yt_dlp/extractor/axs.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     js_to_json,
   5     parse_iso8601,
   6     traverse_obj,
   7     url_or_none,
   8 )
   9
  10
  11 class AxsIE(InfoExtractor):
  12     IE_NAME = 'axs.tv'
  13     _VALID_URL = r'https?://(?:www\.)?axs\.tv/(?:channel/(?:[^/?#]+/)+)?video/(?P<id>[^/?#]+)'
  14
  15     _TESTS = [{
  16         'url': 'https://www.axs.tv/video/5f4dc776b70e4f1c194f22ef/',
  17         'md5': '8d97736ae8e50c64df528e5e676778cf',
  18         'info_dict': {
  19             'id': '5f4dc776b70e4f1c194f22ef',
  20             'title': 'Small Town',
  21             'ext': 'mp4',
  22             'description': 'md5:e314d28bfaa227a4d7ec965fae19997f',
  23             'upload_date': '20230602',
  24             'timestamp': 1685729564,
  25             'duration': 1284.216,
  26             'series': 'Rock & Roll Road Trip with Sammy Hagar',
  27             'season': 2,
  28             'episode': '3',
  29             'thumbnail': 'https://images.dotstudiopro.com/5f4e9d330a0c3b295a7e8394',
  30         },
  31     }, {
  32         'url': 'https://www.axs.tv/channel/rock-star-interview/video/daryl-hall',
  33         'md5': '300ae795cd8f9984652c0949734ffbdc',
  34         'info_dict': {
  35             'id': '5f488148b70e4f392572977c',
  36             'display_id': 'daryl-hall',
  37             'title': 'Daryl Hall',
  38             'ext': 'mp4',
  39             'description': 'md5:e54ecaa0f4b5683fc9259e9e4b196628',
  40             'upload_date': '20230214',
  41             'timestamp': 1676403615,
  42             'duration': 2570.668,
  43             'series': 'The Big Interview with Dan Rather',
  44             'season': 3,
  45             'episode': '5',
  46             'thumbnail': 'https://images.dotstudiopro.com/5f4d1901f340b50d937cec32',
  47         },
  48     }]
  49
  50     def _real_extract(self, url):
  51         display_id = self._match_id(url)
  52         webpage = self._download_webpage(url, display_id)
  53
  54         webpage_json_data = self._search_json(
  55             r'mountObj\s*=', webpage, 'video ID data', display_id,
  56             transform_source=js_to_json)
  57         video_id = webpage_json_data['video_id']
  58         company_id = webpage_json_data['company_id']
  59
  60         meta = self._download_json(
  61             f'https://api.myspotlight.tv/dotplayer/video/{company_id}/{video_id}',
  62             video_id, query={'device_type': 'desktop_web'})['video']
  63
  64         formats = self._extract_m3u8_formats(
  65             meta['video_m3u8'], video_id, 'mp4', m3u8_id='hls')
  66
  67         subtitles = {}
  68         for cc in traverse_obj(meta, ('closeCaption', lambda _, v: url_or_none(v['srtPath']))):
  69             subtitles.setdefault(cc.get('srtShortLang') or 'en', []).append(
  70                 {'ext': cc.get('srtExt'), 'url': cc['srtPath']})
  71
  72         return {
  73             'id': video_id,
  74             'display_id': display_id,
  75             'formats': formats,
  76             **traverse_obj(meta, {
  77                 'title': ('title', {str}),
  78                 'description': ('description', {str}),
  79                 'series': ('seriestitle', {str}),
  80                 'season': ('season', {int}),
  81                 'episode': ('episode', {str}),
  82                 'duration': ('duration', {float_or_none}),
  83                 'timestamp': ('updated_at', {parse_iso8601}),
  84                 'thumbnail': ('thumb', {url_or_none}),
  85             }),
  86             'subtitles': subtitles,
  87         }