]>
Commit | Line | Data |
---|---|---|
061f62da | 1 | # coding: utf-8 |
b24d6336 | 2 | from __future__ import division, unicode_literals |
061f62da | 3 | |
b24d6336 KH |
4 | import re |
5 | import time | |
9d186afa | 6 | |
061f62da | 7 | from .common import InfoExtractor |
8 | from ..utils import ( | |
52f5889f | 9 | dict_get, |
9d186afa | 10 | ExtractorError, |
52f5889f S |
11 | float_or_none, |
12 | int_or_none, | |
061f62da | 13 | ) |
15707c7e | 14 | from ..compat import compat_urllib_parse_urlencode |
061f62da | 15 | |
16 | ||
17 | class VLiveIE(InfoExtractor): | |
18 | IE_NAME = 'vlive' | |
52f5889f | 19 | _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<id>[0-9]+)' |
061f62da | 20 | _TEST = { |
b8b465af | 21 | 'url': 'http://www.vlive.tv/video/1326', |
061f62da | 22 | 'md5': 'cc7314812855ce56de70a06a27314983', |
23 | 'info_dict': { | |
24 | 'id': '1326', | |
25 | 'ext': 'mp4', | |
52f5889f S |
26 | 'title': "[V] Girl's Day's Broadcast", |
27 | 'creator': "Girl's Day", | |
28 | 'view_count': int, | |
061f62da | 29 | }, |
30 | } | |
061f62da | 31 | |
32 | def _real_extract(self, url): | |
33 | video_id = self._match_id(url) | |
34 | ||
35 | webpage = self._download_webpage( | |
52f5889f | 36 | 'http://www.vlive.tv/video/%s' % video_id, video_id) |
061f62da | 37 | |
b24d6336 KH |
38 | # UTC+x - UTC+9 (KST) |
39 | tz = time.altzone if time.localtime().tm_isdst == 1 else time.timezone | |
40 | tz_offset = -tz // 60 - 9 * 60 | |
41 | self._set_cookie('vlive.tv', 'timezoneOffset', '%d' % tz_offset) | |
b8b465af | 42 | |
b24d6336 KH |
43 | status_params = self._download_json( |
44 | 'http://www.vlive.tv/video/status?videoSeq=%s' % video_id, | |
45 | video_id, 'Downloading JSON status', | |
d41ee7b7 | 46 | headers={'Referer': url.encode('utf-8')}) |
b24d6336 KH |
47 | status = status_params.get('status') |
48 | air_start = status_params.get('onAirStartAt', '') | |
49 | is_live = status_params.get('isLive') | |
b8b465af | 50 | |
b24d6336 KH |
51 | video_params = self._search_regex( |
52 | r'vlive\.tv\.video\.ajax\.request\.handler\.init\((.+)\)', | |
53 | webpage, 'video params') | |
54 | live_params, long_video_id, key = re.split( | |
55 | r'"\s*,\s*"', video_params)[1:4] | |
56 | ||
57 | if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR': | |
58 | live_params = self._parse_json('"%s"' % live_params, video_id) | |
59 | live_params = self._parse_json(live_params, video_id) | |
60 | return self._live(video_id, webpage, live_params) | |
61 | elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO': | |
62 | if long_video_id and key: | |
63 | return self._replay(video_id, webpage, long_video_id, key) | |
64 | elif is_live: | |
65 | status = 'LIVE_END' | |
66 | else: | |
67 | status = 'COMING_SOON' | |
68 | ||
69 | if status == 'LIVE_END': | |
70 | raise ExtractorError('Uploading for replay. Please wait...', | |
71 | expected=True) | |
72 | elif status == 'COMING_SOON': | |
73 | raise ExtractorError('Coming soon! %s' % air_start, expected=True) | |
74 | elif status == 'CANCELED': | |
75 | raise ExtractorError('We are sorry, ' | |
76 | 'but the live broadcast has been canceled.', | |
77 | expected=True) | |
78 | else: | |
79 | raise ExtractorError('Unknown status %s' % status) | |
80 | ||
81 | def _get_common_fields(self, webpage): | |
061f62da | 82 | title = self._og_search_title(webpage) |
b24d6336 KH |
83 | creator = self._html_search_regex( |
84 | r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)', | |
85 | webpage, 'creator', fatal=False) | |
86 | thumbnail = self._og_search_thumbnail(webpage) | |
87 | return { | |
88 | 'title': title, | |
89 | 'creator': creator, | |
90 | 'thumbnail': thumbnail, | |
91 | } | |
08354db4 | 92 | |
b24d6336 KH |
93 | def _live(self, video_id, webpage, live_params): |
94 | formats = [] | |
95 | for vid in live_params.get('resolutions', []): | |
96 | formats.extend(self._extract_m3u8_formats( | |
97 | vid['cdnUrl'], video_id, 'mp4', | |
98 | m3u8_id=vid.get('name'), | |
99 | fatal=False, live=True)) | |
100 | self._sort_formats(formats) | |
101 | ||
102 | return dict(self._get_common_fields(webpage), | |
9d186afa YCH |
103 | id=video_id, |
104 | formats=formats, | |
105 | is_live=True) | |
b24d6336 KH |
106 | |
107 | def _replay(self, video_id, webpage, long_video_id, key): | |
52f5889f S |
108 | playinfo = self._download_json( |
109 | 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s' | |
15707c7e | 110 | % compat_urllib_parse_urlencode({ |
52f5889f S |
111 | 'videoId': long_video_id, |
112 | 'key': key, | |
113 | 'ptc': 'http', | |
114 | 'doct': 'json', # document type (xml or json) | |
115 | 'cpt': 'vtt', # captions type (vtt or ttml) | |
116 | }), video_id) | |
061f62da | 117 | |
52f5889f S |
118 | formats = [{ |
119 | 'url': vid['source'], | |
120 | 'format_id': vid.get('encodingOption', {}).get('name'), | |
121 | 'abr': float_or_none(vid.get('bitrate', {}).get('audio')), | |
122 | 'vbr': float_or_none(vid.get('bitrate', {}).get('video')), | |
123 | 'width': int_or_none(vid.get('encodingOption', {}).get('width')), | |
124 | 'height': int_or_none(vid.get('encodingOption', {}).get('height')), | |
125 | 'filesize': int_or_none(vid.get('size')), | |
126 | } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')] | |
061f62da | 127 | self._sort_formats(formats) |
128 | ||
52f5889f S |
129 | view_count = int_or_none(playinfo.get('meta', {}).get('count')) |
130 | ||
061f62da | 131 | subtitles = {} |
b8b465af | 132 | for caption in playinfo.get('captions', {}).get('list', []): |
52f5889f S |
133 | lang = dict_get(caption, ('language', 'locale', 'country', 'label')) |
134 | if lang and caption.get('source'): | |
135 | subtitles[lang] = [{ | |
136 | 'ext': 'vtt', | |
137 | 'url': caption['source']}] | |
061f62da | 138 | |
b24d6336 | 139 | return dict(self._get_common_fields(webpage), |
9d186afa YCH |
140 | id=video_id, |
141 | formats=formats, | |
142 | view_count=view_count, | |
143 | subtitles=subtitles) |