diff options
| -rw-r--r-- | getData.py | 117 | ||||
| -rw-r--r-- | osSpecific.py | 2 | ||||
| -rw-r--r-- | utils/osSpecific.py | 25 |
3 files changed, 96 insertions, 48 deletions
@@ -1,76 +1,99 @@ import pandas as pd import requests -import osSpecific +from utils import osSpecific # Some functions to delete and create directoryes needed for data storing from dotenv import load_dotenv import os +''' +This python script fetches NBA teams and its players (currently playing and retired) and some +additional information about them. +The data is stored in the current working directory (any existing "Data" file is overwritten. +Data is in csv format. + +Author: Rasmus Luha +Created_at: 16.03.2022 +Data fetched from: https://rapidapi.com/theapiguy/api/free-nba/ +''' + +# Loading API key from environment variables. load_dotenv() API_KEY = os.getenv("API_KEY") +# To use this script, you should make .env file in current dir and add there: API_KEY = your API_key +# You can get the API key from url listed above. -# Delete Data Dir, if exists, and then create new. Have to do this to avoid duplicates, as Players are later appended to the files -osSpecific.deleteDataDir() -osSpecific.addDataDir() +# API request details +url = "https://free-nba.p.rapidapi.com/" +headers = { + 'x-rapidapi-host': "free-nba.p.rapidapi.com", + 'x-rapidapi-key': API_KEY + } -# File variables to but data into +# File name variables to store data in if osSpecific.whichOs() == "windows": teamsFile = "Data/NBAteams.csv" - playersDir = "Data\Players" + playersDir = "Data\Players\\" else: teamsFile = "Data/NBAteams.csv" - playersDir = "Data/Players" + playersDir = "Data/Players/" + +# Create new Data directory in order to avoid duplicates, when data is requested multiple times +osSpecific.deleteDataDir() +osSpecific.addDataDir() + -# Requesting data about NBA teams -url = "https://free-nba.p.rapidapi.com/" -querystring = {"page":"0"} -headers = { - 'x-rapidapi-host': "free-nba.p.rapidapi.com", - 'x-rapidapi-key': API_KEY - } -# Adding data to teams file -response = requests.request("GET", url+"teams", headers=headers, params=querystring) -teamsDf = pd.DataFrame(response.json()["data"]) -teamsDf.set_index("id") -teamsDf = teamsDf.drop("id", axis=1) +###### Functions ###### -teamsDf.to_csv(teamsFile) +def getTeamsData(url, headers): -####################################################### -# Now requesting players for each team -# First request is made just to get the amount of pages that must be looped through + querystring = {"page":"0"} + response = requests.request("GET", url+"teams", headers=headers, params=querystring) -querystring = {"per_page":"100","page":"0"} -response = requests.request("GET", url+"players", headers=headers, params=querystring) -pageCount = response.json()["meta"]["total_pages"] + teamsDf = pd.DataFrame(response.json()["data"]) + teamsDf.set_index("id") + teamsDf = teamsDf.drop("id", axis=1) + teamsDf.to_csv(teamsFile) + print("Teams data stored in Data directory as \"NBAteams.csv\"") -for el in range(1, pageCount+1): +def getPlayerData(url, headers): - # Requesting pages in loop till pageCount - querystring = {"per_page":"100","page":el} + # First request is made just to get the amount of pages that must be looped through + querystring = {"per_page":"100","page":"0"} response = requests.request("GET", url+"players", headers=headers, params=querystring) - data = response.json()["data"] + pageCount = response.json()["meta"]["total_pages"] - for player in data: - teamName = player["team"]["full_name"] - playerDf = pd.DataFrame(columns=["first_name", "last_name", "position", "height_feet", "height_inches"]) - - playerSeries = pd.Series({"first_name" : player["first_name"], - "last_name" : player["last_name"], - "position" : player["position"], - "height_feet" : player["height_feet"], - "height_inches" : player["height_inches"]}) - - #add player to dataframe - playerDf.loc[len(playerDf)] = playerSeries - #add dataframe to File - playerDf.to_csv(playersDir+teamName, mode='a', index=False, header=False) - print("Page "+el+" read.") -print("All done, check Data Dir") + for el in range(1, pageCount+1): + + # Requesting pages in loop till pageCount + querystring = {"per_page":"100","page":el} + response = requests.request("GET", url+"players", headers=headers, params=querystring) + data = response.json()["data"] + + for player in data: + teamName = player["team"]["full_name"] + playerDf = pd.DataFrame(columns=["first_name", "last_name", "position", "height_feet", "height_inches"]) + + playerSeries = pd.Series({"first_name" : player["first_name"], + "last_name" : player["last_name"], + "position" : player["position"], + "height_feet" : player["height_feet"], + "height_inches" : player["height_inches"]}) + + #add player to dataframe + playerDf.loc[len(playerDf)] = playerSeries + #add dataframe to File + playerDf.to_csv(playersDir+teamName+".csv", mode='a', index=False, header=False) + + print("Page "+str(el)+" read.") + print("All done, check \"Data\" Dir.") - +# Requesting and storing data +if __name__ == "__main__": + getTeamsData(url, headers) + getPlayerData(url, headers) diff --git a/osSpecific.py b/osSpecific.py index 09f5e59..7caf664 100644 --- a/osSpecific.py +++ b/osSpecific.py @@ -7,7 +7,7 @@ def whichOs(): if sys.platform == "win32": return "windows" else: - return "good" # Sorry, not sorry + return "good" # ...right? def deleteDataDir(): if whichOs() == "windows": diff --git a/utils/osSpecific.py b/utils/osSpecific.py new file mode 100644 index 0000000..7caf664 --- /dev/null +++ b/utils/osSpecific.py @@ -0,0 +1,25 @@ +import os +import sys + +# terminal commands, which are unfortunately os-specific + +def whichOs(): + if sys.platform == "win32": + return "windows" + else: + return "good" # ...right? + +def deleteDataDir(): + if whichOs() == "windows": + os.system("rmdir \s Data") + else: + os.system("rm -r Data") + + +def addDataDir(): + if whichOs() == "windows": + os.system("mkdir Data\Players") + else: + os.system("mkdir -p Data/Players") + print("Created new empty Data directory") + |