from ..compat import (
compat_chr,
compat_ord,
+ compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
)
'only_matching': True,
}]
- # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
- @staticmethod
- def _decrypt_play_info(play_info):
- KEY = 'pleasedontdownloadourmusictheartistswontgetpaid'
+ _keys = [
+ 'return { requestAnimationFrame: function(callback) { callback(); }, innerHeight: 500 };',
+ 'pleasedontdownloadourmusictheartistswontgetpaid',
+ 'window.addEventListener = window.addEventListener || function() {};',
+ '(function() { return new Date().toLocaleDateString(); })()'
+ ]
+ _current_key = None
+ # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
+ def _decrypt_play_info(self, play_info, video_id):
play_info = base64.b64decode(play_info.encode('ascii'))
-
- return ''.join([
- compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)]))
- for idx, ch in enumerate(play_info)])
+ for num, key in enumerate(self._keys, start=1):
+ try:
+ return self._parse_json(
+ ''.join([
+ compat_chr(compat_ord(ch) ^ compat_ord(key[idx % len(key)]))
+ for idx, ch in enumerate(play_info)]),
+ video_id)
+ except ExtractorError:
+ if num == len(self._keys):
+ raise
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, track_id)
+ if not self._current_key:
+ js_url = self._search_regex(
+ r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)',
+ webpage, 'js url', default=None)
+ if js_url:
+ js = self._download_webpage(js_url, track_id, fatal=False)
+ if js:
+ key = self._search_regex(
+ r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P<key>(?:(?!\1).)+)\1',
+ js, 'key', default=None, group='key')
+ if key and isinstance(key, compat_str):
+ self._keys.insert(0, key)
+ self._current_key = key
+
message = self._html_search_regex(
r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
webpage, 'error message', default=None)
encrypted_play_info = self._search_regex(
r'm-play-info="([^"]+)"', webpage, 'play info')
- play_info = self._parse_json(
- self._decrypt_play_info(encrypted_play_info), track_id)
+
+ play_info = self._decrypt_play_info(encrypted_play_info, track_id)
if message and 'stream_url' not in play_info:
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>',
- r'm-tooltip=["\']([\d,.]+) plays'],
+ r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
webpage, 'play count', default=None))
return {
def _get_user_description(self, page_content):
return self._html_search_regex(
- r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
+ r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>',
page_content, 'user description', fatal=False)
class MixcloudUserIE(MixcloudPlaylistBaseIE):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
+ _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
IE_NAME = 'mixcloud:user'
_TESTS = [{
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
- 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ 'description': 'md5:def36060ac8747b3aabca54924897e47',
},
'playlist_mincount': 11,
}, {
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
- 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ 'description': 'md5:def36060ac8747b3aabca54924897e47',
},
'playlist_mincount': 11,
}, {
'info_dict': {
'id': 'dholbach_favorites',
'title': 'Daniel Holbach (favorites)',
- 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ 'description': 'md5:def36060ac8747b3aabca54924897e47',
},
'params': {
'playlist_items': '1-100',
'info_dict': {
'id': 'dholbach_listens',
'title': 'Daniel Holbach (listens)',
- 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ 'description': 'md5:def36060ac8747b3aabca54924897e47',
},
'params': {
'playlist_items': '1-100',
class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
- _VALID_URL = r'
^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
+ _VALID_URL = r'
https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
IE_NAME = 'mixcloud:playlist'
_TESTS = [{
'playlist_mincount': 16,
}, {
'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
- 'info_dict': {
- 'id': 'maxvibes_jazzcat-on-ness-radio',
- 'title': 'Jazzcat on Ness Radio',
- 'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
- },
- 'playlist_mincount': 23
+ 'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = mobj.group('playlist')
video_id = '%s_%s' % (user_id, playlist_id)
- profile = self._download_webpage(
+ webpage = self._download_webpage(
url, user_id,
note='Downloading playlist page',
errnote='Unable to download playlist page')
- description = self._get_user_description(profile)
- playlist_title = self._html_search_regex(
- r'<a class="parent active" href="[^"]*"><b>\d+</b><span title="[^"]*">([^</]*?)</span></a>',
- profile, 'playlist title')
+ title = self._html_search_regex(
+ r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)',
+ webpage, 'playlist title',
+ default=None) or self._og_search_title(webpage, fatal=False)
+ description = self._get_user_description(webpage)
entries = OnDemandPagedList(
functools.partial(
'%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
self._PAGE_SIZE)
- return self.playlist_result(entries, video_id, playlist_title, description)
+ return self.playlist_result(entries, video_id, title, description)
class MixcloudStreamIE(MixcloudPlaylistBaseIE):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
+ _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
IE_NAME = 'mixcloud:stream'
_TEST = {
projects / youtube-dl / blobdiff