2 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from ..compat import compat_urllib_parse_unquote
18 class MailRuIE(InfoExtractor):
20 IE_DESC = 'Видео@Mail.Ru'
23 (?:(?:www|m)\.)?my\.mail\.ru/
25 video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
26 (?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
27 (?:video/embed|\+/video/meta)/(?P<metaid>\d+)
32 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
33 'md5': 'dea205f03120046894db4ebb6159879a',
37 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
38 'timestamp': 1393235077,
39 'upload_date': '20140224',
40 'uploader': 'sonypicturesrus',
41 'uploader_id': 'sonypicturesrus@mail.ru',
44 'skip': 'Not accessible from Travis CI server',
47 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
48 'md5': '00a91a58c3402204dcced523777b475f',
50 'id': '46843144_1263',
52 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
53 'timestamp': 1397039888,
54 'upload_date': '20140409',
56 'uploader_id': 'hitech@corp.mail.ru',
59 'skip': 'Not accessible from Travis CI server',
62 # only available via metaUrl API
63 'url': 'http://my.mail.ru/mail/720pizle/video/_myvideo/502.html',
64 'md5': '3b26d2491c6949d031a32b96bd97c096',
69 'timestamp': 1449094163,
70 'upload_date': '20151202',
71 'uploader': '720pizle@mail.ru',
72 'uploader_id': '720pizle@mail.ru',
75 'skip': 'Not accessible from Travis CI server',
78 'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html',
79 'only_matching': True,
82 'url': 'https://my.mail.ru/video/embed/7949340477499637815',
83 'only_matching': True,
86 'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
87 'only_matching': True,
91 def _real_extract(self, url):
92 mobj = re.match(self._VALID_URL, url)
93 meta_id = mobj.group('metaid')
97 meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id
99 video_id = mobj.group('idv1')
101 video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix')
102 webpage = self._download_webpage(url, video_id)
103 page_config = self._parse_json(self._search_regex(
104 r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
105 webpage, 'page config', default='{}'), video_id, fatal=False)
107 meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl')
113 video_data = self._download_json(
114 meta_url, video_id or meta_id, 'Downloading video meta JSON',
117 # Fallback old approach
119 video_data = self._download_json(
120 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id,
121 video_id, 'Downloading video JSON')
124 for f in video_data['videos']:
125 video_url = f.get('url')
128 format_id = f.get('key')
129 height = int_or_none(self._search_regex(
130 r'^(\d+)[pP]$', format_id, 'height', default=None)) if format_id else None
133 'format_id': format_id,
136 self._sort_formats(formats)
138 meta_data = video_data['meta']
139 title = remove_end(meta_data['title'], '.mp4')
141 author = video_data.get('author')
142 uploader = author.get('name')
143 uploader_id = author.get('id') or author.get('email')
144 view_count = int_or_none(video_data.get('viewsCount') or video_data.get('views_count'))
146 acc_id = meta_data.get('accId')
147 item_id = meta_data.get('itemId')
148 content_id = '%s_%s' % (acc_id, item_id) if acc_id and item_id else video_id
150 thumbnail = meta_data.get('poster')
151 duration = int_or_none(meta_data.get('duration'))
152 timestamp = int_or_none(meta_data.get('timestamp'))
157 'thumbnail': thumbnail,
158 'timestamp': timestamp,
159 'uploader': uploader,
160 'uploader_id': uploader_id,
161 'duration': duration,
162 'view_count': view_count,
167 class MailRuMusicSearchBaseIE(InfoExtractor):
168 def _search(self, query, url, audio_id, limit=100, offset=0):
169 search = self._download_json(
170 'https://my.mail.ru/cgi-bin/my/ajax', audio_id,
171 'Downloading songs JSON page %d' % (offset // limit + 1),
174 'X-Requested-With': 'XMLHttpRequest',
178 'func_name': 'music.search',
183 'arg_search_params': json.dumps({
190 'arg_offset': offset,
192 return next(e for e in search if isinstance(e, dict))
195 def _extract_track(t, fatal=True):
196 audio_url = t['URL'] if fatal else t.get('URL')
200 audio_id = t['File'] if fatal else t.get('File')
204 thumbnail = t.get('AlbumCoverURL') or t.get('FiledAlbumCover')
205 uploader = t.get('OwnerName') or t.get('OwnerName_Text_HTML')
206 uploader_id = t.get('UploaderID')
207 duration = int_or_none(t.get('DurationInSeconds')) or parse_duration(
208 t.get('Duration') or t.get('DurationStr'))
209 view_count = int_or_none(t.get('PlayCount') or t.get('PlayCount_hr'))
211 track = t.get('Name') or t.get('Name_Text_HTML')
212 artist = t.get('Author') or t.get('Author_Text_HTML')
215 title = '%s - %s' % (artist, track) if artist else track
220 'extractor_key': MailRuMusicIE.ie_key(),
223 'thumbnail': thumbnail,
224 'uploader': uploader,
225 'uploader_id': uploader_id,
226 'duration': duration,
227 'view_count': view_count,
229 'abr': int_or_none(t.get('BitRate')),
232 'album': t.get('Album'),
237 class MailRuMusicIE(MailRuMusicSearchBaseIE):
238 IE_NAME = 'mailru:music'
239 IE_DESC = 'Музыка@Mail.Ru'
240 _VALID_URL = r'https?://my\.mail\.ru/music/songs/[^/?#&]+-(?P<id>[\da-f]+)'
242 'url': 'https://my.mail.ru/music/songs/%D0%BC8%D0%BB8%D1%82%D1%85-l-a-h-luciferian-aesthetics-of-herrschaft-single-2017-4e31f7125d0dfaef505d947642366893',
243 'md5': '0f8c22ef8c5d665b13ac709e63025610',
245 'id': '4e31f7125d0dfaef505d947642366893',
247 'title': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017 - М8Л8ТХ',
248 'uploader': 'Игорь Мудрый',
249 'uploader_id': '1459196328',
254 'track': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017',
259 def _real_extract(self, url):
260 audio_id = self._match_id(url)
262 webpage = self._download_webpage(url, audio_id)
264 title = self._og_search_title(webpage)
265 music_data = self._search(title, url, audio_id)['MusicData']
266 t = next(t for t in music_data if t.get('File') == audio_id)
268 info = self._extract_track(t)
269 info['title'] = title
273 class MailRuMusicSearchIE(MailRuMusicSearchBaseIE):
274 IE_NAME = 'mailru:music:search'
275 IE_DESC = 'Музыка@Mail.Ru'
276 _VALID_URL = r'https?://my\.mail\.ru/music/search/(?P<id>[^/?#&]+)'
278 'url': 'https://my.mail.ru/music/search/black%20shadow',
280 'id': 'black shadow',
282 'playlist_mincount': 532,
285 def _real_extract(self, url):
286 query = compat_urllib_parse_unquote(self._match_id(url))
293 for _ in itertools.count(1):
294 search = self._search(query, url, query, LIMIT, offset)
296 music_data = search.get('MusicData')
297 if not music_data or not isinstance(music_data, list):
301 track = self._extract_track(t, fatal=False)
303 entries.append(track)
306 search, lambda x: x['Results']['music']['Total'], int)
308 if total is not None:
314 return self.playlist_result(entries, query)