Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/wwe.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     try_get,
   9     unescapeHTML,
  10     url_or_none,
  11     urljoin,
  12 )
  13
  14
  15 class WWEBaseIE(InfoExtractor):
  16     _SUBTITLE_LANGS = {
  17         'English': 'en',
  18         'Deutsch': 'de',
  19     }
  20
  21     def _extract_entry(self, data, url, video_id=None):
  22         video_id = compat_str(video_id or data['nid'])
  23         title = data['title']
  24
  25         formats = self._extract_m3u8_formats(
  26             data['file'], video_id, 'mp4', entry_protocol='m3u8_native',
  27             m3u8_id='hls')
  28
  29         description = data.get('description')
  30         thumbnail = urljoin(url, data.get('image'))
  31         series = data.get('show_name')
  32         episode = data.get('episode_name')
  33
  34         subtitles = {}
  35         tracks = data.get('tracks')
  36         if isinstance(tracks, list):
  37             for track in tracks:
  38                 if not isinstance(track, dict):
  39                     continue
  40                 if track.get('kind') != 'captions':
  41                     continue
  42                 track_file = url_or_none(track.get('file'))
  43                 if not track_file:
  44                     continue
  45                 label = track.get('label')
  46                 lang = self._SUBTITLE_LANGS.get(label, label) or 'en'
  47                 subtitles.setdefault(lang, []).append({
  48                     'url': track_file,
  49                 })
  50
  51         return {
  52             'id': video_id,
  53             'title': title,
  54             'description': description,
  55             'thumbnail': thumbnail,
  56             'series': series,
  57             'episode': episode,
  58             'formats': formats,
  59             'subtitles': subtitles,
  60         }
  61
  62
  63 class WWEIE(WWEBaseIE):
  64     _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*videos/(?P<id>[^/?#&]+)'
  65     _TESTS = [{
  66         'url': 'https://www.wwe.com/videos/daniel-bryan-vs-andrade-cien-almas-smackdown-live-sept-4-2018',
  67         'md5': '92811c6a14bfc206f7a6a9c5d9140184',
  68         'info_dict': {
  69             'id': '40048199',
  70             'ext': 'mp4',
  71             'title': 'Daniel Bryan vs. Andrade "Cien" Almas: SmackDown LIVE, Sept. 4, 2018',
  72             'description': 'md5:2d7424dbc6755c61a0e649d2a8677f67',
  73             'thumbnail': r're:^https?://.*\.jpg$',
  74         }
  75     }, {
  76         'url': 'https://de.wwe.com/videos/gran-metalik-vs-tony-nese-wwe-205-live-sept-4-2018',
  77         'only_matching': True,
  78     }]
  79
  80     def _real_extract(self, url):
  81         display_id = self._match_id(url)
  82         webpage = self._download_webpage(url, display_id)
  83
  84         landing = self._parse_json(
  85             self._html_search_regex(
  86                 r'(?s)Drupal\.settings\s*,\s*({.+?})\s*\)\s*;',
  87                 webpage, 'drupal settings'),
  88             display_id)['WWEVideoLanding']
  89
  90         data = landing['initialVideo']['playlist'][0]
  91         video_id = landing.get('initialVideoId')
  92
  93         info = self._extract_entry(data, url, video_id)
  94         info['display_id'] = display_id
  95         return info
  96
  97
  98 class WWEPlaylistIE(WWEBaseIE):
  99     _VALID_URL = r'https?://(?:[^/]+\.)?wwe\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
 100     _TESTS = [{
 101         'url': 'https://www.wwe.com/shows/raw/2018-11-12',
 102         'info_dict': {
 103             'id': '2018-11-12',
 104         },
 105         'playlist_mincount': 11,
 106     }, {
 107         'url': 'http://www.wwe.com/article/walk-the-prank-wwe-edition',
 108         'only_matching': True,
 109     }, {
 110         'url': 'https://www.wwe.com/shows/wwenxt/article/matt-riddle-interview',
 111         'only_matching': True,
 112     }]
 113
 114     @classmethod
 115     def suitable(cls, url):
 116         return False if WWEIE.suitable(url) else super(WWEPlaylistIE, cls).suitable(url)
 117
 118     def _real_extract(self, url):
 119         display_id = self._match_id(url)
 120         webpage = self._download_webpage(url, display_id)
 121
 122         entries = []
 123         for mobj in re.finditer(
 124                 r'data-video\s*=\s*(["\'])(?P<data>{.+?})\1', webpage):
 125             video = self._parse_json(
 126                 mobj.group('data'), display_id, transform_source=unescapeHTML,
 127                 fatal=False)
 128             if not video:
 129                 continue
 130             data = try_get(video, lambda x: x['playlist'][0], dict)
 131             if not data:
 132                 continue
 133             try:
 134                 entry = self._extract_entry(data, url)
 135             except Exception:
 136                 continue
 137             entry['extractor_key'] = WWEIE.ie_key()
 138             entries.append(entry)
 139
 140         return self.playlist_result(entries, display_id)