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

   1 from __future__ import unicode_literals
   2
   3 import functools
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_unquote,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     clean_html,
  13     ExtractorError,
  14     HEADRequest,
  15     OnDemandPagedList,
  16     NO_DEFAULT,
  17     parse_count,
  18     str_to_int,
  19 )
  20
  21
  22 class MixcloudIE(InfoExtractor):
  23     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
  24     IE_NAME = 'mixcloud'
  25
  26     _TESTS = [{
  27         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
  28         'info_dict': {
  29             'id': 'dholbach-cryptkeeper',
  30             'ext': 'm4a',
  31             'title': 'Cryptkeeper',
  32             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
  33             'uploader': 'Daniel Holbach',
  34             'uploader_id': 'dholbach',
  35             'thumbnail': 're:https?://.*\.jpg',
  36             'view_count': int,
  37             'like_count': int,
  38         },
  39     }, {
  40         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
  41         'info_dict': {
  42             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
  43             'ext': 'mp3',
  44             'title': 'Caribou 7 inch Vinyl Mix & Chat',
  45             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
  46             'uploader': 'Gilles Peterson Worldwide',
  47             'uploader_id': 'gillespeterson',
  48             'thumbnail': 're:https?://.*/images/',
  49             'view_count': int,
  50             'like_count': int,
  51         },
  52     }]
  53
  54     def _check_url(self, url, track_id, ext):
  55         try:
  56             # We only want to know if the request succeed
  57             # don't download the whole file
  58             self._request_webpage(
  59                 HEADRequest(url), track_id,
  60                 'Trying %s URL' % ext)
  61             return True
  62         except ExtractorError:
  63             return False
  64
  65     def _real_extract(self, url):
  66         mobj = re.match(self._VALID_URL, url)
  67         uploader = mobj.group(1)
  68         cloudcast_name = mobj.group(2)
  69         track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
  70
  71         webpage = self._download_webpage(url, track_id)
  72
  73         message = self._html_search_regex(
  74             r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
  75             webpage, 'error message', default=None)
  76
  77         preview_url = self._search_regex(
  78             r'\s(?:data-preview-url|m-preview)="([^"]+)"',
  79             webpage, 'preview url', default=None if message else NO_DEFAULT)
  80
  81         if message:
  82             raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
  83
  84         song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
  85         song_url = song_url.replace('/previews/', '/c/originals/')
  86         if not self._check_url(song_url, track_id, 'mp3'):
  87             song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
  88             if not self._check_url(song_url, track_id, 'm4a'):
  89                 raise ExtractorError('Unable to extract track url')
  90
  91         PREFIX = (
  92             r'm-play-on-spacebar[^>]+'
  93             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
  94         title = self._html_search_regex(
  95             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
  96         thumbnail = self._proto_relative_url(self._html_search_regex(
  97             PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
  98             fatal=False))
  99         uploader = self._html_search_regex(
 100             PREFIX + r'm-owner-name="([^"]+)"',
 101             webpage, 'uploader', fatal=False)
 102         uploader_id = self._search_regex(
 103             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
 104         description = self._og_search_description(webpage)
 105         like_count = parse_count(self._search_regex(
 106             r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
 107             webpage, 'like count', fatal=False))
 108         view_count = str_to_int(self._search_regex(
 109             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
 110              r'/listeners/?">([0-9,.]+)</a>'],
 111             webpage, 'play count', fatal=False))
 112
 113         return {
 114             'id': track_id,
 115             'title': title,
 116             'url': song_url,
 117             'description': description,
 118             'thumbnail': thumbnail,
 119             'uploader': uploader,
 120             'uploader_id': uploader_id,
 121             'view_count': view_count,
 122             'like_count': like_count,
 123         }
 124
 125
 126 class MixcloudPlaylistBaseIE(InfoExtractor):
 127     _PAGE_SIZE = 24
 128
 129     def _fetch_tracks_page(self, path, video_id, page_name, current_page):
 130         resp = self._download_webpage(
 131             'https://www.mixcloud.com/%s/' % path, video_id,
 132             note='Download %s (page %d)' % (page_name, current_page + 1),
 133             errnote='Unable to download %s' % page_name,
 134             query={'page': (current_page + 1), 'list': 'main', '_ajax': '1'},
 135             headers={'X-Requested-With': 'XMLHttpRequest'})
 136
 137         for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', resp):
 138             yield self.url_result(
 139                 compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
 140                 MixcloudIE.ie_key())
 141
 142     def _get_user_description(self, page_content):
 143         return self._html_search_regex(
 144             r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
 145             page_content, 'user description', fatal=False)
 146
 147
 148 class MixcloudUserIE(MixcloudPlaylistBaseIE):
 149     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
 150     IE_NAME = 'mixcloud:user'
 151
 152     _TESTS = [{
 153         'url': 'http://www.mixcloud.com/dholbach/',
 154         'info_dict': {
 155             'id': 'dholbach_uploads',
 156             'title': 'Daniel Holbach (uploads)',
 157             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 158         },
 159         'playlist_mincount': 11,
 160     }, {
 161         'url': 'http://www.mixcloud.com/dholbach/uploads/',
 162         'info_dict': {
 163             'id': 'dholbach_uploads',
 164             'title': 'Daniel Holbach (uploads)',
 165             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 166         },
 167         'playlist_mincount': 11,
 168     }, {
 169         'url': 'http://www.mixcloud.com/dholbach/favorites/',
 170         'info_dict': {
 171             'id': 'dholbach_favorites',
 172             'title': 'Daniel Holbach (favorites)',
 173             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 174         },
 175         'params': {
 176             'playlist_items': '1-100',
 177         },
 178         'playlist_mincount': 100,
 179     }, {
 180         'url': 'http://www.mixcloud.com/dholbach/listens/',
 181         'info_dict': {
 182             'id': 'dholbach_listens',
 183             'title': 'Daniel Holbach (listens)',
 184             'description': 'md5:327af72d1efeb404a8216c27240d1370',
 185         },
 186         'params': {
 187             'playlist_items': '1-100',
 188         },
 189         'playlist_mincount': 100,
 190     }]
 191
 192     def _real_extract(self, url):
 193         mobj = re.match(self._VALID_URL, url)
 194         user_id = mobj.group('user')
 195         list_type = mobj.group('type')
 196
 197         # if only a profile URL was supplied, default to download all uploads
 198         if list_type is None:
 199             list_type = 'uploads'
 200
 201         video_id = '%s_%s' % (user_id, list_type)
 202
 203         profile = self._download_webpage(
 204             'https://www.mixcloud.com/%s/' % user_id, video_id,
 205             note='Downloading user profile',
 206             errnote='Unable to download user profile')
 207
 208         username = self._og_search_title(profile)
 209         description = self._get_user_description(profile)
 210
 211         entries = OnDemandPagedList(
 212             functools.partial(
 213                 self._fetch_tracks_page,
 214                 '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
 215             self._PAGE_SIZE, use_cache=True)
 216
 217         return self.playlist_result(
 218             entries, video_id, '%s (%s)' % (username, list_type), description)
 219
 220
 221 class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
 222     _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
 223     IE_NAME = 'mixcloud:playlist'
 224
 225     _TESTS = [{
 226         'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
 227         'info_dict': {
 228             'id': 'RedBullThre3style_tokyo-finalists-2015',
 229             'title': 'National Champions 2015',
 230             'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
 231         },
 232         'playlist_mincount': 16,
 233     }, {
 234         'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
 235         'info_dict': {
 236             'id': 'maxvibes_jazzcat-on-ness-radio',
 237             'title': 'Jazzcat on Ness Radio',
 238             'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
 239         },
 240         'playlist_mincount': 23
 241     }]
 242
 243     def _real_extract(self, url):
 244         mobj = re.match(self._VALID_URL, url)
 245         user_id = mobj.group('user')
 246         playlist_id = mobj.group('playlist')
 247         video_id = '%s_%s' % (user_id, playlist_id)
 248
 249         profile = self._download_webpage(
 250             url, user_id,
 251             note='Downloading playlist page',
 252             errnote='Unable to download playlist page')
 253
 254         description = self._get_user_description(profile)
 255         playlist_title = self._html_search_regex(
 256             r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
 257             profile, 'playlist title')
 258
 259         entries = OnDemandPagedList(
 260             functools.partial(
 261                 self._fetch_tracks_page,
 262                 '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
 263             self._PAGE_SIZE)
 264
 265         return self.playlist_result(entries, video_id, playlist_title, description)