yt_dlp/extractor/wwe.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     try_get,
   7     unescapeHTML,
   8     url_or_none,
   9     urljoin,
  10 )
  11
  12
  13 class WWEBaseIE(InfoExtractor):
  14     _SUBTITLE_LANGS = {
  15         'English': 'en',
  16         'Deutsch': 'de',
  17     }
  18
  19     def _extract_entry(self, data, url, video_id=None):
  20         video_id = compat_str(video_id or data['nid'])
  21         title = data['title']
  22
  23         formats = self._extract_m3u8_formats(
  24             data['file'], video_id, 'mp4', entry_protocol='m3u8_native',
  25             m3u8_id='hls')
  26
  27         description = data.get('description')
  28         thumbnail = urljoin(url, data.get('image'))
  29         series = data.get('show_name')
  30         episode = data.get('episode_name')
  31
  32         subtitles = {}
  33         tracks = data.get('tracks')
  34         if isinstance(tracks, list):
  35             for track in tracks:
  36                 if not isinstance(track, dict):
  37                     continue
  38                 if track.get('kind') != 'captions':
  39                     continue
  40                 track_file = url_or_none(track.get('file'))
  41                 if not track_file:
  42                     continue
  43                 label = track.get('label')
  44                 lang = self._SUBTITLE_LANGS.get(label, label) or 'en'
  45                 subtitles.setdefault(lang, []).append({
  46                     'url': track_file,
  47                 })
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'description': description,
  53             'thumbnail': thumbnail,
  54             'series': series,
  55             'episode': episode,
  56             'formats': formats,
  57             'subtitles': subtitles,
  58         }
  59
  60
  61 class WWEIE(WWEBaseIE):
  62     _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P<id>[^/?#&]+)'
  63     _TESTS = [{
  64         'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018',
  65         'md5': '92811c6a14bfc206f7a6a9c5d9140184',
  66         'info_dict': {
  67             'id': '40048199',
  68             'ext': 'mp4',
  69             'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018',
  70             'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67',
  71             'thumbnail': r're:^https?://.*\.jpg$',
  72         }
  73     }, {
  74         'url': 'https://de.wwe.com/videos/gran-metalik-vs-tony-nese-wwe-205-live-sept-4-2018',
  75         'only_matching': True,
  76     }]
  77
  78     def _real_extract(self, url):
  79         display_id = self._match_id(url)
  80         webpage = self._download_webpage(url, display_id)
  81
  82         landing = self._parse_json(
  83             self._html_search_regex(
  84                 r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;',
  85                 webpage, 'drupal settings'),
  86             display_id)['WWEVideoLanding']
  87
  88         data = landing['initialVideo']['playlist'][0]
  89         video_id = landing.get('initialVideoId')
  90
  91         info = self._extract_entry(data, url, video_id)
  92         info['display_id'] = display_id
  93         return info
  94
  95
  96 class WWEPlaylistIE(WWEBaseIE):
  97     _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  98     _TESTS = [{
  99         'url': 'https://www.wwe.com/shows/raw/2018-11-12',
 100         'info_dict': {
 101             'id': '2018-11-12',
 102         },
 103         'playlist_mincount': 11,
 104     }, {
 105         'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition',
 106         'only_matching': True,
 107     }, {
 108         'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview',
 109         'only_matching': True,
 110     }]
 111
 112     @classmethod
 113     def suitable(cls, url):
 114         return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url)
 115
 116     def _real_extract(self, url):
 117         display_id = self._match_id(url)
 118         webpage = self._download_webpage(url, display_id)
 119
 120         entries = []
 121         for mobj in re.finditer(
 122                 r'data-video\s*=\s*(["\'])(?P<data>{.+?})\1', webpage):
 123             video = self._parse_json(
 124                 mobj.group('data'), display_id, transform_source=unescapeHTML,
 125                 fatal=False)
 126             if not video:
 127                 continue
 128             data = try_get(video, lambda x: x['playlist'][0], dict)
 129             if not data:
 130                 continue
 131             try:
 132                 entry = self._extract_entry(data, url)
 133             except Exception:
 134                 continue
 135             entry['extractor_key'] = WWEIE.ie_key()
 136             entries.append(entry)
 137
 138         return self.playlist_result(entries, display_id)