yt_dlp/extractor/ichinanalive.py

   1 from .common import InfoExtractor
   2 from ..utils import ExtractorError, str_or_none, traverse_obj, unified_strdate
   3
   4
   5 class IchinanaLiveIE(InfoExtractor):
   6     IE_NAME = '17live'
   7     _VALID_URL = r'https?://(?:www\.)?17\.live/(?:[^/]+/)*(?:live|profile/r)/(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'https://17.live/live/3773096',
  10         'info_dict': {
  11             'id': '3773096',
  12             'title': '萠珈☕🤡🍫moka',
  13             'is_live': True,
  14             'uploader': '萠珈☕🤡🍫moka',
  15             'uploader_id': '3773096',
  16             'like_count': 366,
  17             'view_count': 18121,
  18             'timestamp': 1630569012,
  19         },
  20         'skip': 'running as of writing, but may be ended as of testing',
  21     }, {
  22         'note': 'nothing except language differs',
  23         'url': 'https://17.live/ja/live/3773096',
  24         'only_matching': True,
  25     }]
  26
  27     @classmethod
  28     def suitable(cls, url):
  29         return not IchinanaLiveClipIE.suitable(url) and super().suitable(url)
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         url = f'https://17.live/live/{video_id}'
  34
  35         enter = self._download_json(
  36             f'https://api-dsa.17app.co/api/v1/lives/{video_id}/enter', video_id,
  37             headers={'Referer': url}, fatal=False, expected_status=420,
  38             data=b'\0')
  39         if enter and enter.get('message') == 'ended':
  40             raise ExtractorError('This live has ended.', expected=True)
  41
  42         view_data = self._download_json(
  43             f'https://api-dsa.17app.co/api/v1/lives/{video_id}', video_id,
  44             headers={'Referer': url})
  45
  46         uploader = traverse_obj(
  47             view_data, ('userInfo', 'displayName'), ('userInfo', 'openID'))
  48
  49         video_urls = view_data.get('rtmpUrls')
  50         if not video_urls:
  51             raise ExtractorError('unable to extract live URL information')
  52         formats = []
  53         for (name, value) in video_urls[0].items():
  54             if not isinstance(value, str):
  55                 continue
  56             if not value.startswith('http'):
  57                 continue
  58             quality = -1
  59             if 'web' in name:
  60                 quality -= 1
  61             if 'High' in name:
  62                 quality += 4
  63             if 'Low' in name:
  64                 quality -= 2
  65             formats.append({
  66                 'format_id': name,
  67                 'url': value,
  68                 'quality': quality,
  69                 'http_headers': {'Referer': url},
  70                 'ext': 'flv',
  71                 'vcodec': 'h264',
  72                 'acodec': 'aac',
  73             })
  74
  75         return {
  76             'id': video_id,
  77             'title': uploader or video_id,
  78             'formats': formats,
  79             'is_live': True,
  80             'uploader': uploader,
  81             'uploader_id': video_id,
  82             'like_count': view_data.get('receivedLikeCount'),
  83             'view_count': view_data.get('viewerCount'),
  84             'thumbnail': view_data.get('coverPhoto'),
  85             'description': view_data.get('caption'),
  86             'timestamp': view_data.get('beginTime'),
  87         }
  88
  89
  90 class IchinanaLiveClipIE(InfoExtractor):
  91     IE_NAME = '17live:clip'
  92     _VALID_URL = r'https?://(?:www\.)?17\.live/(?:[^/]+/)*profile/r/(?P<uploader_id>\d+)/clip/(?P<id>[^/]+)'
  93     _TESTS = [{
  94         'url': 'https://17.live/profile/r/1789280/clip/1bHQSK8KUieruFXaCH4A4upCzlN',
  95         'info_dict': {
  96             'id': '1bHQSK8KUieruFXaCH4A4upCzlN',
  97             'title': 'マチコ先生🦋Class💋',
  98             'description': 'マチ戦隊　第一次　バスターコール\n総額200万coin！\n動画制作@うぉーかー🌱Walker🎫',
  99             'uploader_id': '1789280',
 100         },
 101     }, {
 102         'url': 'https://17.live/ja/profile/r/1789280/clip/1bHQSK8KUieruFXaCH4A4upCzlN',
 103         'only_matching': True,
 104     }]
 105
 106     def _real_extract(self, url):
 107         uploader_id, video_id = self._match_valid_url(url).groups()
 108         url = f'https://17.live/profile/r/{uploader_id}/clip/{video_id}'
 109
 110         view_data = self._download_json(
 111             f'https://api-dsa.17app.co/api/v1/clips/{video_id}', video_id,
 112             headers={'Referer': url})
 113
 114         uploader = traverse_obj(
 115             view_data, ('userInfo', 'displayName'), ('userInfo', 'name'))
 116
 117         formats = []
 118         if view_data.get('videoURL'):
 119             formats.append({
 120                 'id': 'video',
 121                 'url': view_data['videoURL'],
 122                 'quality': -1,
 123             })
 124         if view_data.get('transcodeURL'):
 125             formats.append({
 126                 'id': 'transcode',
 127                 'url': view_data['transcodeURL'],
 128                 'quality': -1,
 129             })
 130         if view_data.get('srcVideoURL'):
 131             # highest quality
 132             formats.append({
 133                 'id': 'srcVideo',
 134                 'url': view_data['srcVideoURL'],
 135                 'quality': 1,
 136             })
 137
 138         for fmt in formats:
 139             fmt.update({
 140                 'ext': 'mp4',
 141                 'protocol': 'https',
 142                 'vcodec': 'h264',
 143                 'acodec': 'aac',
 144                 'http_headers': {'Referer': url},
 145             })
 146
 147         return {
 148             'id': video_id,
 149             'title': uploader or video_id,
 150             'formats': formats,
 151             'uploader': uploader,
 152             'uploader_id': uploader_id,
 153             'like_count': view_data.get('likeCount'),
 154             'view_count': view_data.get('viewCount'),
 155             'thumbnail': view_data.get('imageURL'),
 156             'duration': view_data.get('duration'),
 157             'description': view_data.get('caption'),
 158             'upload_date': unified_strdate(str_or_none(view_data.get('createdAt'))),
 159         }