yt_dlp/extractor/caltrans.py

   1 from .common import InfoExtractor
   2
   3
   4 class CaltransIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:[^/]+\.)?ca\.gov/vm/loc/[^/]+/(?P<id>[a-z0-9_]+)\.htm'
   6     _TEST = {
   7         'url': 'https://cwwp2.dot.ca.gov/vm/loc/d3/hwy50at24th.htm',
   8         'info_dict': {
   9             'id': 'hwy50at24th',
  10             'ext': 'ts',
  11             'title': 'US-50 : Sacramento : Hwy 50 at 24th',
  12             'live_status': 'is_live',
  13             'thumbnail': 'https://cwwp2.dot.ca.gov/data/d3/cctv/image/hwy50at24th/hwy50at24th.jpg',
  14         },
  15     }
  16
  17     def _real_extract(self, url):
  18         video_id = self._match_id(url)
  19         webpage = self._download_webpage(url, video_id)
  20
  21         global_vars = self._search_regex(
  22             r'<script[^<]+?([^<]+\.m3u8[^<]+)</script>',
  23             webpage, 'Global Vars')
  24         route_place = self._search_regex(r'routePlace\s*=\s*"([^"]+)"', global_vars, 'Route Place', fatal=False)
  25         location_name = self._search_regex(r'locationName\s*=\s*"([^"]+)"', global_vars, 'Location Name', fatal=False)
  26         poster_url = self._search_regex(r'posterURL\s*=\s*"([^"]+)"', global_vars, 'Poster Url', fatal=False)
  27         video_stream = self._search_regex(r'videoStreamURL\s*=\s*"([^"]+)"', global_vars, 'Video Stream URL', fatal=False)
  28
  29         formats = self._extract_m3u8_formats(video_stream, video_id, 'ts', live=True)
  30
  31         return {
  32             'id': video_id,
  33             'title': f'{route_place} : {location_name}',
  34             'is_live': True,
  35             'formats': formats,
  36             'thumbnail': poster_url,
  37         }