yt_dlp/extractor/hse.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     traverse_obj,
   5     unified_timestamp,
   6 )
   7
   8
   9 class HSEShowBaseInfoExtractor(InfoExtractor):
  10     _GEO_COUNTRIES = ['DE']
  11
  12     def _extract_redux_data(self, url, video_id):
  13         webpage = self._download_webpage(url, video_id)
  14         redux = self._html_search_regex(
  15             r'window\.__REDUX_DATA__\s*=\s*({.*});?', webpage, 'redux data')
  16         return self._parse_json(redux.replace('\n', ''), video_id)
  17
  18     def _extract_formats_and_subtitles(self, sources, video_id):
  19         if not sources:
  20             raise ExtractorError('No video found', expected=True, video_id=video_id)
  21         formats, subtitles = [], {}
  22         for src in sources:
  23             if src['mimetype'] != 'application/x-mpegURL':
  24                 continue
  25             fmts, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, ext='mp4')
  26             formats.extend(fmts)
  27             subtitles = self._merge_subtitles(subtitles, subs)
  28         return formats, subtitles
  29
  30
  31 class HSEShowIE(HSEShowBaseInfoExtractor):
  32     _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/c/tv-shows/(?P<id>[0-9]+)'
  33     _TESTS = [{
  34         'url': 'https://www.hse.de/dpl/c/tv-shows/505350',
  35         'info_dict': {
  36             'id': '505350',
  37             'ext': 'mp4',
  38             'title': 'Pfeffinger Mode & Accessoires',
  39             'timestamp': 1638810000,
  40             'upload_date': '20211206',
  41             'channel': 'HSE24',
  42             'uploader': 'Arina Pirayesh',
  43         },
  44         'params': {'skip_download': 'm3u8'},
  45     }]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         json_data = self._extract_redux_data(url, video_id)
  50         formats, subtitles = self._extract_formats_and_subtitles(
  51             traverse_obj(json_data, ('tvShowPage', 'tvShowVideo', 'sources')), video_id)
  52
  53         show = traverse_obj(json_data, ('tvShowPage', 'tvShow')) or {}
  54         return {
  55             'id': video_id,
  56             'title': show.get('title') or video_id,
  57             'formats': formats,
  58             'timestamp': unified_timestamp(f'{show.get("date")} {show.get("hour")}:00'),
  59             'thumbnail': traverse_obj(json_data, ('tvShowVideo', 'poster')),
  60             'channel': self._search_regex(
  61                 r'tvShow \| ([A-Z0-9]+)_', show.get('actionFieldText') or '', video_id, fatal=False),
  62             'uploader': show.get('presenter'),
  63             'subtitles': subtitles,
  64         }
  65
  66
  67 class HSEProductIE(HSEShowBaseInfoExtractor):
  68     _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/p/product/(?P<id>[0-9]+)'
  69     _TESTS = [{
  70         'url': 'https://www.hse.de/dpl/p/product/408630',
  71         'info_dict': {
  72             'id': '408630',
  73             'ext': 'mp4',
  74             'title': 'Hose im Ponte-Mix',
  75             'uploader': 'Judith Williams',
  76         },
  77         'params': {'skip_download': 'm3u8'},
  78     }]
  79
  80     def _real_extract(self, url):
  81         video_id = self._match_id(url)
  82         json_data = self._extract_redux_data(url, video_id)
  83         video = traverse_obj(json_data, ('productContent', 'productContent', 'videos', 0)) or {}
  84         formats, subtitles = self._extract_formats_and_subtitles(video.get('sources'), video_id)
  85
  86         return {
  87             'id': video_id,
  88             'title': traverse_obj(json_data, ('productDetail', 'product', 'name', 'short')) or video_id,
  89             'formats': formats,
  90             'subtitles': subtitles,
  91             'thumbnail': video.get('poster'),
  92             'uploader': traverse_obj(json_data, ('productDetail', 'product', 'brand', 'brandName')),
  93         }