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