Scrape Data from Music League for Analysis

ml_scraper.py

import requests
import spotipy
import pandas as pd
from spotipy.oauth2 import SpotifyClientCredentials

#define api information
user = 'ml_userid'
base_url = 'https://app.musicleague.com/api/v1/'
url = base_url + 'users/' + user + '/leagues'
cookie = {'session':'session cookie from browser'}

def get_member(members, id):
    for member in members:
        if member['user']['id'] == id:
            return member['user']['name']
    return 'Error collecting name'

def spoticheck(uri):
    track = sp.track(uri)
    t_name = track['name']
    t_artist = track['album']['artists'][0]['name']
    t_artist_id = track['album']['artists'][0]['id']
    t_genres = ''
    artist = sp.artist(t_artist_id)
    for genre in artist['genres']:
        if t_genres == '':
            t_genres = genre
        else:
            t_genres += ',' + genre
    return t_name,t_artist,t_genres

#define spotify info
s_client_id = 'spotify api client id'
s_client_secret = 'spotify api client secret'
sp = spotipy.Spotify(auth_manager=SpotifyClientCredentials(client_id=s_client_id,
                                                           client_secret=s_client_secret))

#initialize df
df = pd.DataFrame(columns=['League','Round','Song','Artist','Genres','Submitter','Voter','Points'])

#get leagues
req_leagues = requests.get(url,cookies=cookie)
#iterate leagues
for league in req_leagues.json():
    l_name, l_id = league['name'], league['id']
    #print(l_name)
    #get members for that league
    url = base_url + 'leagues/' + l_id + '/members'
    req_members = requests.get(url, cookies=cookie)
    #get rounds for that league
    url = base_url + 'leagues/' + l_id + '/rounds'
    req_rounds = requests.get(url, cookies=cookie)
    for round in req_rounds.json():
        try:
            r_name, r_id = round['name'], round['id']
            #print('    ' + r_name)
            url = base_url + 'leagues/' + l_id + '/rounds/' + r_id + '/results'
            req_subs = requests.get(url, cookies=cookie)
            for result in req_subs.json()['standings']:
                s_score, s_uri, s_votes, s_submitter = result['pointsPossible'], result['submission']['spotifyUri'], result['votes'], result['submission']['submitterId']
                s_name,s_artist,s_genres = spoticheck(s_uri)
                s_submitter = get_member(req_members.json(), s_submitter)
                #print('        ' + s_submitter + ': ' + s_info + ': ' + str(s_score))
                for vote in s_votes:
                    v_id, v_points = vote['voterId'], vote['weight']
                    v_id = get_member(req_members.json(), v_id)
                    df.loc[len(df)] = [l_name,r_name,s_name,s_artist,s_genres,s_submitter,v_id,v_points]
                    #print('            ' + v_id + ': ' + str(v_points))
        except:
            continue
            #print('        Round still running or other error')

df.to_csv('output.csv', index=None)