functions.py

import requests # To make get calls to API
from bs4 import BeautifulSoup # Helps make parsing html files much easier

import re, string, unicodedata
import nltk
import contractions
import inflect
from nltk import word_tokenize, sent_tokenize
from nltk.corpus import stopwords
from nltk.stem import LancasterStemmer, WordNetLemmatizer

# This token was granted through the use of Genius's website and allows us to make calls to the API
client_access_token = "_mDTViAvedsTbhpMuhLml-2gkMw1DU8tKQRnqmFkQDXT2aypVvCg67wDEr4eqBIs"

# Get artist object from Genius API
def request_artist_info(artist_name, page):
    base_url = 'https://api.genius.com'
    headers = {'Authorization': 'Bearer ' + client_access_token}
    search_url = base_url + '/search?per_page=10&page=' + str(page)
    data = {'q': artist_name}
    response = requests.get(search_url, data=data, headers=headers)
    return response

# Get Genius.com song url's from artist object
def request_song_url(artist_name, song_cap):
    page = 1
    songs = []
    
    while True:
        response = request_artist_info(artist_name, page)
        json = response.json()
        
        # Collect up to song_cap song objects from artist
        song_info = []
        for hit in json['response']['hits']:
            if artist_name.lower() in hit['result']['primary_artist']['name'].lower():
                song_info.append(hit)
    
        # Collect song URL's from song objects
        for song in song_info:
            if (len(songs) < song_cap):
                url = song['result']['url']
                songs.append(url)
            
        if (len(songs) == song_cap):
            break
        else:
            page += 1
        
    print('Found {} songs by {}'.format(len(songs), artist_name))
    return songs




def clean_lyrics(test_str):
    ret = ''
    skip1c = 0
    skip2c = 0
    for i in test_str:
        if i == '[':
            skip1c += 1
        elif i == '(':
            skip2c += 1
        elif i == ']' and skip1c > 0:
            skip1c -= 1
        elif i == ')'and skip2c > 0:
            skip2c -= 1
        elif skip1c == 0 and skip2c == 0:
            ret += i
    return ret