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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     merge_dicts,
   8     urljoin,
   9 )
  10
  11
  12 class WakanimIE(InfoExtractor):
  13     _VALID_URL = r'https://(?:www\.)?wakanim\.tv/[^/]+/v2/catalogue/episode/(?P<id>\d+)'
  14     _TESTS = [{
  15         'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/2997/the-asterisk-war-omu-staffel-1-episode-02-omu',
  16         'info_dict': {
  17             'id': '2997',
  18             'ext': 'mp4',
  19             'title': 'Episode 02',
  20             'description': 'md5:2927701ea2f7e901de8bfa8d39b2852d',
  21             'series': 'The Asterisk War  (OmU.)',
  22             'season_number': 1,
  23             'episode': 'Episode 02',
  24             'episode_number': 2,
  25         },
  26         'params': {
  27             'format': 'bestvideo',
  28             'skip_download': True,
  29         },
  30     }, {
  31         # DRM Protected
  32         'url': 'https://www.wakanim.tv/de/v2/catalogue/episode/7843/sword-art-online-alicization-omu-arc-2-folge-15-omu',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, video_id)
  40
  41         m3u8_url = urljoin(url, self._search_regex(
  42             r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url',
  43             group='url'))
  44         # https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls
  45         encryption = self._search_regex(
  46             r'encryption%3D(c(?:enc|bc(?:s-aapl)?))',
  47             m3u8_url, 'encryption', default=None)
  48         if encryption and encryption in ('cenc', 'cbcs-aapl'):
  49             raise ExtractorError('This video is DRM protected.', expected=True)
  50
  51         formats = self._extract_m3u8_formats(
  52             m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
  53             m3u8_id='hls')
  54
  55         info = self._search_json_ld(webpage, video_id, default={})
  56
  57         title = self._search_regex(
  58             (r'<h1[^>]+\bclass=["\']episode_h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
  59              r'<span[^>]+\bclass=["\']episode_title["\'][^>]*>(?P<title>[^<]+)'),
  60             webpage, 'title', default=None, group='title')
  61
  62         return merge_dicts(info, {
  63             'id': video_id,
  64             'title': title,
  65             'formats': formats,
  66         })