X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvlive.py;h=f79531e6f3a2e922b0369706cc0d76a22feb2499;hb=a6211d237b4e7051ca018cc09440502561fedaa7;hp=f75d4e254d78a54ba7655e8deaec7762451360ee;hpb=ef19739e64e91bb5ca2eeccd3ff6fdefb1a98cce;p=youtube-dl diff --git a/youtube_dl/extractor/vlive.py b/youtube_dl/extractor/vlive.py index f75d4e254..f79531e6f 100644 --- a/youtube_dl/extractor/vlive.py +++ b/youtube_dl/extractor/vlive.py @@ -6,22 +6,18 @@ import time import itertools from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlencode, - compat_str, -) +from .naver import NaverBaseIE +from ..compat import compat_str from ..utils import ( - dict_get, ExtractorError, - float_or_none, - int_or_none, + merge_dicts, remove_start, try_get, urlencode_postdata, ) -class VLiveIE(InfoExtractor): +class VLiveIE(NaverBaseIE): IE_NAME = 'vlive' _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P[0-9]+)' _NETRC_MACHINE = 'vlive' @@ -34,6 +30,7 @@ class VLiveIE(InfoExtractor): 'title': "[V LIVE] Girl's Day's Broadcast", 'creator': "Girl's Day", 'view_count': int, + 'uploader_id': 'muploader_a', }, }, { 'url': 'http://www.vlive.tv/video/16937', @@ -44,6 +41,7 @@ class VLiveIE(InfoExtractor): 'creator': 'EXO', 'view_count': int, 'subtitles': 'mincount:12', + 'uploader_id': 'muploader_j', }, 'params': { 'skip_download': True, @@ -54,8 +52,8 @@ class VLiveIE(InfoExtractor): 'info_dict': { 'id': '129100', 'ext': 'mp4', - 'title': "[V LIVE] [BTS+] Run BTS! 2019 - EP.71 :: Behind the scene", - 'creator': "BTS+", + 'title': '[V LIVE] [BTS+] Run BTS! 2019 - EP.71 :: Behind the scene', + 'creator': 'BTS+', 'view_count': int, 'subtitles': 'mincount:10', }, @@ -187,45 +185,9 @@ class VLiveIE(InfoExtractor): 'This video is only available for CH+ subscribers') long_video_id, key = video_info['vid'], video_info['inkey'] - playinfo = self._download_json( - 'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s' - % compat_urllib_parse_urlencode({ - 'videoId': long_video_id, - 'key': key, - 'ptc': 'http', - 'doct': 'json', # document type (xml or json) - 'cpt': 'vtt', # captions type (vtt or ttml) - }), video_id) - - formats = [{ - 'url': vid['source'], - 'format_id': vid.get('encodingOption', {}).get('name'), - 'abr': float_or_none(vid.get('bitrate', {}).get('audio')), - 'vbr': float_or_none(vid.get('bitrate', {}).get('video')), - 'width': int_or_none(vid.get('encodingOption', {}).get('width')), - 'height': int_or_none(vid.get('encodingOption', {}).get('height')), - 'filesize': int_or_none(vid.get('size')), - } for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')] - self._sort_formats(formats) - - view_count = int_or_none(playinfo.get('meta', {}).get('count')) - - subtitles = {} - for caption in playinfo.get('captions', {}).get('list', []): - lang = dict_get(caption, ('locale', 'language', 'country', 'label')) - if lang and caption.get('source'): - subtitles[lang] = [{ - 'ext': 'vtt', - 'url': caption['source']}] - - info = self._get_common_fields(webpage) - info.update({ - 'id': video_id, - 'formats': formats, - 'view_count': view_count, - 'subtitles': subtitles, - }) - return info + return merge_dicts( + self._get_common_fields(webpage), + self._extract_video_info(video_id, long_video_id, key)) def _download_init_page(self, video_id): return self._download_webpage( @@ -332,26 +294,45 @@ class VLiveChannelIE(InfoExtractor): class VLivePlaylistIE(InfoExtractor): IE_NAME = 'vlive:playlist' _VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P[0-9]+)/playlist/(?P[0-9]+)' - _TEST = { + _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': '아이돌룸(IDOL ROOM) 41회 - (여자)아이들' + }, + 'playlist_mincount': 10 + }, { + # playlist with no playlistVideoSeqs 'url': 'http://www.vlive.tv/video/22867/playlist/22912', 'info_dict': { - 'id': '22912', - 'title': 'Valentine Day Message from TWICE' + 'id': '22867', + 'ext': 'mp4', + 'title': '[V LIVE] Valentine Day Message from MINA', + 'creator': 'TWICE', + 'view_count': int }, - 'playlist_mincount': 9 - } + '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') - VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s' if self._downloader.params.get('noplaylist'): - self.to_screen( - 'Downloading just video %s because of --no-playlist' % video_id) - return self.url_result( - VIDEO_URL_TEMPLATE % video_id, - ie=VLiveIE.ie_key(), video_id=video_id) + 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' @@ -361,15 +342,21 @@ class VLivePlaylistIE(InfoExtractor): 'http://www.vlive.tv/video/%s/playlist/%s' % (video_id, playlist_id), playlist_id) - item_ids = self._parse_json( - self._search_regex( - r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage, - 'playlist video seqs'), - 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( - VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(), + self._VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(), video_id=compat_str(item_id)) for item_id in item_ids]