# coding: utf-8
from __future__ import unicode_literals
-import re
-import time
import itertools
import json
-from .common import InfoExtractor
from .naver import NaverBaseIE
from ..compat import (
compat_HTTPError,
ExtractorError,
int_or_none,
merge_dicts,
+ str_or_none,
+ strip_or_none,
try_get,
urlencode_postdata,
)
}, {
'url': 'https://www.vlive.tv/embed/1326',
'only_matching': True,
+ }, {
+ # works only with gcc=KR
+ 'url': 'https://www.vlive.tv/video/225019',
+ 'only_matching': True,
}]
def _real_initialize(self):
raise ExtractorError('Unable to log in', expected=True)
def _call_api(self, path_template, video_id, fields=None):
- query = {'appId': self._APP_ID}
+ query = {'appId': self._APP_ID, 'gcc': 'KR'}
if fields:
query['fields'] = fields
- return self._download_json(
- 'https://www.vlive.tv/globalv-web/vam-web/' + path_template % video_id, video_id,
- 'Downloading %s JSON metadata' % path_template.split('/')[-1].split('-')[0],
- headers={'Referer': 'https://www.vlive.tv/'}, query=query)
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
try:
- post = self._call_api(
- 'post/v1.0/officialVideoPost-%s', video_id,
- 'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId}')
+ return self._download_json(
+ 'https://www.vlive.tv/globalv-web/vam-web/' + path_template % video_id, video_id,
+ 'Downloading %s JSON metadata' % path_template.split('/')[-1].split('-')[0],
+ headers={'Referer': 'https://www.vlive.tv/'}, query=query)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
self.raise_login_required(json.loads(e.cause.read().decode())['message'])
raise
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ post = self._call_api(
+ 'post/v1.0/officialVideoPost-%s', video_id,
+ 'author{nickname},channel{channelCode,channelName},officialVideo{commentCount,exposeStatus,likeCount,playCount,playTime,status,title,type,vodId}')
+
video = post['officialVideo']
def get_common_fields():
'old/v3/live/%s/playInfo',
video_id)['result']['adaptiveStreamUrl']
formats = self._extract_m3u8_formats(stream_url, video_id, 'mp4')
+ self._sort_formats(formats)
info = get_common_fields()
info.update({
'title': self._live_title(video['title']),
raise ExtractorError('Unknown status ' + status)
+class VLivePostIE(VLiveIE):
+ IE_NAME = 'vlive:post'
+ _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/post/(?P<id>\d-\d+)'
+ _TESTS = [{
+ # uploadType = SOS
+ 'url': 'https://www.vlive.tv/post/1-20088044',
+ 'info_dict': {
+ 'id': '1-20088044',
+ 'title': 'Hola estrellitas la tierra les dice hola (si era asรญ no?) Ha...',
+ 'description': 'md5:fab8a1e50e6e51608907f46c7fa4b407',
+ },
+ 'playlist_count': 3,
+ }, {
+ # uploadType = V
+ 'url': 'https://www.vlive.tv/post/1-20087926',
+ 'info_dict': {
+ 'id': '1-20087926',
+ 'title': 'James Corden: And so, the baby becamos the Papa๐๐ญ๐ช๐ญ',
+ },
+ 'playlist_count': 1,
+ }]
+ _FVIDEO_TMPL = 'fvideo/v1.0/fvideo-%%s/%s'
+ _SOS_TMPL = _FVIDEO_TMPL % 'sosPlayInfo'
+ _INKEY_TMPL = _FVIDEO_TMPL % 'inKey'
+
+ def _real_extract(self, url):
+ post_id = self._match_id(url)
+
+ post = self._call_api(
+ 'post/v1.0/post-%s', post_id,
+ 'attachments{video},officialVideo{videoSeq},plainBody,title')
+
+ video_seq = str_or_none(try_get(
+ post, lambda x: x['officialVideo']['videoSeq']))
+ if video_seq:
+ return self.url_result(
+ 'http://www.vlive.tv/video/' + video_seq,
+ VLiveIE.ie_key(), video_seq)
+
+ title = post['title']
+ entries = []
+ for idx, video in enumerate(post['attachments']['video'].values()):
+ video_id = video.get('videoId')
+ if not video_id:
+ continue
+ upload_type = video.get('uploadType')
+ upload_info = video.get('uploadInfo') or {}
+ entry = None
+ if upload_type == 'SOS':
+ download = self._call_api(
+ self._SOS_TMPL, video_id)['videoUrl']['download']
+ formats = []
+ for f_id, f_url in download.items():
+ formats.append({
+ 'format_id': f_id,
+ 'url': f_url,
+ 'height': int_or_none(f_id[:-1]),
+ })
+ self._sort_formats(formats)
+ entry = {
+ 'formats': formats,
+ 'id': video_id,
+ 'thumbnail': upload_info.get('imageUrl'),
+ }
+ elif upload_type == 'V':
+ vod_id = upload_info.get('videoId')
+ if not vod_id:
+ continue
+ inkey = self._call_api(self._INKEY_TMPL, video_id)['inKey']
+ entry = self._extract_video_info(video_id, vod_id, inkey)
+ if entry:
+ entry['title'] = '%s_part%s' % (title, idx)
+ entries.append(entry)
+ return self.playlist_result(
+ entries, post_id, title, strip_or_none(post.get('plainBody')))
+
+
class VLiveChannelIE(VLiveBaseIE):
IE_NAME = 'vlive:channel'
_VALID_URL = r'https?://(?:channels\.vlive\.tv|(?:(?:www|m)\.)?vlive\.tv/channel)/(?P<id>[0-9A-Z]+)'
for video in videos:
video_id = video.get('videoSeq')
- if not video_id:
+ video_type = video.get('videoType')
+
+ if not video_id or not video_type:
continue
video_id = compat_str(video_id)
- entries.append(
- self.url_result(
- 'http://www.vlive.tv/video/%s' % video_id,
- ie=VLiveIE.ie_key(), video_id=video_id))
+
+ if video_type in ('PLAYLIST'):
+ playlist_videos = try_get(
+ video,
+ lambda x: x['videoPlaylist']['videoList'], list)
+ if not playlist_videos:
+ continue
+
+ for playlist_video in playlist_videos:
+ playlist_video_id = playlist_video.get('videoSeq')
+ if not playlist_video_id:
+ continue
+ playlist_video_id = compat_str(playlist_video_id)
+
+ entries.append(
+ self.url_result(
+ 'http://www.vlive.tv/video/%s' % playlist_video_id,
+ ie=VLiveIE.ie_key(), video_id=playlist_video_id))
+ else:
+ entries.append(
+ self.url_result(
+ 'http://www.vlive.tv/video/%s' % video_id,
+ ie=VLiveIE.ie_key(), video_id=video_id))
return self.playlist_result(
entries, channel_code, channel_name)
-
-
-# old extractor. Rewrite?
-
-class VLivePlaylistIE(VLiveBaseIE):
- IE_NAME = 'vlive:playlist'
- _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
- _VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
- _TESTS = [{
- # regular working playlist
- 'url': 'https://www.vlive.tv/video/117956/playlist/117963',
- 'info_dict': {
- 'id': '117963',
- 'title': '์์ด๋๋ฃธ(IDOL ROOM) 41ํ - (แแ
งแแ
ก)แแ
กแแ
ตแแ
ณแฏ'
- },
- 'playlist_mincount': 10
- }, {
- # playlist with no playlistVideoSeqs
- 'url': 'http://www.vlive.tv/video/22867/playlist/22912',
- 'info_dict': {
- 'id': '22867',
- 'ext': 'mp4',
- 'title': '[V LIVE] Valentine Day Message from MINA',
- 'creator': 'TWICE',
- 'view_count': int
- },
- 'params': {
- 'skip_download': True,
- }
- }]
-
- def _build_video_result(self, video_id, message):
- self.to_screen(message)
- return self.url_result(
- self._VIDEO_URL_TEMPLATE % video_id,
- ie=VLiveIE.ie_key(), video_id=video_id)
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id, playlist_id = mobj.group('video_id', 'id')
-
- if self._downloader.params.get('noplaylist'):
- return self._build_video_result(
- video_id,
- 'Downloading just video %s because of --no-playlist'
- % video_id)
-
- self.to_screen(
- 'Downloading playlist %s - add --no-playlist to just download video'
- % playlist_id)
-
- webpage = self._download_webpage(
- 'http://www.vlive.tv/video/%s/playlist/%s'
- % (video_id, playlist_id), playlist_id)
-
- raw_item_ids = self._search_regex(
- r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
- 'playlist video seqs', default=None, fatal=False)
-
- if not raw_item_ids:
- return self._build_video_result(
- video_id,
- 'Downloading just video %s because no playlist was found'
- % video_id)
-
- item_ids = self._parse_json(raw_item_ids, playlist_id)
-
- entries = [
- self.url_result(
- self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
- video_id=compat_str(item_id))
- for item_id in item_ids]
-
- playlist_name = self._html_search_regex(
- r'<div[^>]+class="[^"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)',
- webpage, 'playlist title', fatal=False)
-
- return self.playlist_result(entries, playlist_id, playlist_name)