aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/mixcloud.py
blob: 4811823802c46e709116ef2e2daefe53c123c70a (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
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
from __future__ import unicode_literals

import base64
import functools
import itertools
import re

from .common import InfoExtractor
from ..compat import (
    compat_chr,
    compat_ord,
    compat_urllib_parse_unquote,
    compat_urlparse,
    compat_zip
)
from ..utils import (
    clean_html,
    ExtractorError,
    OnDemandPagedList,
    str_to_int,
    try_get)


class MixcloudIE(InfoExtractor):
    _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?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': r're:https?://.*\.jpg',
            'view_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?://.*',
            'view_count': int,
        },
    }, {
        'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
        'only_matching': True,
    }]

    @staticmethod
    def _decrypt_xor_cipher(key, ciphertext):
        """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
        return ''.join([
            compat_chr(compat_ord(ch) ^ compat_ord(k))
            for ch, k in compat_zip(ciphertext, itertools.cycle(key))])

    @staticmethod
    def _decrypt_and_extend(stream_info, url_key, getter, key, formats):
        maybe_url = stream_info.get(url_key)
        if maybe_url is not None:
            decrypted = MixcloudIE._decrypt_xor_cipher(key, base64.b64decode(maybe_url))
            formats.extend(getter(decrypted))

    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)

        # Legacy path
        encrypted_play_info = self._search_regex(
            r'm-play-info="([^"]+)"', webpage, 'play info', default=None)

        if encrypted_play_info is not None:
            # Decode
            encrypted_play_info = base64.b64decode(encrypted_play_info)
        else:
            # New path
            full_info_json = self._parse_json(self._html_search_regex(
                r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>', webpage, 'play info'), 'play info')
            for item in full_info_json:
                item_data = try_get(item, lambda x: x['cloudcast']['data']['cloudcastLookup'])
                if try_get(item_data, lambda x: x['streamInfo']['url']):
                    info_json = item_data
                    break
            else:
                raise ExtractorError('Failed to extract matching stream info')

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

        js_url = self._search_regex(
            r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)',
            webpage, 'js url', default=None)
        if js_url is None:
            js_url = self._search_regex(
                r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js/www\.[^>]+\.js)',
                webpage, 'js url')
        js = self._download_webpage(js_url, track_id)
        # Known plaintext attack
        if encrypted_play_info:
            kps = ['{"stream_url":']
            kpa_target = encrypted_play_info
        else:
            kps = ['https://', 'http://']
            kpa_target = base64.b64decode(info_json['streamInfo']['url'])
        for kp in kps:
            partial_key = self._decrypt_xor_cipher(kpa_target, kp)
            for quote in ["'", '"']:
                key = self._search_regex(r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), js,
                                         "encryption key", default=None)
                if key is not None:
                    break
            else:
                continue
            break
        else:
            raise ExtractorError('Failed to extract encryption key')

        if encrypted_play_info is not None:
            play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info')
            if message and 'stream_url' not in play_info:
                raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
            song_url = play_info['stream_url']
            formats = [{
                'format_id': 'normal',
                'url': song_url
            }]

            title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
            thumbnail = self._proto_relative_url(self._html_search_regex(
                r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
            uploader = self._html_search_regex(
                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)
            view_count = str_to_int(self._search_regex(
                [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
                 r'/listeners/?">([0-9,.]+)</a>',
                 r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
                webpage, 'play count', default=None))

        else:
            title = info_json['name']
            thumbnail = try_get(info_json,
                                lambda x: 'https://thumbnailer.mixcloud.com/unsafe/600x600/' + x['picture']['urlRoot'])
            uploader = try_get(info_json, lambda x: x['owner']['displayName'])
            uploader_id = try_get(info_json, lambda x: x['owner']['username'])
            description = try_get(info_json, lambda x: x['description'])
            view_count = try_get(info_json, lambda x: x['plays'])

            stream_info = info_json['streamInfo']
            formats = []
            self._decrypt_and_extend(stream_info, 'url', lambda x: [{
                'format_id': 'normal',
                'url': x
            }], key, formats)
            self._decrypt_and_extend(stream_info, 'hlsUrl', lambda x: self._extract_m3u8_formats(x, title), key,
                                     formats)
            self._decrypt_and_extend(stream_info, 'dashUrl', lambda x: self._extract_mpd_formats(x, title), key,
                                     formats)

        return {
            'id': track_id,
            'title': title,
            'formats': formats,
            'description': description,
            'thumbnail': thumbnail,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'view_count': view_count,
        }


class MixcloudPlaylistBaseIE(InfoExtractor):
    _PAGE_SIZE = 24

    def _find_urls_in_page(self, page):
        for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page):
            yield self.url_result(
                compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
                MixcloudIE.ie_key())

    def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None):
        real_page_number = real_page_number or current_page + 1
        return self._download_webpage(
            'https://www.mixcloud.com/%s/' % path, video_id,
            note='Download %s (page %d)' % (page_name, current_page + 1),
            errnote='Unable to download %s' % page_name,
            query={'page': real_page_number, 'list': 'main', '_ajax': '1'},
            headers={'X-Requested-With': 'XMLHttpRequest'})

    def _tracks_page_func(self, page, video_id, page_name, current_page):
        resp = self._fetch_tracks_page(page, video_id, page_name, current_page)

        for item in self._find_urls_in_page(resp):
            yield item

    def _get_user_description(self, page_content):
        return self._html_search_regex(
            r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>',
            page_content, 'user description', fatal=False)


class MixcloudUserIE(MixcloudPlaylistBaseIE):
    _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:def36060ac8747b3aabca54924897e47',
        },
        'playlist_mincount': 11,
    }, {
        'url': 'http://www.mixcloud.com/dholbach/uploads/',
        'info_dict': {
            'id': 'dholbach_uploads',
            'title': 'Daniel Holbach (uploads)',
            'description': 'md5:def36060ac8747b3aabca54924897e47',
        },
        'playlist_mincount': 11,
    }, {
        'url': 'http://www.mixcloud.com/dholbach/favorites/',
        'info_dict': {
            'id': 'dholbach_favorites',
            'title': 'Daniel Holbach (favorites)',
            'description': 'md5:def36060ac8747b3aabca54924897e47',
        },
        'params': {
            'playlist_items': '1-100',
        },
        'playlist_mincount': 100,
    }, {
        'url': 'http://www.mixcloud.com/dholbach/listens/',
        'info_dict': {
            'id': 'dholbach_listens',
            'title': 'Daniel Holbach (listens)',
            'description': 'md5:def36060ac8747b3aabca54924897e47',
        },
        'params': {
            'playlist_items': '1-100',
        },
        'playlist_mincount': 100,
    }]

    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)

        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._og_search_title(profile)
        description = self._get_user_description(profile)

        entries = OnDemandPagedList(
            functools.partial(
                self._tracks_page_func,
                '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
            self._PAGE_SIZE, use_cache=True)

        return self.playlist_result(
            entries, video_id, '%s (%s)' % (username, list_type), description)


class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
    _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_tokyo-finalists-2015',
            'title': 'National Champions 2015',
            'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
        },
        'playlist_mincount': 16,
    }, {
        'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
        'only_matching': 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_%s' % (user_id, playlist_id)

        webpage = self._download_webpage(
            url, user_id,
            note='Downloading playlist page',
            errnote='Unable to download playlist page')

        title = self._html_search_regex(
            r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)',
            webpage, 'playlist title',
            default=None) or self._og_search_title(webpage, fatal=False)
        description = self._get_user_description(webpage)

        entries = OnDemandPagedList(
            functools.partial(
                self._tracks_page_func,
                '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
            self._PAGE_SIZE)

        return self.playlist_result(entries, video_id, title, description)


class MixcloudStreamIE(MixcloudPlaylistBaseIE):
    _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
    IE_NAME = 'mixcloud:stream'

    _TEST = {
        'url': 'https://www.mixcloud.com/FirstEar/stream/',
        'info_dict': {
            'id': 'FirstEar',
            'title': 'First Ear',
            'description': 'Curators of good music\nfirstearmusic.com',
        },
        'playlist_mincount': 192,
    }

    def _real_extract(self, url):
        user_id = self._match_id(url)

        webpage = self._download_webpage(url, user_id)

        entries = []
        prev_page_url = None

        def _handle_page(page):
            entries.extend(self._find_urls_in_page(page))
            return self._search_regex(
                r'm-next-page-url="([^"]+)"', page,
                'next page URL', default=None)

        next_page_url = _handle_page(webpage)

        for idx in itertools.count(0):
            if not next_page_url or prev_page_url == next_page_url:
                break

            prev_page_url = next_page_url
            current_page = int(self._search_regex(
                r'\?page=(\d+)', next_page_url, 'next page number'))

            next_page_url = _handle_page(self._fetch_tracks_page(
                '%s/stream' % user_id, user_id, 'stream', idx,
                real_page_number=current_page))

        username = self._og_search_title(webpage)
        description = self._get_user_description(webpage)

        return self.playlist_result(entries, user_id, username, description)