yt_dlp/extractor/daystar.py

   1 from .common import InfoExtractor
   2 from ..utils import js_to_json, urljoin
   3
   4
   5 class DaystarClipIE(InfoExtractor):
   6     IE_NAME = 'daystar:clip'
   7     _VALID_URL = r'https?://player\.daystar\.tv/(?P<id>\w+)'
   8     _TESTS = [{
   9         'url': 'https://player.daystar.tv/0MTO2ITM',
  10         'info_dict': {
  11             'id': '0MTO2ITM',
  12             'ext': 'mp4',
  13             'title': 'The Dark World of COVID Pt. 1 | Aaron Siri',
  14             'description': 'a420d320dda734e5f29458df3606c5f4',
  15             'thumbnail': r're:^https?://.+\.jpg',
  16         },
  17     }]
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(url, video_id)
  22
  23         src_iframe = self._search_regex(r'\<iframe[^>]+src="([^"]+)"', webpage, 'src iframe')
  24         webpage_iframe = self._download_webpage(
  25             src_iframe.replace('player.php', 'config2.php'), video_id, headers={'Referer': src_iframe})
  26
  27         sources = self._parse_json(self._search_regex(
  28             r'sources\:\s*(\[.*?\])', webpage_iframe, 'm3u8 source'), video_id, transform_source=js_to_json)
  29
  30         formats, subtitles = [], {}
  31         for source in sources:
  32             file = source.get('file')
  33             if file and source.get('type') == 'm3u8':
  34                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
  35                     urljoin('https://www.lightcast.com/embed/', file),
  36                     video_id, 'mp4', fatal=False, headers={'Referer': src_iframe})
  37                 formats.extend(fmts)
  38                 subtitles = self._merge_subtitles(subtitles, subs)
  39
  40         return {
  41             'id': video_id,
  42             'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
  43             'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
  44             'thumbnail': self._search_regex(r'image:\s*"([^"]+)', webpage_iframe, 'thumbnail'),
  45             'formats': formats,
  46             'subtitles': subtitles,
  47         }