Scrape a list of Spotify track IDs for JSON and preview URLs. Can handle very large lists of tracks by using subdirectories based on the track ID. Picks up where it lefts off. Ignores errors during downloading.

spotify-scrape.py

#!/usr/bin/env python

import json, urllib
import os.path
import subprocess
import argparse
from subprocess import call

parser = argparse.ArgumentParser(
	description='Scrape a list of Spotify track IDs for JSON and preview URLs.')
parser.add_argument('filename')
args = parser.parse_args()
filename = args.filename

def download(remote, local):
	# print("{} > {}".format(remote, local))
	# urllib.urlretrieve(data['preview_url'], outMp3) # urllib version
	call(['curl', remote, '--output', local, '--create-dirs', '--progress-bar']) # curl version

def safe(char):
	if char.isupper():
		char = '+'+char
	return char

def linecount(filename):
	return sum(1 for line in open(filename))

i = 0
n = linecount(filename)
with open(filename) as f:
	for line in f:
		track = line.rstrip()
		jsonUrl = 'https://api.spotify.com/v1/tracks/{}'.format(track)
		path = '{}/{}/{}/{}'.format(safe(track[0]), safe(track[1]), safe(track[2]), track)
		outMp3 = 'mp3/{}.mp3'.format(path)
		outJson = 'json/{}.json'.format(path)
		try:
			needJson = not os.path.isfile(outJson)
			needMp3 = not os.path.isfile(outMp3)
			if needJson or needMp3:
				print('loading {} ({:.2f}%)'.format(track, (100. * i) / n))
				if needJson:
					download(jsonUrl, outJson)
				else:
					print('[json downloaded]')
				if needMp3:
					data = json.load(open(outJson))
					if 'preview_url' in data and data['preview_url']:
						download(data['preview_url'], outMp3)
					else:
						print('[mp3 not available]')
				else:
					print('[mp3 downloaded]')
		except KeyboardInterrupt as e:
			break
		except Exception as e:
			print e
		i += 1