youtube_dl/extractor/mixcloud.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4 import functools
   5 import itertools
   6 import re
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_chr,
  11     compat_ord,
  12     compat_urllib_parse_unquote,
  13     compat_urlparse,
  14 )
  15 from ..utils import (
  16     clean_html,
  17     ExtractorError,
  18     OnDemandPagedList,
  19     parse_count,
  20     str_to_int,
  21 )
  22
  23
  24 class MixcloudIE(InfoExtractor):
  25     _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
  26     IE_NAME = 'mixcloud'
  27
  28     _TESTS = [{
  29         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  30         'info_dict': {
  31             'id': 'dholbach-cryptkeeper',
  32             'ext': 'm4a',
  33             'title': 'Cryptkeeper',
  34             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  35             'uploader': 'Daniel Holbach',
  36             'uploader_id': 'dholbach',
  37             'thumbnail': r're:https?://.*\.jpg',
  38             'view_count': int,
  39             'like_count': int,
  40         },
  41     }, {
  42         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  43         'info_dict': {
  44             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  45             'ext': 'mp3',
  46             'title': 'Caribou 7 inch Vinyl Mix & Chat',
  47             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  48             'uploader': 'Gilles Peterson Worldwide',
  49             'uploader_id': 'gillespeterson',
  50             'thumbnail': 're:https?://.*',
  51             'view_count': int,
  52             'like_count': int,
  53         },
  54     }, {
  55         'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
  56         'only_matching': True,
  57     }]
  58
  59     # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
  60     @staticmethod
  61     def _decrypt_play_info(play_info):
  62         KEY = 'pleasedontdownloadourmusictheartistswontgetpaid'
  63
  64         play_info = base64.b64decode(play_info.encode('ascii'))
  65
  66         return ''.join([
  67             compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)]))
  68             for idx, ch in enumerate(play_info)])
  69
  70     def _real_extract(self, url):
  71         mobj = re.match(self._VALID_URL, url)
  72         uploader = mobj.group(1)
  73         cloudcast_name = mobj.group(2)
  74         track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
  75
  76         webpage = self._download_webpage(url, track_id)
  77
  78         message = self._html_search_regex(
  79             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
  80             webpage, 'error message', default=None)
  81
  82         encrypted_play_info = self._search_regex(
  83             r'm-play-info="([^"]+)"', webpage, 'play info')
  84         play_info = self._parse_json(
  85             self._decrypt_play_info(encrypted_play_info), track_id)
  86
  87         if message and 'stream_url' not in play_info:
  88             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  89
  90         song_url = play_info['stream_url']
  91
  92         PREFIX = (
  93             r'm-play-on-spacebar[^>]+'
  94             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  95         title = self._html_search_regex(
  96             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  97         thumbnail = self._proto_relative_url(self._html_search_regex(
  98             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  99             fatal=False))
 100         uploader = self._html_search_regex(
 101             PREFIX + r'm-owner-name="([^"]+)"',
 102             webpage, 'uploader', fatal=False)
 103         uploader_id = self._search_regex(
 104             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
 105         description = self._og_search_description(webpage)
 106         like_count = parse_count(self._search_regex(
 107             r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
 108             webpage, 'like count', default=None))
 109         view_count = str_to_int(self._search_regex(
 110             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 111              r'/listeners/?">([0-9,.]+)</a>'],
 112             webpage, 'play count', default=None))
 113
 114         return {
 115             'id': track_id,
 116             'title': title,
 117             'url': song_url,
 118             'description': description,
 119             'thumbnail': thumbnail,
 120             'uploader': uploader,
 121             'uploader_id': uploader_id,
 122             'view_count': view_count,
 123             'like_count': like_count,
 124         }
 125
 126
 127 class MixcloudPlaylistBaseIE(InfoExtractor):
 128     _PAGE_SIZE = 24
 129
 130     def _find_urls_in_page(self, page):
 131         for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page):
 132             yield self.url_result(
 133                 compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
 134                 MixcloudIE.ie_key())
 135
 136     def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None):
 137         real_page_number = real_page_number or current_page + 1
 138         return self._download_webpage(
 139             'https://www.mixcloud.com/%s/' % path, video_id,
 140             note='Download %s (page %d)' % (page_name, current_page + 1),
 141             errnote='Unable to download %s' % page_name,
 142             query={'page': real_page_number, 'list': 'main', '_ajax': '1'},
 143             headers={'X-Requested-With': 'XMLHttpRequest'})
 144
 145     def _tracks_page_func(self, page, video_id, page_name, current_page):
 146         resp = self._fetch_tracks_page(page, video_id, page_name, current_page)
 147
 148         for item in self._find_urls_in_page(resp):
 149             yield item
 150
 151     def _get_user_description(self, page_content):
 152         return self._html_search_regex(
 153             r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
 154             page_content, 'user description', fatal=False)
 155
 156
 157 class MixcloudUserIE(MixcloudPlaylistBaseIE):
 158     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
 159     IE_NAME = 'mixcloud:user'
 160
 161     _TESTS = [{
 162         'url': 'http://www.mixcloud.com/dholbach/',
 163         'info_dict': {
 164             'id': 'dholbach_uploads',
 165             'title': 'Daniel Holbach (uploads)',
 166             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 167         },
 168         'playlist_mincount': 11,
 169     }, {
 170         'url': 'http://www.mixcloud.com/dholbach/uploads/',
 171         'info_dict': {
 172             'id': 'dholbach_uploads',
 173             'title': 'Daniel Holbach (uploads)',
 174             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 175         },
 176         'playlist_mincount': 11,
 177     }, {
 178         'url': 'http://www.mixcloud.com/dholbach/favorites/',
 179         'info_dict': {
 180             'id': 'dholbach_favorites',
 181             'title': 'Daniel Holbach (favorites)',
 182             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 183         },
 184         'params': {
 185             'playlist_items': '1-100',
 186         },
 187         'playlist_mincount': 100,
 188     }, {
 189         'url': 'http://www.mixcloud.com/dholbach/listens/',
 190         'info_dict': {
 191             'id': 'dholbach_listens',
 192             'title': 'Daniel Holbach (listens)',
 193             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 194         },
 195         'params': {
 196             'playlist_items': '1-100',
 197         },
 198         'playlist_mincount': 100,
 199     }]
 200
 201     def _real_extract(self, url):
 202         mobj = re.match(self._VALID_URL, url)
 203         user_id = mobj.group('user')
 204         list_type = mobj.group('type')
 205
 206         # if only a profile URL was supplied, default to download all uploads
 207         if list_type is None:
 208             list_type = 'uploads'
 209
 210         video_id = '%s_%s' % (user_id, list_type)
 211
 212         profile = self._download_webpage(
 213             'https://www.mixcloud.com/%s/' % user_id, video_id,
 214             note='Downloading user profile',
 215             errnote='Unable to download user profile')
 216
 217         username = self._og_search_title(profile)
 218         description = self._get_user_description(profile)
 219
 220         entries = OnDemandPagedList(
 221             functools.partial(
 222                 self._tracks_page_func,
 223                 '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
 224             self._PAGE_SIZE, use_cache=True)
 225
 226         return self.playlist_result(
 227             entries, video_id, '%s (%s)' % (username, list_type), description)
 228
 229
 230 class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
 231     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
 232     IE_NAME = 'mixcloud:playlist'
 233
 234     _TESTS = [{
 235         'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
 236         'info_dict': {
 237             'id': 'RedBullThre3style_tokyo-finalists-2015',
 238             'title': 'National Champions 2015',
 239             'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
 240         },
 241         'playlist_mincount': 16,
 242     }, {
 243         'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
 244         'info_dict': {
 245             'id': 'maxvibes_jazzcat-on-ness-radio',
 246             'title': 'Jazzcat on Ness Radio',
 247             'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
 248         },
 249         'playlist_mincount': 23
 250     }]
 251
 252     def _real_extract(self, url):
 253         mobj = re.match(self._VALID_URL, url)
 254         user_id = mobj.group('user')
 255         playlist_id = mobj.group('playlist')
 256         video_id = '%s_%s' % (user_id, playlist_id)
 257
 258         profile = self._download_webpage(
 259             url, user_id,
 260             note='Downloading playlist page',
 261             errnote='Unable to download playlist page')
 262
 263         description = self._get_user_description(profile)
 264         playlist_title = self._html_search_regex(
 265             r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
 266             profile, 'playlist title')
 267
 268         entries = OnDemandPagedList(
 269             functools.partial(
 270                 self._tracks_page_func,
 271                 '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
 272             self._PAGE_SIZE)
 273
 274         return self.playlist_result(entries, video_id, playlist_title, description)
 275
 276
 277 class MixcloudStreamIE(MixcloudPlaylistBaseIE):
 278     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
 279     IE_NAME = 'mixcloud:stream'
 280
 281     _TEST = {
 282         'url': 'https://www.mixcloud.com/FirstEar/stream/',
 283         'info_dict': {
 284             'id': 'FirstEar',
 285             'title': 'First Ear',
 286             'description': 'Curators of good music\nfirstearmusic.com',
 287         },
 288         'playlist_mincount': 192,
 289     }
 290
 291     def _real_extract(self, url):
 292         user_id = self._match_id(url)
 293
 294         webpage = self._download_webpage(url, user_id)
 295
 296         entries = []
 297         prev_page_url = None
 298
 299         def _handle_page(page):
 300             entries.extend(self._find_urls_in_page(page))
 301             return self._search_regex(
 302                 r'm-next-page-url="([^"]+)"', page,
 303                 'next page URL', default=None)
 304
 305         next_page_url = _handle_page(webpage)
 306
 307         for idx in itertools.count(0):
 308             if not next_page_url or prev_page_url == next_page_url:
 309                 break
 310
 311             prev_page_url = next_page_url
 312             current_page = int(self._search_regex(
 313                 r'\?page=(\d+)', next_page_url, 'next page number'))
 314
 315             next_page_url = _handle_page(self._fetch_tracks_page(
 316                 '%s/stream' % user_id, user_id, 'stream', idx,
 317                 real_page_number=current_page))
 318
 319         username = self._og_search_title(webpage)
 320         description = self._get_user_description(webpage)
 321
 322         return self.playlist_result(entries, user_id, username, description)