yt_dlp/extractor/caltrans.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class CaltransIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:[^/]+\.)?ca\.gov/vm/loc/[^/]+/(?P<id>[a-z0-9_]+)\.htm'
   9     _TEST = {
  10         'url': 'https://cwwp2.dot.ca.gov/vm/loc/d3/hwy50at24th.htm',
  11         'info_dict': {
  12             'id': 'hwy50at24th',
  13             'ext': 'ts',
  14             'title': 'US-50 : Sacramento : Hwy 50 at 24th',
  15             'live_status': 'is_live',
  16             'thumbnail': 'https://cwwp2.dot.ca.gov/data/d3/cctv/image/hwy50at24th/hwy50at24th.jpg',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         global_vars = self._search_regex(
  25             r'<script[^<]+?([^<]+\.m3u8[^<]+)</script>',
  26             webpage, 'Global Vars')
  27         route_place = self._search_regex(r'routePlace\s*=\s*"([^"]+)"', global_vars, 'Route Place', fatal=False)
  28         location_name = self._search_regex(r'locationName\s*=\s*"([^"]+)"', global_vars, 'Location Name', fatal=False)
  29         poster_url = self._search_regex(r'posterURL\s*=\s*"([^"]+)"', global_vars, 'Poster Url', fatal=False)
  30         video_stream = self._search_regex(r'videoStreamURL\s*=\s*"([^"]+)"', global_vars, 'Video Stream URL', fatal=False)
  31
  32         formats = self._extract_m3u8_formats(video_stream, video_id, 'ts', live=True)
  33         self._sort_formats(formats)
  34
  35         return {
  36             'id': video_id,
  37             'title': f'{route_place} : {location_name}',
  38             'is_live': True,
  39             'formats': formats,
  40             'thumbnail': poster_url,
  41         }