yt_dlp/extractor/gronkh.py

   1 import functools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     OnDemandPagedList,
   6     float_or_none,
   7     traverse_obj,
   8     unified_strdate,
   9 )
  10
  11
  12 class GronkhIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?gronkh\.tv/(?:watch/)?streams?/(?P<id>\d+)'
  14
  15     _TESTS = [{
  16         'url': 'https://gronkh.tv/streams/657',
  17         'info_dict': {
  18             'id': '657',
  19             'ext': 'mp4',
  20             'title': 'H.O.R.D.E. - DAS ZWEiTE ZEiTALTER 🎲 Session 1',
  21             'view_count': int,
  22             'thumbnail': 'https://01.cdn.vod.farm/preview/9e2555d3a23bf4e5c5b7c6b3b70a9d84.jpg',
  23             'upload_date': '20221111',
  24             'chapters': 'count:3',
  25             'duration': 31463,
  26         },
  27         'params': {'skip_download': True},
  28     }, {
  29         'url': 'https://gronkh.tv/stream/536',
  30         'info_dict': {
  31             'id': '536',
  32             'ext': 'mp4',
  33             'title': 'GTV0536, 2021-10-01 - MARTHA IS DEAD  #FREiAB1830  !FF7 !horde !archiv',
  34             'view_count': int,
  35             'thumbnail': 'https://01.cdn.vod.farm/preview/6436746cce14e25f751260a692872b9b.jpg',
  36             'upload_date': '20211001',
  37             'duration': 32058,
  38         },
  39         'params': {'skip_download': True},
  40     }, {
  41         'url': 'https://gronkh.tv/watch/stream/546',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         data_json = self._download_json(f'https://api.gronkh.tv/v1/video/info?episode={video_id}', video_id)
  48         m3u8_url = self._download_json(f'https://api.gronkh.tv/v1/video/playlist?episode={video_id}', video_id)['playlist_url']
  49         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
  50         if data_json.get('vtt_url'):
  51             subtitles.setdefault('en', []).append({
  52                 'url': data_json['vtt_url'],
  53                 'ext': 'vtt',
  54             })
  55         return {
  56             'id': video_id,
  57             'title': data_json.get('title'),
  58             'view_count': data_json.get('views'),
  59             'thumbnail': data_json.get('preview_url'),
  60             'upload_date': unified_strdate(data_json.get('created_at')),
  61             'formats': formats,
  62             'subtitles': subtitles,
  63             'duration': float_or_none(data_json.get('source_length')),
  64             'chapters': traverse_obj(data_json, (
  65                 'chapters', lambda _, v: float_or_none(v['offset']) is not None, {
  66                     'title': 'title',
  67                     'start_time': ('offset', {float_or_none}),
  68                 })) or None,
  69         }
  70
  71
  72 class GronkhFeedIE(InfoExtractor):
  73     _VALID_URL = r'https?://(?:www\.)?gronkh\.tv(?:/feed)?/?(?:#|$)'
  74     IE_NAME = 'gronkh:feed'
  75
  76     _TESTS = [{
  77         'url': 'https://gronkh.tv/feed',
  78         'info_dict': {
  79             'id': 'feed',
  80         },
  81         'playlist_count': 16,
  82     }, {
  83         'url': 'https://gronkh.tv',
  84         'only_matching': True,
  85     }]
  86
  87     def _entries(self):
  88         for type_ in ('recent', 'views'):
  89             info = self._download_json(
  90                 f'https://api.gronkh.tv/v1/video/discovery/{type_}', 'feed', note=f'Downloading {type_} API JSON')
  91             for item in traverse_obj(info, ('discovery', ...)) or []:
  92                 yield self.url_result(f'https://gronkh.tv/watch/stream/{item["episode"]}', GronkhIE, item.get('title'))
  93
  94     def _real_extract(self, url):
  95         return self.playlist_result(self._entries(), 'feed')
  96
  97
  98 class GronkhVodsIE(InfoExtractor):
  99     _VALID_URL = r'https?://(?:www\.)?gronkh\.tv/vods/streams/?(?:#|$)'
 100     IE_NAME = 'gronkh:vods'
 101
 102     _TESTS = [{
 103         'url': 'https://gronkh.tv/vods/streams',
 104         'info_dict': {
 105             'id': 'vods',
 106         },
 107         'playlist_mincount': 150,
 108     }]
 109     _PER_PAGE = 25
 110
 111     def _fetch_page(self, page):
 112         items = traverse_obj(self._download_json(
 113             'https://api.gronkh.tv/v1/search', 'vods', query={'offset': self._PER_PAGE * page, 'first': self._PER_PAGE},
 114             note=f'Downloading stream video page {page + 1}'), ('results', 'videos', ...))
 115         for item in items or []:
 116             yield self.url_result(f'https://gronkh.tv/watch/stream/{item["episode"]}', GronkhIE, item['episode'], item.get('title'))
 117
 118     def _real_extract(self, url):
 119         entries = OnDemandPagedList(functools.partial(self._fetch_page), self._PER_PAGE)
 120         return self.playlist_result(entries, 'vods')