youtube_dl/extractor/byutv.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class BYUtvIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
  11     _TESTS = [{
  12         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
  13         'info_dict': {
  14             'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
  15             'display_id': 'studio-c-season-5-episode-5',
  16             'ext': 'mp4',
  17             'title': 'Season 5 Episode 5',
  18             'description': 'md5:e07269172baff037f8e8bf9956bc9747',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'duration': 1486.486,
  21         },
  22         'params': {
  23             'skip_download': True,
  24         },
  25         'add_ie': ['Ooyala'],
  26     }, {
  27         'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34         display_id = mobj.group('display_id') or video_id
  35
  36         webpage = self._download_webpage(url, display_id)
  37         episode_code = self._search_regex(
  38             r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
  39
  40         ep = self._parse_json(
  41             episode_code, display_id, transform_source=lambda s:
  42             re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
  43
  44         if ep['providerType'] != 'Ooyala':
  45             raise ExtractorError('Unsupported provider %s' % ep['provider'])
  46
  47         return {
  48             '_type': 'url_transparent',
  49             'ie_key': 'Ooyala',
  50             'url': 'ooyala:%s' % ep['providerId'],
  51             'id': video_id,
  52             'display_id': display_id,
  53             'title': ep['title'],
  54             'description': ep.get('description'),
  55             'thumbnail': ep.get('imageThumbnail'),
  56         }
  57
  58
  59 class BYUtvEventIE(InfoExtractor):
  60     _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)'
  61     _TEST = {
  62         'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b',
  63         'info_dict': {
  64             'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b',
  65             'ext': 'mp4',
  66             'title': 'Toledo vs. BYU (9/30/16)',
  67         },
  68         'params': {
  69             'skip_download': True,
  70         },
  71         'add_ie': ['Ooyala'],
  72     }
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76
  77         webpage = self._download_webpage(url, video_id)
  78
  79         ooyala_id = self._search_regex(
  80             r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
  81             webpage, 'ooyala id', group='id')
  82
  83         title = self._search_regex(
  84             r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage,
  85             'title').strip()
  86
  87         return {
  88             '_type': 'url_transparent',
  89             'ie_key': 'Ooyala',
  90             'url': 'ooyala:%s' % ooyala_id,
  91             'id': video_id,
  92             'title': title,
  93         }