yt_dlp/extractor/wwe.py

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