union
+import sys
+
+
+def get_console_handler() -> logging.StreamHandler:
+    """Get console handler.
+    Returns:
+        logging.StreamHandler which logs into stdout
+    """
+
+    console_handler = logging.StreamHandler(sys.stdout)
+    formatter = logging.Formatter(
+        "%(asctime)s — %(name)s — %(levelname)s — %(message)s"
+    )
+    console_handler.setFormatter(formatter)
+
+    return console_handler
+
+
+def get_logger(
+    name: Text = __name__, log_level: Union[Text, int] = logging.DEBUG
+) -> logging.Logger:
+    """Get logger.
+    Args:
+        name {Text}: logger name
+        log_level {Text or int}: logging level; can be string name or integer value
+    Returns:
+        logging.Logger instance
+    """
+
+    logger = logging.getLogger(name)
+    logger.setLevel(log_level)
+
+    # Prevent duplicate outputs in Jypyter Notebook
+    if logger.hasHandlers():
+        logger.handlers.clear()
+
+    logger.addHandler(get_console_handler())
+    logger.propagate = False
+
+    return logger

basketball_reference_webscrapper-0.1.3/basketball_reference_webscrapper/webscrapping_basketball_reference.py

@@ -0,0 +1,115 @@
+from dataclasses import dataclass
+from urllib.request import urlopen
+from bs4 import BeautifulSoup
+import pandas as pd
+import requests
+import time
+import importlib_resources
+
+from basketball_reference_webscrapper.utils.logs import get_logger
+
+logger = get_logger("WEB_SCRAPPING_EXECUTION", log_level="INFO")
+
+@dataclass
+class WebScrapBasketballReference:
+    """
+    Class that take as inputs url and season and return all games teams stats
+    """
+
+    # init method or constructor
+    def __init__(self, url, season):
+        self.url = url
+        self.season = season
+
+    def webscrappe_nba_games_data(self):
+        """
+        Webscrappe NBA games data
+        """
+        
+        #------------------------------------------------------
+        # Get team reference data 
+        ref = (
+            importlib_resources.files("basketball_reference_webscrapper")
+            / "constants/team_city_refdata.csv"
+        )
+        with importlib_resources.as_file(ref) as path:
+            # Do something with path.  After the with-statement exits, any
+            # temporary file created will be immediately cleaned up.
+            team_city_refdata = pd.read_csv(path, sep = ';')
+
+        #------------------------------------------------------
+        # Initialization of the dataframe to fill-in
+        games = pd.DataFrame()
+
+        #------------------------------------------------------
+        # For Loop Throught all the team abrev for the given season
+
+        team_city_refdata = team_city_refdata.head(2)
+
+        for index, row in team_city_refdata.iterrows():
+
+            # URL to scrape
+            team = row['team_abrev']
+
+            logger.info(
+                f"Execution for {team}"
+            )
+            
+            # url = f"https://www.basketball-reference.com/teams/{team}/{self.season}/gamelog/"
+            url = f"https://www.basketball-reference.com/teams/ATL/2022/gamelog/"
+
+
+            if '200' in str(requests.get(url)):
+
+                # collect HTML data and create beautiful soup object:
+                # collect HTML data
+                html = urlopen(url)
+                        
+                # create beautiful soup object from HTML
+                soup = BeautifulSoup(html, "html.parser")
+
+                rows = soup.findAll('tr')[2:]
+
+                rows_data = [[td.getText() for td in rows[i].findAll('td')]
+                                    for i in range(len(rows))]
+
+                if len(rows_data) != 0:
+                    # create the dataframe
+                    games_tmp = pd.DataFrame(rows_data)
+                    cols = ["game_nb", "game_date", "extdom", "opp", "results",
+                            "pts_tm","pts_opp",
+                            "fg_tm", "fga_tm","fg_prct_tm",
+                            "3p_tm","3pa_tm", "3p_prct_tm","ft_tm","fta_tm","ft_prct_tm",
+                            "orb_tm","trb_tm", "ast_tm","stl_tm","blk_tm" ,"tov_tm","pf_tm",
+                            "nc",
+                            "fg_opp","fga_opp","fg_prct_opp",
+                            "3p_opp", "3pa_opp", "3p_prct_opp", "ft_opp", "fta_opp","ft_prct_opp",
+                            "orb_opp", "trb_opp","ast_opp", "stl_opp", "blk_opp","tov_opp", "pf_opp"]
+
+                    games_tmp.columns =  cols
+                    games_tmp = games_tmp.dropna()
+                    games_tmp['id_season'] = self.season
+                    games_tmp['tm'] = team
+                    games = pd.concat([games, games_tmp], axis=0)
+            
+            time.sleep(5)
+
+        games = games[[
+            'id_season', 'game_nb', 'game_date', 'extdom', 'tm','opp', 'results', 'pts_tm', 'pts_opp',
+            'fg_tm', 'fga_tm', 'fg_prct_tm', '3p_tm', '3pa_tm', '3p_prct_tm',
+            'ft_tm', 'fta_tm', 'ft_prct_tm', 'orb_tm', 'trb_tm', 'ast_tm', 'stl_tm',
+            'blk_tm', 'tov_tm', 'pf_tm', 'fg_opp', 'fga_opp', 'fg_prct_opp',
+            '3p_opp', '3pa_opp', '3p_prct_opp', 'ft_opp', 'fta_opp', 'ft_prct_opp',
+            'orb_opp', 'trb_opp', 'ast_opp', 'stl_opp', 'blk_opp', 'tov_opp',
+            'pf_opp']]
+
+        return games
+    
+if __name__ == "__main__":
+    webscrapping_class = WebScrapBasketballReference(
+        url = "test",
+        season = 2022
+    )
+
+    nba_games = webscrapping_class.webscrappe_nba_games_data()
+

basketball_reference_webscrapper-0.1.3/pyproject.toml

@@ -0,0 +1,39 @@
+[tool.poetry]
+name = "basketball-reference-webscrapper"
+version = "0.1.3"
+description = "Python package for Basketball Reference that gathers data by scraping the website"
+authors = ["Yannick Flores <yannick.flores1992@gmail.com>"]
+readme = "README.md"
+exclude = ["tests", "docs"]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+pandas = "2.*"
+numpy = "1.26.*"
+pytest = "*"
+pylint = "^2.15.10"
+beautifulsoup4 = "4.12.*"
+requests = "2.32.*"
+
+[tool.poetry.dev-dependencies]
+coverage = {extras = ["toml"], version = "6.5.*"}
+black = {version = "22.10.*", allow-prereleases = true}
+pytest = "7.2.*"
+pytest-html = "3.1.*"
+pytest-cov = "2.12.*"
+py = "1.11.*"
+pylint = "2.15.*"
+python-decouple = "3.6"
+mkdocs = "1.4.*"
+importlib-resources="6.0.1"
+
+[tool.pytest.ini_options]
+pythonpath = "."
+testpaths = "tests"
+addopts = [
+    "--import-mode=importlib",
+]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"