1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
|
'''NBA data reciever
This python script fetches NBA teams and its players (including retired)
with some additional information about them.
The data is stored in the current working directory and thus,
any existing "Data" file is overwritten. Data will be in csv format.
To use this script, "pandas" and "python-dotenv" must be installed
You also have to make .env file in current dir and add there: API_KEY = your API_key
You can get the API key from url below.
Used API: https://rapidapi.com/theapiguy/api/free-nba/
'''
import os
import requests
import pandas as pd
from utils import osSpecific # Some functions to delete and create directories for data
from dotenv import load_dotenv
# Loading API key from environment variables.
load_dotenv()
API_KEY = os.getenv("API_KEY")
# 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 name variables to store data in
if osSpecific.whichOs() == "windows":
teamsFile = "Data/NBAteams.csv"
playersDir = "Data\Players\\"
else:
teamsFile = "Data/NBAteams.csv"
playersDir = "Data/Players/"
# Createubg new Data dir to avoid duplicates (due appending)
osSpecific.deleteDataDir()
osSpecific.addDataDir()
###### Functions ######
def getTeamsData(url, headers):
'''
Requests Data about NBA teams and stores it.
Takes API url as first and its headers as second argument.
'''
querystring = {"page": "0"}
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)
teamsDf.to_csv(teamsFile)
print("Teams data stored in Data directory as \"NBAteams.csv\"")
def getPlayerData(url, headers):
'''
Requests Data about NBA players and stores it, based on teams
Takes API url as first and its headers as second argument.
'''
print("Stared reading players data")
# First request is made to get the page count to loop
querystring = {"per_page": "100","page":"0"}
response = requests.request("GET", url+"players", headers=headers, params=querystring)
pageCount = response.json()["meta"]["total_pages"] # Got the page count here
print("Pages to read: "+str(pageCount))
for el in range(1, pageCount+1):
# Requesting pages in loop till pageCount is reached
querystring = {"per_page": "100","page": el}
response = requests.request("GET", url+"players", headers=headers, params=querystring)
data = response.json()["data"]
# Making dataframe for each player to store it suitable file
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"]})
playerDf.loc[len(playerDf)] = playerSeries
# Add dataframe to File, if first to be added, then also add column names
hdr = False if os.path.isfile(playersDir+teamName+".csv") else True
playerDf.to_csv(playersDir+teamName+".csv", mode='a', index=False, header=hdr)
print("Page "+str(el)+" read.")
print("All done, check \"Data\" Dir.")
if __name__ == "__main__":
getTeamsData(url, headers)
getPlayerData(url, headers)
|
