_ Git - youtube-dl/blob - youtube_dl/extractor/mixcloud.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4 import functools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_chr,
  10     compat_ord,
  11     compat_urllib_parse_unquote,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     clean_html,
  16     ExtractorError,
  17     OnDemandPagedList,
  18     parse_count,
  19     str_to_int,
  20 )
  21
  22
  23 class MixcloudIE(InfoExtractor):
  24     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
  25     IE_NAME = 'mixcloud'
  26
  27     _TESTS = [{
  28         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  29         'info_dict': {
  30             'id': 'dholbach-cryptkeeper',
  31             'ext': 'm4a',
  32             'title': 'Cryptkeeper',
  33             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  34             'uploader': 'Daniel Holbach',
  35             'uploader_id': 'dholbach',
  36             'thumbnail': 're:https?://.*\.jpg',
  37             'view_count': int,
  38             'like_count': int,
  39         },
  40     }, {
  41         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  42         'info_dict': {
  43             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  44             'ext': 'mp3',
  45             'title': 'Caribou 7 inch Vinyl Mix & Chat',
  46             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  47             'uploader': 'Gilles Peterson Worldwide',
  48             'uploader_id': 'gillespeterson',
  49             'thumbnail': 're:https?://.*',
  50             'view_count': int,
  51             'like_count': int,
  52         },
  53     }]
  54
  55     # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
  56     @staticmethod
  57     def _decrypt_play_info(play_info):
  58         KEY = 'pleasedontdownloadourmusictheartistswontgetpaid'
  59
  60         play_info = base64.b64decode(play_info.encode('ascii'))
  61
  62         return ''.join([
  63             compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)]))
  64             for idx, ch in enumerate(play_info)])
  65
  66     def _real_extract(self, url):
  67         mobj = re.match(self._VALID_URL, url)
  68         uploader = mobj.group(1)
  69         cloudcast_name = mobj.group(2)
  70         track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
  71
  72         webpage = self._download_webpage(url, track_id)
  73
  74         message = self._html_search_regex(
  75             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
  76             webpage, 'error message', default=None)
  77
  78         encrypted_play_info = self._search_regex(
  79             r'm-play-info="([^"]+)"', webpage, 'play info')
  80         play_info = self._parse_json(
  81             self._decrypt_play_info(encrypted_play_info), track_id)
  82
  83         if message and 'stream_url' not in play_info:
  84             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  85
  86         song_url = play_info['stream_url']
  87
  88         PREFIX = (
  89             r'm-play-on-spacebar[^>]+'
  90             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  91         title = self._html_search_regex(
  92             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  93         thumbnail = self._proto_relative_url(self._html_search_regex(
  94             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  95             fatal=False))
  96         uploader = self._html_search_regex(
  97             PREFIX + r'm-owner-name="([^"]+)"',
  98             webpage, 'uploader', fatal=False)
  99         uploader_id = self._search_regex(
 100             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
 101         description = self._og_search_description(webpage)
 102         like_count = parse_count(self._search_regex(
 103             r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
 104             webpage, 'like count', fatal=False))
 105         view_count = str_to_int(self._search_regex(
 106             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 107              r'/listeners/?">([0-9,.]+)</a>'],
 108             webpage, 'play count', fatal=False))
 109
 110         return {
 111             'id': track_id,
 112             'title': title,
 113             'url': song_url,
 114             'description': description,
 115             'thumbnail': thumbnail,
 116             'uploader': uploader,
 117             'uploader_id': uploader_id,
 118             'view_count': view_count,
 119             'like_count': like_count,
 120         }
 121
 122
 123 class MixcloudPlaylistBaseIE(InfoExtractor):
 124     _PAGE_SIZE = 24
 125
 126     def _fetch_tracks_page(self, path, video_id, page_name, current_page):
 127         resp = self._download_webpage(
 128             'https://www.mixcloud.com/%s/' % path, video_id,
 129             note='Download %s (page %d)' % (page_name, current_page + 1),
 130             errnote='Unable to download %s' % page_name,
 131             query={'page': (current_page + 1), 'list': 'main', '_ajax': '1'},
 132             headers={'X-Requested-With': 'XMLHttpRequest'})
 133
 134         for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', resp):
 135             yield self.url_result(
 136                 compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
 137                 MixcloudIE.ie_key())
 138
 139     def _get_user_description(self, page_content):
 140         return self._html_search_regex(
 141             r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
 142             page_content, 'user description', fatal=False)
 143
 144
 145 class MixcloudUserIE(MixcloudPlaylistBaseIE):
 146     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
 147     IE_NAME = 'mixcloud:user'
 148
 149     _TESTS = [{
 150         'url': 'http://www.mixcloud.com/dholbach/',
 151         'info_dict': {
 152             'id': 'dholbach_uploads',
 153             'title': 'Daniel Holbach (uploads)',
 154             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 155         },
 156         'playlist_mincount': 11,
 157     }, {
 158         'url': 'http://www.mixcloud.com/dholbach/uploads/',
 159         'info_dict': {
 160             'id': 'dholbach_uploads',
 161             'title': 'Daniel Holbach (uploads)',
 162             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 163         },
 164         'playlist_mincount': 11,
 165     }, {
 166         'url': 'http://www.mixcloud.com/dholbach/favorites/',
 167         'info_dict': {
 168             'id': 'dholbach_favorites',
 169             'title': 'Daniel Holbach (favorites)',
 170             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 171         },
 172         'params': {
 173             'playlist_items': '1-100',
 174         },
 175         'playlist_mincount': 100,
 176     }, {
 177         'url': 'http://www.mixcloud.com/dholbach/listens/',
 178         'info_dict': {
 179             'id': 'dholbach_listens',
 180             'title': 'Daniel Holbach (listens)',
 181             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 182         },
 183         'params': {
 184             'playlist_items': '1-100',
 185         },
 186         'playlist_mincount': 100,
 187     }]
 188
 189     def _real_extract(self, url):
 190         mobj = re.match(self._VALID_URL, url)
 191         user_id = mobj.group('user')
 192         list_type = mobj.group('type')
 193
 194         # if only a profile URL was supplied, default to download all uploads
 195         if list_type is None:
 196             list_type = 'uploads'
 197
 198         video_id = '%s_%s' % (user_id, list_type)
 199
 200         profile = self._download_webpage(
 201             'https://www.mixcloud.com/%s/' % user_id, video_id,
 202             note='Downloading user profile',
 203             errnote='Unable to download user profile')
 204
 205         username = self._og_search_title(profile)
 206         description = self._get_user_description(profile)
 207
 208         entries = OnDemandPagedList(
 209             functools.partial(
 210                 self._fetch_tracks_page,
 211                 '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
 212             self._PAGE_SIZE, use_cache=True)
 213
 214         return self.playlist_result(
 215             entries, video_id, '%s (%s)' % (username, list_type), description)
 216
 217
 218 class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
 219     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
 220     IE_NAME = 'mixcloud:playlist'
 221
 222     _TESTS = [{
 223         'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
 224         'info_dict': {
 225             'id': 'RedBullThre3style_tokyo-finalists-2015',
 226             'title': 'National Champions 2015',
 227             'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
 228         },
 229         'playlist_mincount': 16,
 230     }, {
 231         'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
 232         'info_dict': {
 233             'id': 'maxvibes_jazzcat-on-ness-radio',
 234             'title': 'Jazzcat on Ness Radio',
 235             'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
 236         },
 237         'playlist_mincount': 23
 238     }]
 239
 240     def _real_extract(self, url):
 241         mobj = re.match(self._VALID_URL, url)
 242         user_id = mobj.group('user')
 243         playlist_id = mobj.group('playlist')
 244         video_id = '%s_%s' % (user_id, playlist_id)
 245
 246         profile = self._download_webpage(
 247             url, user_id,
 248             note='Downloading playlist page',
 249             errnote='Unable to download playlist page')
 250
 251         description = self._get_user_description(profile)
 252         playlist_title = self._html_search_regex(
 253             r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
 254             profile, 'playlist title')
 255
 256         entries = OnDemandPagedList(
 257             functools.partial(
 258                 self._fetch_tracks_page,
 259                 '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
 260             self._PAGE_SIZE)
 261
 262         return self.playlist_result(entries, video_id, playlist_title, description)