spotify_scraper.py

import sys
from selenium import webdriver
import string
import time
import os

def main(letter1):
	browser = webdriver.Chrome(executable_path='/usr/local/bin/chromedriver')
	browser.get(url="https://accounts.spotify.com/fr/login")
	time.sleep(3)
	browser.find_element_by_xpath("//input[@ng-model='form.username']").send_keys('your_email_here')
	browser.find_element_by_xpath("//input[@ng-model='form.password']").send_keys('your_password_here')
	browser.find_element_by_id("login-button").click()
	time.sleep(3)
	browser.get(url='https://open.spotify.com/search')

	def scroll_down(browser):
		search_content = browser.find_element_by_xpath('//div[@class="Search__content"]')
		last_artist = search_content.find_elements_by_class_name('media-object')[-1]
		browser.execute_script("arguments[0].scrollIntoView();", last_artist)

	def get_attributes(info_artists):
		artists = {}
		for info in info_artists:
			artists[info.get_attribute('href').replace('https://open.spotify.com/artist/','')] = info.get_attribute('title')
		return artists

	max_scroll = 100

	for letter2 in string.ascii_lowercase:
		print(letter1, letter2)
		if os.path.exists('artists_'+letter1+letter2+'.txt'):
			print(letter1, letter2, 'already exists')
			continue
		counter_scroll = 0
		browser.get(url='https://open.spotify.com/search/'+letter1+letter2+'/artists')
		time.sleep(1)

		while counter_scroll < max_scroll:
			print('\t'+str(counter_scroll))
			scroll_down(browser)
			time.sleep(1)
			counter_scroll += 1
		
		artists = get_attributes(
			browser.find_element_by_xpath('//div[@class="Search__content"]')
			.find_elements_by_xpath('//a[@class="mo-info-name"]')
		)

		with open('artists_'+letter1+letter2+'.txt', 'a') as f:
			f.write(str(artists))

if __name__ == '__main__':
	main(sys.argv[1])

Great work! I see that the Spotify scheme has changed. Is it possible to update the links in your code? I cannot find the search page you scrape.