Udio media URL extraction script

udioSongURL.py

import argparse
import json
import re
import sys
import urllib.error
import urllib.request
from urllib.parse import urlparse


HTTP_TIMEOUT = 10
HTTP_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
SONGS_API_URL = 'https://www.udio.com/api/songs?songIds='


def main():
	parser = argparse.ArgumentParser(
		prog='udioSongURL.py',
		description='Given a link to a song on Udio, print its media file URL.',
	)
	parser.add_argument('link', help='The Udio song link, with or without "www." in the domain name, and with or without additional query string params on the end.')
	args = parser.parse_args()

	try:
		result = run(args.link)
	except RuntimeError as e:
		print(f'Error extracting media URL for song link: {args.link}:\n{e}')
		sys.exit(1)

	print(f'{result["artist"]} - {result["title"]}:\n{result["mediaURL"]}')


def run(songLink):
	urlPath = urlparse(songLink).path

	if match := re.search(r'/songs/([^/?]+)', urlPath):
		songID = match.group(1)
	else:
		raise RuntimeError('Could not extract song ID from provided link')

	requestURL = f'{SONGS_API_URL}{songID}'
	try:
		request = urllib.request.Request(requestURL, headers={'User-Agent': HTTP_USER_AGENT}, method='GET')
		with urllib.request.urlopen(request, timeout=HTTP_TIMEOUT) as response:
			responseBody = response.read().decode('utf-8')
	except urllib.error.HTTPError as e:
		raise RuntimeError(f'Request to API URL {requestURL} failed: {e}')
	except TimeoutError as e:
		raise RuntimeError(f'Request to API URL {requestURL} failed: HTTP connection timed out after {HTTP_TIMEOUT} seconds')

	try:
		data = json.loads(responseBody)
	except Exception as e:
		raise RuntimeError(f'Unable to decode HTTP response as JSON from: {requestURL}')

	songs = data.get('songs', [])
	numberOfSongs = len(songs)
	if numberOfSongs == 0:
		raise RuntimeError('No matching songs')
	elif numberOfSongs > 1:
		raise RuntimeError(f'{numberOfSongs} matching songs found; multiple song matches are not supported')

	song = songs[0]
	result = {
		'artist': song.get('artist', 'Unknown Artist'),
		'title': song.get('title', 'Unknown Title'),
		'mediaURL': song.get('song_path', None),
	}
	if result['mediaURL'] is None:
			raise RuntimeError(f'Unable to extract media URL for song from API response:\n{responseBody}')

	return result


if __name__ == '__main__':
	main()