yt_dlp/extractor/webcamerapl.py

   1 import codecs
   2
   3 from .common import InfoExtractor
   4
   5
   6 class WebcameraplIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?P<id>[\w-]+)\.webcamera\.pl'
   8     _TESTS = [{
   9         'url': 'https://warszawa-plac-zamkowy.webcamera.pl',
  10         'info_dict': {
  11             'id': 'warszawa-plac-zamkowy',
  12             'ext': 'mp4',
  13             'title': r're:WIDOK NA PLAC ZAMKOWY W WARSZAWIE \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  14             'live_status': 'is_live',
  15         }
  16     }, {
  17         'url': 'https://gdansk-stare-miasto.webcamera.pl/',
  18         'info_dict': {
  19             'id': 'gdansk-stare-miasto',
  20             'ext': 'mp4',
  21             'title': r're:GDAŃSK - widok na Stare Miasto \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
  22             'live_status': 'is_live',
  23         }
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         rot13_m3u8_url = self._search_regex(r'data-src\s*=\s*"(uggc[^"]+\.z3h8)"',
  31                                             webpage, 'm3u8 url', default=None)
  32         if not rot13_m3u8_url:
  33             self.raise_no_formats('No video/audio found at the provided url', expected=True)
  34
  35         m3u8_url = codecs.decode(rot13_m3u8_url, 'rot-13')
  36         formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, live=True)
  37
  38         return {
  39             'id': video_id,
  40             'title': self._html_search_regex(r'<h1\b[^>]*>([^>]+)</h1>', webpage, 'title'),
  41             'formats': formats,
  42             'subtitles': subtitles,
  43             'is_live': True,
  44         }