6 from .common
import InfoExtractor
7 from ..compat
import compat_urllib_parse_unquote
17 class MailRuIE(InfoExtractor
):
19 IE_DESC
= 'Видео@Mail.Ru'
22 (?:(?:www|m|videoapi)\.)?my\.mail\.ru/+
24 video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
25 (?:videos/embed/)?(?:(?P<idv2prefix>(?:[^/]+/+){2})(?:video/(?:embed/)?)?(?P<idv2suffix>[^/]+/\d+))(?:\.html)?|
26 (?:video/embed|\+/video/meta)/(?P<metaid>\d+)
31 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
32 'md5': 'dea205f03120046894db4ebb6159879a',
36 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
37 'timestamp': 1393235077,
38 'upload_date': '20140224',
39 'uploader': 'sonypicturesrus',
40 'uploader_id': 'sonypicturesrus@mail.ru',
43 'skip': 'Not accessible from Travis CI server',
46 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
47 'md5': '00a91a58c3402204dcced523777b475f',
49 'id': '46843144_1263',
51 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
52 'timestamp': 1397039888,
53 'upload_date': '20140409',
55 'uploader_id': 'hitech@corp.mail.ru',
58 'skip': 'Not accessible from Travis CI server',
61 # only available via metaUrl API
62 'url': 'http://my.mail.ru/mail/720pizle/video/_myvideo/502.html',
63 'md5': '3b26d2491c6949d031a32b96bd97c096',
68 'timestamp': 1449094163,
69 'upload_date': '20151202',
70 'uploader': '720pizle@mail.ru',
71 'uploader_id': '720pizle@mail.ru',
74 'skip': 'Not accessible from Travis CI server',
77 'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html',
78 'only_matching': True,
81 'url': 'https://my.mail.ru/video/embed/7949340477499637815',
82 'only_matching': True,
85 'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
86 'only_matching': True,
89 'url': 'https://my.mail.ru//list/sinyutin10/video/_myvideo/4.html',
90 'only_matching': True,
93 'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html',
94 'only_matching': True,
97 'url': 'https://my.mail.ru/mail/cloud-strife/video/embed/Games/2009',
98 'only_matching': True,
101 'url': 'https://videoapi.my.mail.ru/videos/embed/mail/cloud-strife/Games/2009.html',
102 'only_matching': True,
106 def _real_extract(self
, url
):
107 mobj
= self
._match
_valid
_url
(url
)
108 meta_id
= mobj
.group('metaid')
112 meta_url
= 'https://my.mail.ru/+/video/meta/%s' % meta_id
114 video_id
= mobj
.group('idv1')
116 video_id
= mobj
.group('idv2prefix') + mobj
.group('idv2suffix')
117 webpage
= self
._download
_webpage
(url
, video_id
)
118 page_config
= self
._parse
_json
(self
._search
_regex
([
119 r
'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>',
120 r
'(?s)"video":\s*({.+?}),'],
121 webpage
, 'page config', default
='{}'), video_id
, fatal
=False)
123 meta_url
= page_config
.get('metaUrl') or page_config
.get('video', {}).get('metaUrl') or page_config
.get('metadataUrl')
129 # fix meta_url if missing the host address
130 if re
.match(r
'^\/\+\/', meta_url
):
131 meta_url
= urljoin('https://my.mail.ru', meta_url
)
134 video_data
= self
._download
_json
(
135 meta_url
, video_id
or meta_id
, 'Downloading video meta JSON',
138 # Fallback old approach
140 video_data
= self
._download
_json
(
141 'http://api.video.mail.ru/videos/%s.json?new=1' % video_id
,
142 video_id
, 'Downloading video JSON')
144 video_key
= self
._get
_cookies
('https://my.mail.ru').get('video_key')
147 for f
in video_data
['videos']:
148 video_url
= f
.get('url')
152 self
._set
_cookie
(urllib
.parse
.urlparse(video_url
).hostname
, 'video_key', video_key
.value
)
153 format_id
= f
.get('key')
154 height
= int_or_none(self
._search
_regex
(
155 r
'^(\d+)[pP]$', format_id
, 'height', default
=None)) if format_id
else None
158 'format_id': format_id
,
162 meta_data
= video_data
['meta']
163 title
= remove_end(meta_data
['title'], '.mp4')
165 author
= video_data
.get('author')
166 uploader
= author
.get('name')
167 uploader_id
= author
.get('id') or author
.get('email')
168 view_count
= int_or_none(video_data
.get('viewsCount') or video_data
.get('views_count'))
170 acc_id
= meta_data
.get('accId')
171 item_id
= meta_data
.get('itemId')
172 content_id
= '%s_%s' % (acc_id
, item_id
) if acc_id
and item_id
else video_id
174 thumbnail
= meta_data
.get('poster')
175 duration
= int_or_none(meta_data
.get('duration'))
176 timestamp
= int_or_none(meta_data
.get('timestamp'))
181 'thumbnail': thumbnail
,
182 'timestamp': timestamp
,
183 'uploader': uploader
,
184 'uploader_id': uploader_id
,
185 'duration': duration
,
186 'view_count': view_count
,
191 class MailRuMusicSearchBaseIE(InfoExtractor
):
192 def _search(self
, query
, url
, audio_id
, limit
=100, offset
=0):
193 search
= self
._download
_json
(
194 'https://my.mail.ru/cgi-bin/my/ajax', audio_id
,
195 'Downloading songs JSON page %d' % (offset
// limit
+ 1),
198 'X-Requested-With': 'XMLHttpRequest',
202 'func_name': 'music.search',
207 'arg_search_params': json
.dumps({
214 'arg_offset': offset
,
216 return next(e
for e
in search
if isinstance(e
, dict))
219 def _extract_track(t
, fatal
=True):
220 audio_url
= t
['URL'] if fatal
else t
.get('URL')
224 audio_id
= t
['File'] if fatal
else t
.get('File')
228 thumbnail
= t
.get('AlbumCoverURL') or t
.get('FiledAlbumCover')
229 uploader
= t
.get('OwnerName') or t
.get('OwnerName_Text_HTML')
230 uploader_id
= t
.get('UploaderID')
231 duration
= int_or_none(t
.get('DurationInSeconds')) or parse_duration(
232 t
.get('Duration') or t
.get('DurationStr'))
233 view_count
= int_or_none(t
.get('PlayCount') or t
.get('PlayCount_hr'))
235 track
= t
.get('Name') or t
.get('Name_Text_HTML')
236 artist
= t
.get('Author') or t
.get('Author_Text_HTML')
239 title
= '%s - %s' % (artist
, track
) if artist
else track
244 'extractor_key': MailRuMusicIE
.ie_key(),
247 'thumbnail': thumbnail
,
248 'uploader': uploader
,
249 'uploader_id': uploader_id
,
250 'duration': duration
,
251 'view_count': view_count
,
253 'abr': int_or_none(t
.get('BitRate')),
256 'album': t
.get('Album'),
261 class MailRuMusicIE(MailRuMusicSearchBaseIE
):
262 IE_NAME
= 'mailru:music'
263 IE_DESC
= 'Музыка@Mail.Ru'
264 _VALID_URL
= r
'https?://my\.mail\.ru/+music/+songs/+[^/?#&]+-(?P<id>[\da-f]+)'
266 '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',
267 'md5': '0f8c22ef8c5d665b13ac709e63025610',
269 'id': '4e31f7125d0dfaef505d947642366893',
271 'title': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017 - М8Л8ТХ',
272 'uploader': 'Игорь Мудрый',
273 'uploader_id': '1459196328',
278 'track': 'L.A.H. (Luciferian Aesthetics of Herrschaft) single, 2017',
283 def _real_extract(self
, url
):
284 audio_id
= self
._match
_id
(url
)
286 webpage
= self
._download
_webpage
(url
, audio_id
)
288 title
= self
._og
_search
_title
(webpage
)
289 music_data
= self
._search
(title
, url
, audio_id
)['MusicData']
290 t
= next(t
for t
in music_data
if t
.get('File') == audio_id
)
292 info
= self
._extract
_track
(t
)
293 info
['title'] = title
297 class MailRuMusicSearchIE(MailRuMusicSearchBaseIE
):
298 IE_NAME
= 'mailru:music:search'
299 IE_DESC
= 'Музыка@Mail.Ru'
300 _VALID_URL
= r
'https?://my\.mail\.ru/+music/+search/+(?P<id>[^/?#&]+)'
302 'url': 'https://my.mail.ru/music/search/black%20shadow',
304 'id': 'black shadow',
306 'playlist_mincount': 532,
309 def _real_extract(self
, url
):
310 query
= compat_urllib_parse_unquote(self
._match
_id
(url
))
317 for _
in itertools
.count(1):
318 search
= self
._search
(query
, url
, query
, LIMIT
, offset
)
320 music_data
= search
.get('MusicData')
321 if not music_data
or not isinstance(music_data
, list):
325 track
= self
._extract
_track
(t
, fatal
=False)
327 entries
.append(track
)
330 search
, lambda x
: x
['Results']['music']['Total'], int)
332 if total
is not None:
338 return self
.playlist_result(entries
, query
)