trying.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 18 18:08:03 2021

@author: thakkar
"""

# Tekore imports
import tekore as tk

# Data analysis imports
import modin.pandas as md
import pandas as pd
import numpy as np
from tqdm import tqdm
from collections import OrderedDict

# Util functions
def check_presence(target : dict, source: dict,
                   target_col: str, source_col : str, col_nest: str = '',
                   is_num : bool = False):
    
    if source_col in source:
        if col_nest != '':
            target[target_col] = source[source_col][col_nest]
        else:
            target[target_col] = source[source_col]
    else:
        if is_num:
            target[target_col] = np.NaN
        else:
            target[target_col] = None
            
    return target

# Load the files for running tekore
conf = tk.config_from_file('config.txt')
scope = tk.scope.playlist_read_private
token = tk.prompt_for_user_token(*conf, scope=scope)

# Data processing
data = md.read_csv('Artist-Genres-URIs.csv')
data['id'] = data['spotify_uri'].apply(lambda x: x.split(':')[-1])

spotify = tk.Spotify(token, max_limits_on=True, chunked_on=True)

def extract_details(artists, source_id):
    
    if len(artists) > 0:
    
        detail_response_chunk = []
            
        for artist in artists:
            
            response = artist.asbuiltin()
            
            res_detail = OrderedDict()
            
            res_detail = OrderedDict()
            res_detail['source_artist_uri'] = 'spotify:artist:'+source_id
            res_detail = check_presence(res_detail, response, 'artist_uri', 'uri')
            res_detail = check_presence(res_detail, response, 'artist_name', 'name')
            res_detail = check_presence(res_detail, response, 'id', 'id')
            res_detail = check_presence(res_detail, response, 'genres', 'genres')
        
            detail_response_chunk.append(res_detail)
        
        detail_response_chunk = pd.DataFrame(detail_response_chunk)
    
    else:
        
        cols = ['source_artist_uri', 'artist_uri', 'artist_name', 'id', 'genres']
        
        detail_response_chunk = pd.DataFrame(columns = cols)
        detail_response_chunk.loc[0, 'source_artist_uri'] = 'spotify:artist:'+source_id
        detail_response_chunk.loc[0, 'artist_uri'] = None
        detail_response_chunk.loc[0, 'artist_name'] = None
        detail_response_chunk.loc[0, 'id'] = ''
        detail_response_chunk.loc[0, 'genres'] = []
    
    return detail_response_chunk

# Artists
artist_dfs = []

for id_val in tqdm(range(len(data))):
    source_id = data['id'][id_val]
    artists = spotify.artist_related_artists(source_id)
    artist_dfs.append(extract_details(artists, source_id))