2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
10 compat_urllib_parse_urlencode
,
24 class VLiveIE(InfoExtractor
):
26 _VALID_URL
= r
'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)'
27 _NETRC_MACHINE
= 'vlive'
29 'url': 'http://www.vlive.tv/video/1326',
30 'md5': 'cc7314812855ce56de70a06a27314983',
34 'title': "[V LIVE] Girl's Day's Broadcast",
35 'creator': "Girl's Day",
39 'url': 'http://www.vlive.tv/video/16937',
43 'title': '[V LIVE] 첸백시 걍방',
46 'subtitles': 'mincount:12',
49 'skip_download': True,
52 'url': 'https://www.vlive.tv/video/129100',
53 'md5': 'ca2569453b79d66e5b919e5d308bff6b',
57 'title': '[V LIVE] [BTS+] Run BTS! 2019 - EP.71 :: Behind the scene',
60 'subtitles': 'mincount:10',
62 'skip': 'This video is only available for CH+ subscribers',
66 def suitable(cls
, url
):
67 return False if VLivePlaylistIE
.suitable(url
) else super(VLiveIE
, cls
).suitable(url
)
69 def _real_initialize(self
):
73 email
, password
= self
._get
_login
_info
()
74 if None in (email
, password
):
78 login_info
= self
._download
_json
(
79 'https://www.vlive.tv/auth/loginInfo', None,
80 note
='Downloading login info',
81 headers
={'Referer': 'https://www.vlive.tv/home'})
83 login_info
, lambda x
: x
['message']['login'], bool) or False
85 LOGIN_URL
= 'https://www.vlive.tv/auth/email/login'
86 self
._request
_webpage
(
87 LOGIN_URL
, None, note
='Downloading login cookies')
89 self
._download
_webpage
(
90 LOGIN_URL
, None, note
='Logging in',
91 data
=urlencode_postdata({'email': email
, 'pwd': password
}),
94 'Content-Type': 'application/x-www-form-urlencoded'
97 if not is_logged_in():
98 raise ExtractorError('Unable to log in', expected
=True)
100 def _real_extract(self
, url
):
101 video_id
= self
._match
_id
(url
)
103 webpage
= self
._download
_webpage
(
104 'https://www.vlive.tv/video/%s' % video_id
, video_id
)
106 VIDEO_PARAMS_RE
= r
'\bvlive\.video\.init\(([^)]+)'
107 VIDEO_PARAMS_FIELD
= 'video params'
109 params
= self
._parse
_json
(self
._search
_regex
(
110 VIDEO_PARAMS_RE
, webpage
, VIDEO_PARAMS_FIELD
, default
=''), video_id
,
111 transform_source
=lambda s
: '[' + s
+ ']', fatal
=False)
113 if not params
or len(params
) < 7:
114 params
= self
._search
_regex
(
115 VIDEO_PARAMS_RE
, webpage
, VIDEO_PARAMS_FIELD
)
116 params
= [p
.strip(r
'"') for p
in re
.split(r
'\s*,\s*', params
)]
118 status
, long_video_id
, key
= params
[2], params
[5], params
[6]
119 status
= remove_start(status
, 'PRODUCT_')
121 if status
in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'):
122 return self
._live
(video_id
, webpage
)
123 elif status
in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'):
124 return self
._replay
(video_id
, webpage
, long_video_id
, key
)
126 if status
== 'LIVE_END':
127 raise ExtractorError('Uploading for replay. Please wait...',
129 elif status
== 'COMING_SOON':
130 raise ExtractorError('Coming soon!', expected
=True)
131 elif status
== 'CANCELED':
132 raise ExtractorError('We are sorry, '
133 'but the live broadcast has been canceled.',
135 elif status
== 'ONLY_APP':
136 raise ExtractorError('Unsupported video type', expected
=True)
138 raise ExtractorError('Unknown status %s' % status
)
140 def _get_common_fields(self
, webpage
):
141 title
= self
._og
_search
_title
(webpage
)
142 creator
= self
._html
_search
_regex
(
143 r
'<div[^>]+class="info_area"[^>]*>\s*(?:<em[^>]*>.*?</em\s*>\s*)?<a\s+[^>]*>([^<]+)',
144 webpage
, 'creator', fatal
=False)
145 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
149 'thumbnail': thumbnail
,
152 def _live(self
, video_id
, webpage
):
153 init_page
= self
._download
_init
_page
(video_id
)
155 live_params
= self
._search
_regex
(
156 r
'"liveStreamInfo"\s*:\s*(".*"),',
157 init_page
, 'live stream info')
158 live_params
= self
._parse
_json
(live_params
, video_id
)
159 live_params
= self
._parse
_json
(live_params
, video_id
)
162 for vid
in live_params
.get('resolutions', []):
163 formats
.extend(self
._extract
_m
3u8_formats
(
164 vid
['cdnUrl'], video_id
, 'mp4',
165 m3u8_id
=vid
.get('name'),
166 fatal
=False, live
=True))
167 self
._sort
_formats
(formats
)
169 info
= self
._get
_common
_fields
(webpage
)
171 'title': self
._live
_title
(info
['title']),
178 def _replay(self
, video_id
, webpage
, long_video_id
, key
):
179 if '' in (long_video_id
, key
):
180 init_page
= self
._download
_init
_page
(video_id
)
181 video_info
= self
._parse
_json
(self
._search
_regex
(
182 (r
'(?s)oVideoStatus\s*=\s*({.+?})\s*</script',
183 r
'(?s)oVideoStatus\s*=\s*({.+})'), init_page
, 'video info'),
185 if video_info
.get('status') == 'NEED_CHANNEL_PLUS':
186 self
.raise_login_required(
187 'This video is only available for CH+ subscribers')
188 long_video_id
, key
= video_info
['vid'], video_info
['inkey']
190 playinfo
= self
._download
_json
(
191 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s'
192 % compat_urllib_parse_urlencode({
193 'videoId': long_video_id
,
196 'doct': 'json', # document type (xml or json)
197 'cpt': 'vtt', # captions type (vtt or ttml)
201 'url': vid
['source'],
202 'format_id': vid
.get('encodingOption', {}).get('name'),
203 'abr': float_or_none(vid
.get('bitrate', {}).get('audio')),
204 'vbr': float_or_none(vid
.get('bitrate', {}).get('video')),
205 'width': int_or_none(vid
.get('encodingOption', {}).get('width')),
206 'height': int_or_none(vid
.get('encodingOption', {}).get('height')),
207 'filesize': int_or_none(vid
.get('size')),
208 } for vid
in playinfo
.get('videos', {}).get('list', []) if vid
.get('source')]
209 self
._sort
_formats
(formats
)
211 view_count
= int_or_none(playinfo
.get('meta', {}).get('count'))
214 for caption
in playinfo
.get('captions', {}).get('list', []):
215 lang
= dict_get(caption
, ('locale', 'language', 'country', 'label'))
216 if lang
and caption
.get('source'):
219 'url': caption
['source']}]
221 info
= self
._get
_common
_fields
(webpage
)
225 'view_count': view_count
,
226 'subtitles': subtitles
,
230 def _download_init_page(self
, video_id
):
231 return self
._download
_webpage
(
232 'https://www.vlive.tv/video/init/view',
233 video_id
, note
='Downloading live webpage',
234 data
=urlencode_postdata({'videoSeq': video_id
}),
236 'Referer': 'https://www.vlive.tv/video/%s' % video_id
,
237 'Content-Type': 'application/x-www-form-urlencoded'
241 class VLiveChannelIE(InfoExtractor
):
242 IE_NAME
= 'vlive:channel'
243 _VALID_URL
= r
'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)'
245 'url': 'http://channels.vlive.tv/FCD4B',
250 'playlist_mincount': 110
252 _APP_ID
= '8c6cc7b45d2568fb668be6e05b6e5a3b'
254 def _real_extract(self
, url
):
255 channel_code
= self
._match
_id
(url
)
257 webpage
= self
._download
_webpage
(
258 'http://channels.vlive.tv/%s/video' % channel_code
, channel_code
)
262 app_js_url
= self
._search
_regex
(
263 r
'<script[^>]+src=(["\'])(?P
<url
>http
.+?
/app\
.js
.*?
)\
1',
264 webpage, 'app js
', default=None, group='url
')
267 app_js = self._download_webpage(
268 app_js_url, channel_code, 'Downloading app JS
', fatal=False)
270 app_id = self._search_regex(
271 r'Global\
.VFAN_APP_ID\s
*=\s
*[\'"]([^\'"]+)[\'"]',
272 app_js, 'app id', default=None)
274 app_id = app_id or self._APP_ID
276 channel_info = self._download_json(
277 'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode',
278 channel_code, note='Downloading decode channel code',
281 'channelCode': channel_code,
282 '_': int(time.time())
285 channel_seq = channel_info['result']['channelSeq']
289 for page_num in itertools.count(1):
290 video_list = self._download_json(
291 'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList',
292 channel_code, note='Downloading channel list page #%d' % page_num,
295 'channelSeq': channel_seq,
296 # Large values of maxNumOfRows (~300 or above) may cause
297 # empty responses (see [1]), e.g. this happens for [2] that
298 # has more than 300 videos.
299 # 1. https://github.com/ytdl-org/youtube-dl/issues/13830
300 # 2. http://channels.vlive.tv/EDBF.
302 '_': int(time.time()),
308 channel_name = try_get(
310 lambda x: x['result']['channelInfo']['channelName'],
314 video_list, lambda x: x['result']['videoList'], list)
319 video_id = video.get('videoSeq')
322 video_id = compat_str(video_id)
325 'http://www.vlive.tv/video/%s' % video_id,
326 ie=VLiveIE.ie_key(), video_id=video_id))
328 return self.playlist_result(
329 entries, channel_code, channel_name)
332 class VLivePlaylistIE(InfoExtractor):
333 IE_NAME = 'vlive:playlist'
334 _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
335 _VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
337 # regular working playlist
338 'url': 'https://www.vlive.tv/video/117956/playlist/117963',
341 'title': '아이돌룸(IDOL ROOM) 41회 - (여자)아이들'
343 'playlist_mincount': 10
345 # playlist with no playlistVideoSeqs
346 'url': 'http://www.vlive.tv/video/22867/playlist/22912',
350 'title': '[V LIVE] Valentine Day Message from MINA',
355 'skip_download': True,
359 def _build_video_result(self, video_id, message):
360 self.to_screen(message)
361 return self.url_result(
362 self._VIDEO_URL_TEMPLATE % video_id,
363 ie=VLiveIE.ie_key(), video_id=video_id)
365 def _real_extract(self, url):
366 mobj = re.match(self._VALID_URL, url)
367 video_id, playlist_id = mobj.group('video_id', 'id')
369 if self._downloader.params.get('noplaylist'):
370 return self._build_video_result(
372 'Downloading just video %s because of --no-playlist'
376 'Downloading playlist %s - add --no-playlist to just download video'
379 webpage = self._download_webpage(
380 'http://www.vlive.tv/video/%s/playlist/%s'
381 % (video_id, playlist_id), playlist_id)
383 raw_item_ids = self._search_regex(
384 r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
385 'playlist video seqs', default=None, fatal=False)
388 return self._build_video_result(
390 'Downloading just video %s because no playlist was found'
393 item_ids = self._parse_json(raw_item_ids, playlist_id)
397 self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
398 video_id=compat_str(item_id))
399 for item_id in item_ids]
401 playlist_name = self._html_search_regex(
402 r'<div[^>]+class="[^
"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)',
403 webpage, 'playlist title', fatal=False)
405 return self.playlist_result(entries, playlist_id, playlist_name)