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]+)'
28 'url': 'http://www.vlive.tv/video/1326',
29 'md5': 'cc7314812855ce56de70a06a27314983',
33 'title': "[V LIVE] Girl's Day's Broadcast",
34 'creator': "Girl's Day",
38 'url': 'http://www.vlive.tv/video/16937',
42 'title': '[V LIVE] 첸백시 걍방',
45 'subtitles': 'mincount:12',
48 'skip_download': True,
53 def suitable(cls
, url
):
54 return False if VLivePlaylistIE
.suitable(url
) else super(VLiveIE
, cls
).suitable(url
)
56 def _real_extract(self
, url
):
57 video_id
= self
._match
_id
(url
)
59 webpage
= self
._download
_webpage
(
60 'http://www.vlive.tv/video/%s' % video_id
, video_id
)
62 VIDEO_PARAMS_RE
= r
'\bvlive\.video\.init\(([^)]+)'
63 VIDEO_PARAMS_FIELD
= 'video params'
65 params
= self
._parse
_json
(self
._search
_regex
(
66 VIDEO_PARAMS_RE
, webpage
, VIDEO_PARAMS_FIELD
, default
=''), video_id
,
67 transform_source
=lambda s
: '[' + s
+ ']', fatal
=False)
69 if not params
or len(params
) < 7:
70 params
= self
._search
_regex
(
71 VIDEO_PARAMS_RE
, webpage
, VIDEO_PARAMS_FIELD
)
72 params
= [p
.strip(r
'"') for p
in re
.split(r
'\s*,\s*', params
)]
74 status
, long_video_id
, key
= params
[2], params
[5], params
[6]
75 status
= remove_start(status
, 'PRODUCT_')
77 if status
in ('LIVE_ON_AIR', 'BIG_EVENT_ON_AIR'):
78 return self
._live
(video_id
, webpage
)
79 elif status
in ('VOD_ON_AIR', 'BIG_EVENT_INTRO'):
80 if long_video_id
and key
:
81 return self
._replay
(video_id
, webpage
, long_video_id
, key
)
83 status
= 'COMING_SOON'
85 if status
== 'LIVE_END':
86 raise ExtractorError('Uploading for replay. Please wait...',
88 elif status
== 'COMING_SOON':
89 raise ExtractorError('Coming soon!', expected
=True)
90 elif status
== 'CANCELED':
91 raise ExtractorError('We are sorry, '
92 'but the live broadcast has been canceled.',
95 raise ExtractorError('Unknown status %s' % status
)
97 def _get_common_fields(self
, webpage
):
98 title
= self
._og
_search
_title
(webpage
)
99 creator
= self
._html
_search
_regex
(
100 r
'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
101 webpage
, 'creator', fatal
=False)
102 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
106 'thumbnail': thumbnail
,
109 def _live(self
, video_id
, webpage
):
110 init_page
= self
._download
_webpage
(
111 'http://www.vlive.tv/video/init/view',
112 video_id
, note
='Downloading live webpage',
113 data
=urlencode_postdata({'videoSeq': video_id
}),
115 'Referer': 'http://www.vlive.tv/video/%s' % video_id
,
116 'Content-Type': 'application/x-www-form-urlencoded'
119 live_params
= self
._search
_regex
(
120 r
'"liveStreamInfo"\s*:\s*(".*"),',
121 init_page
, 'live stream info')
122 live_params
= self
._parse
_json
(live_params
, video_id
)
123 live_params
= self
._parse
_json
(live_params
, video_id
)
126 for vid
in live_params
.get('resolutions', []):
127 formats
.extend(self
._extract
_m
3u8_formats
(
128 vid
['cdnUrl'], video_id
, 'mp4',
129 m3u8_id
=vid
.get('name'),
130 fatal
=False, live
=True))
131 self
._sort
_formats
(formats
)
133 info
= self
._get
_common
_fields
(webpage
)
135 'title': self
._live
_title
(info
['title']),
142 def _replay(self
, video_id
, webpage
, long_video_id
, key
):
143 playinfo
= self
._download
_json
(
144 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s'
145 % compat_urllib_parse_urlencode({
146 'videoId': long_video_id
,
149 'doct': 'json', # document type (xml or json)
150 'cpt': 'vtt', # captions type (vtt or ttml)
154 'url': vid
['source'],
155 'format_id': vid
.get('encodingOption', {}).get('name'),
156 'abr': float_or_none(vid
.get('bitrate', {}).get('audio')),
157 'vbr': float_or_none(vid
.get('bitrate', {}).get('video')),
158 'width': int_or_none(vid
.get('encodingOption', {}).get('width')),
159 'height': int_or_none(vid
.get('encodingOption', {}).get('height')),
160 'filesize': int_or_none(vid
.get('size')),
161 } for vid
in playinfo
.get('videos', {}).get('list', []) if vid
.get('source')]
162 self
._sort
_formats
(formats
)
164 view_count
= int_or_none(playinfo
.get('meta', {}).get('count'))
167 for caption
in playinfo
.get('captions', {}).get('list', []):
168 lang
= dict_get(caption
, ('locale', 'language', 'country', 'label'))
169 if lang
and caption
.get('source'):
172 'url': caption
['source']}]
174 info
= self
._get
_common
_fields
(webpage
)
178 'view_count': view_count
,
179 'subtitles': subtitles
,
184 class VLiveChannelIE(InfoExtractor
):
185 IE_NAME
= 'vlive:channel'
186 _VALID_URL
= r
'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)'
188 'url': 'http://channels.vlive.tv/FCD4B',
193 'playlist_mincount': 110
195 _APP_ID
= '8c6cc7b45d2568fb668be6e05b6e5a3b'
197 def _real_extract(self
, url
):
198 channel_code
= self
._match
_id
(url
)
200 webpage
= self
._download
_webpage
(
201 'http://channels.vlive.tv/%s/video' % channel_code
, channel_code
)
205 app_js_url
= self
._search
_regex
(
206 r
'<script[^>]+src=(["\'])(?P
<url
>http
.+?
/app\
.js
.*?
)\
1',
207 webpage, 'app js
', default=None, group='url
')
210 app_js = self._download_webpage(
211 app_js_url, channel_code, 'Downloading app JS
', fatal=False)
213 app_id = self._search_regex(
214 r'Global\
.VFAN_APP_ID\s
*=\s
*[\'"]([^\'"]+)[\'"]',
215 app_js, 'app id', default=None)
217 app_id = app_id or self._APP_ID
219 channel_info = self._download_json(
220 'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode',
221 channel_code, note='Downloading decode channel code',
224 'channelCode': channel_code,
225 '_': int(time.time())
228 channel_seq = channel_info['result']['channelSeq']
232 for page_num in itertools.count(1):
233 video_list = self._download_json(
234 'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList',
235 channel_code, note='Downloading channel list page #%d' % page_num,
238 'channelSeq': channel_seq,
239 # Large values of maxNumOfRows (~300 or above) may cause
240 # empty responses (see [1]), e.g. this happens for [2] that
241 # has more than 300 videos.
242 # 1. https://github.com/rg3/youtube-dl/issues/13830
243 # 2. http://channels.vlive.tv/EDBF.
245 '_': int(time.time()),
251 channel_name = try_get(
253 lambda x: x['result']['channelInfo']['channelName'],
257 video_list, lambda x: x['result']['videoList'], list)
262 video_id = video.get('videoSeq')
265 video_id = compat_str(video_id)
268 'http://www.vlive.tv/video/%s' % video_id,
269 ie=VLiveIE.ie_key(), video_id=video_id))
271 return self.playlist_result(
272 entries, channel_code, channel_name)
275 class VLivePlaylistIE(InfoExtractor):
276 IE_NAME = 'vlive:playlist'
277 _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
279 'url': 'http://www.vlive.tv/video/22867/playlist/22912',
282 'title': 'Valentine Day Message from TWICE'
284 'playlist_mincount': 9
287 def _real_extract(self, url):
288 mobj = re.match(self._VALID_URL, url)
289 video_id, playlist_id = mobj.group('video_id', 'id')
291 VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
292 if self._downloader.params.get('noplaylist'):
294 'Downloading just video %s because of --no-playlist' % video_id)
295 return self.url_result(
296 VIDEO_URL_TEMPLATE % video_id,
297 ie=VLiveIE.ie_key(), video_id=video_id)
300 'Downloading playlist %s - add --no-playlist to just download video'
303 webpage = self._download_webpage(
304 'http://www.vlive.tv/video/%s/playlist/%s'
305 % (video_id, playlist_id), playlist_id)
307 item_ids = self._parse_json(
309 r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
310 'playlist video seqs'),
315 VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
316 video_id=compat_str(item_id))
317 for item_id in item_ids]
319 playlist_name = self._html_search_regex(
320 r'<div[^>]+class="[^
"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)',
321 webpage, 'playlist title', fatal=False)
323 return self.playlist_result(entries, playlist_id, playlist_name)