youtube_dl/extractor/nintendo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .ooyala import OoyalaIE
   8
   9
  10 class NintendoIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?nintendo\.com/(?:games/detail|nintendo-direct)/(?P<id>[^/?#&]+)'
  12     _TESTS = [{
  13         'url': 'https://www.nintendo.com/games/detail/duck-hunt-wii-u/',
  14         'info_dict': {
  15             'id': 'MzMmticjp0VPzO3CCj4rmFOuohEuEWoW',
  16             'ext': 'flv',
  17             'title': 'Duck Hunt Wii U VC NES - Trailer',
  18             'duration': 60.326,
  19         },
  20         'params': {
  21             'skip_download': True,
  22         },
  23         'add_ie': ['Ooyala'],
  24     }, {
  25         'url': 'http://www.nintendo.com/games/detail/tokyo-mirage-sessions-fe-wii-u',
  26         'info_dict': {
  27             'id': 'tokyo-mirage-sessions-fe-wii-u',
  28             'title': 'Tokyo Mirage Sessions ♯FE',
  29         },
  30         'playlist_count': 4,
  31     }, {
  32         'url': 'https://www.nintendo.com/nintendo-direct/09-04-2019/',
  33         'info_dict': {
  34             'id': 'J2bXdmaTE6fe3dWJTPcc7m23FNbc_A1V',
  35             'ext': 'mp4',
  36             'title': 'Switch_ROS_ND0904-H264.mov',
  37             'duration': 2324.758,
  38         },
  39         'params': {
  40             'skip_download': True,
  41         },
  42         'add_ie': ['Ooyala'],
  43     }]
  44
  45     def _real_extract(self, url):
  46         page_id = self._match_id(url)
  47
  48         webpage = self._download_webpage(url, page_id)
  49
  50         entries = [
  51             OoyalaIE._build_url_result(m.group('code'))
  52             for m in re.finditer(
  53                 r'data-(?:video-id|directVideoId)=(["\'])(?P<code>(?:(?!\1).)+)\1', webpage)]
  54
  55         title = self._html_search_regex(
  56             r'(?s)<(?:span|div)[^>]+class="(?:title|wrapper)"[^>]*>.*?<h1>(.+?)</h1>',
  57             webpage, 'title', fatal=False)
  58
  59         return self.playlist_result(
  60             entries, page_id, title)