aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mixcloud.py
blob: 30b33e7e98581fb0142d30837276dc476f6acd49 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_urllib_parse_unquote,
    compat_urllib_request
)
from ..utils import (
    ExtractorError,
    HEADRequest,
    NO_DEFAULT,
    parse_count,
    str_to_int,
    clean_html
)


class MixcloudIE(InfoExtractor):
    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
    IE_NAME = 'mixcloud'

    _TESTS = [{
        'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
        'info_dict': {
            'id': 'dholbach-cryptkeeper',
            'ext': 'm4a',
            'title': 'Cryptkeeper',
            'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
            'uploader': 'Daniel Holbach',
            'uploader_id': 'dholbach',
            'thumbnail': 're:https?://.*\.jpg',
            'view_count': int,
            'like_count': int,
        },
    }, {
        'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
        'info_dict': {
            'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
            'ext': 'mp3',
            'title': 'Caribou 7 inch Vinyl Mix & Chat',
            'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
            'uploader': 'Gilles Peterson Worldwide',
            'uploader_id': 'gillespeterson',
            'thumbnail': 're:https?://.*/images/',
            'view_count': int,
            'like_count': int,
        },
    }]

    def _check_url(self, url, track_id, ext):
        try:
            # We only want to know if the request succeed
            # don't download the whole file
            self._request_webpage(
                HEADRequest(url), track_id,
                'Trying %s URL' % ext)
            return True
        except ExtractorError:
            return False

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        uploader = mobj.group(1)
        cloudcast_name = mobj.group(2)
        track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))

        webpage = self._download_webpage(url, track_id)

        message = self._html_search_regex(
            r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
            webpage, 'error message', default=None)

        preview_url = self._search_regex(
            r'\s(?:data-preview-url|m-preview)="([^"]+)"',
            webpage, 'preview url', default=None if message else NO_DEFAULT)

        if message:
            raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)

        song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
        song_url = song_url.replace('/previews/', '/c/originals/')
        if not self._check_url(song_url, track_id, 'mp3'):
            song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
            if not self._check_url(song_url, track_id, 'm4a'):
                raise ExtractorError('Unable to extract track url')

        PREFIX = (
            r'm-play-on-spacebar[^>]+'
            r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
        title = self._html_search_regex(
            PREFIX + r'm-title="([^"]+)"', webpage, 'title')
        thumbnail = self._proto_relative_url(self._html_search_regex(
            PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail',
            fatal=False))
        uploader = self._html_search_regex(
            PREFIX + r'm-owner-name="([^"]+)"',
            webpage, 'uploader', fatal=False)
        uploader_id = self._search_regex(
            r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
        description = self._og_search_description(webpage)
        like_count = parse_count(self._search_regex(
            r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
            webpage, 'like count', fatal=False))
        view_count = str_to_int(self._search_regex(
            [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
             r'/listeners/?">([0-9,.]+)</a>'],
            webpage, 'play count', fatal=False))

        return {
            'id': track_id,
            'title': title,
            'url': song_url,
            'description': description,
            'thumbnail': thumbnail,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'view_count': view_count,
            'like_count': like_count,
        }


class MixcloudUserIE(InfoExtractor):
    """
    Information extractor for Mixcloud users.
    It can retrieve a list of a user's uploads, favorites or listens.
    """

    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
    IE_NAME = 'mixcloud:user'

    _TESTS = [{
        'url': 'http://www.mixcloud.com/dholbach/',
        'info_dict': {
            'id': 'dholbach/uploads',
            'title': 'Daniel Holbach (uploads)',
            'description': 'md5:327af72d1efeb404a8216c27240d1370',
        },
        'playlist_mincount': 11
    }, {
        'url': 'http://www.mixcloud.com/dholbach/uploads/',
        'info_dict': {
            'id': 'dholbach/uploads',
            'title': 'Daniel Holbach (uploads)',
            'description': 'md5:327af72d1efeb404a8216c27240d1370',
        },
        'playlist_mincount': 11
    }, {
        'url': 'http://www.mixcloud.com/dholbach/favorites/',
        'info_dict': {
            'id': 'dholbach/favorites',
            'title': 'Daniel Holbach (favorites)',
            'description': 'md5:327af72d1efeb404a8216c27240d1370',
        },
        'playlist_mincount': 244
    }, {
        'url': 'http://www.mixcloud.com/dholbach/listens/',
        'info_dict': {
            'id': 'dholbach/listens',
            'title': 'Daniel Holbach (listens)',
            'description': 'md5:327af72d1efeb404a8216c27240d1370',
        },
        'playlist_mincount': 846
    }]

    def _fetch_tracks(self, base_url, video_id, dl_note=None, dl_errnote=None):
        # retrieve all fragments of a list of tracks with fake AJAX calls
        track_urls = []
        current_page = 1
        while True:
            # fake a AJAX request to retrieve a list fragment
            page_url = base_url + "?page=%d&list=main&_ajax=1" % current_page
            req = compat_urllib_request.Request(page_url, headers={"X-Requested-With": "XMLHttpRequest"})
            resp = self._download_webpage(req, video_id, note=dl_note + " (page %d)" % current_page, errnote=dl_errnote)

            # extract all track URLs from fragment
            urls = re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', resp)
            # clean up URLs
            urls = map(clean_html, urls)
            # create absolute URLs
            urls = map(lambda u: "https://www.mixcloud.com" + u, urls)
            track_urls.extend(urls)

            # advance to next fragment, if any
            if " m-next-page-url=" in resp:
                current_page += 1
            else:
                break

        return track_urls

    def _handle_track_urls(self, urls):
        return map(lambda u: self.url_result(u, "Mixcloud"), urls)

    def _get_user_description(self, page_content):
        return self._html_search_regex(
            r'<div class="description-text">.*?<p>(.*?)</p></div></div></div>',
            page_content,
            "user description",
            fatal=False)

    def _get_username(self, page_content):
        return self._og_search_title(page_content)

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user_id = mobj.group("user")
        list_type = mobj.group("type")

        # if only a profile URL was supplied, default to download all uploads
        if list_type is None:
            list_type = "uploads"

        video_id = "%s/%s" % (user_id, list_type)

        # download the user's profile to retrieve some metadata
        profile = self._download_webpage("https://www.mixcloud.com/%s/" % user_id,
                                         video_id,
                                         note="Downloading user profile",
                                         errnote="Unable to download user profile")

        username = self._get_username(profile)
        description = self._get_user_description(profile)

        # retrieve all page fragments of uploads, favorites or listens
        track_urls = self._fetch_tracks(
            "https://www.mixcloud.com/%s/%s/" % (user_id, list_type),
            video_id,
            dl_note="Downloading list of %s" % list_type,
            dl_errnote="Unable to download list of %s" % list_type)

        # let MixcloudIE handle each track URL
        entries = self._handle_track_urls(track_urls)

        return {
            '_type': 'playlist',
            'entries': entries,
            'title': "%s (%s)" % (username, list_type),
            'id': video_id,
            "description": description
        }


class MixcloudPlaylistIE(MixcloudUserIE):
    """
    Information extractor for Mixcloud playlists.
    """

    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
    IE_NAME = 'mixcloud:playlist'

    _TESTS = [{
        'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
        'info_dict': {
            'id': 'RedBullThre3style/playlists/tokyo-finalists-2015',
            'title': 'National Champions 2015',
            'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
        },
        'playlist_mincount': 16
    }, {
        'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
        'info_dict': {
            'id': 'maxvibes/playlists/jazzcat-on-ness-radio',
            'title': 'Jazzcat on Ness Radio',
            'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
        },
        'playlist_mincount': 23
    }]

    def _get_playlist_title(self, page_content):
        return self._html_search_regex(
            r'<span class="main-list-title list-playlist-title ">(?P<title>.*?)</span>',
            page_content,
            "playlist title",
            group="title",
            fatal=True
        )

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        user_id = mobj.group("user")
        playlist_id = mobj.group("playlist")
        video_id = "%s/playlists/%s" % (user_id, playlist_id)

        # download the playlist page to retrieve some metadata
        profile = 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._get_playlist_title(profile)

        # retrieve all page fragments of playlist
        track_urls = self._fetch_tracks(
            "https://www.mixcloud.com/%s/playlists/%s/" % (user_id, playlist_id),
            video_id,
            dl_note="Downloading tracklist of %s" % playlist_title,
            dl_errnote="Unable to tracklist of %s" % playlist_title)

        # let MixcloudIE handle each track
        entries = self._handle_track_urls(track_urls)

        return {
            '_type': 'playlist',
            'entries': entries,
            'title': playlist_title,
            'id': video_id,
            "description": description
        }