from ..utils import (
ExtractorError,
HEADRequest,
- int_or_none,
+ str_to_int,
parse_iso8601,
)
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
IE_NAME = 'mixcloud'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
'id': 'dholbach-cryptkeeper',
'view_count': int,
'like_count': int,
},
- }
+ }, {
+ 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
+ 'info_dict': {
+ 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+ 'ext': 'm4a',
+ 'title': 'Electric Relaxation vol. 3',
+ 'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
+ 'uploader': 'Daniel Drumz',
+ 'uploader_id': 'gillespeterson',
+ 'thumbnail': 're:https?://.*\.jpg',
+ 'view_count': int,
+ 'like_count': int,
+ },
+ }]
def _get_url(self, track_id, template_url):
server_count = 30
webpage = self._download_webpage(url, track_id)
preview_url = self._search_regex(
- r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
+ r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
song_url = preview_url.replace('/previews/', '/c/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
final_song_url = self._get_url(track_id, template_url)
uploader_id = self._search_regex(
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
- like_count = int_or_none(self._search_regex(
- r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+ like_count = str_to_int(self._search_regex(
+ [r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
+ r'/favorites/?">([0-9]+)<'],
webpage, 'like count', fatal=False))
- view_count = int_or_none(self._search_regex(
- r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+ view_count = str_to_int(self._search_regex(
+ [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
+ r'/listeners/?">([0-9,.]+)</a>'],
webpage, 'play count', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'<time itemprop="dateCreated" datetime="([^"]+)">',
- webpage, 'upload date'))
+ webpage, 'upload date', default=None))
return {
'id': track_id,