_ Git - youtube-dl/blob - youtube_dl/extractor/ellentube.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_html,
   7     int_or_none,
   8 )
   9
  10
  11 class EllenTubeIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13                     (?:
  14                         https://api-prod\.ellentube\.com/ellenapi/api/item/
  15                         |ellentube:
  16                     )
  17                     (?P<id>
  18                         [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}
  19                     )'''
  20
  21     _TESTS = [{
  22         'url': 'https://api-prod.ellentube.com/ellenapi/api/item/75c64c16-aefd-4558-b4f5-3de09b22e6fc',
  23         'match_only': True,
  24     }, {
  25         'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
  26         'match_only': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         data = self._download_json(
  32             'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, video_id)
  33         title = data['title']
  34         description = data.get('description')
  35         publish_time = int_or_none(data.get('publishTime'))
  36         thumbnail = data.get('thumbnail')
  37
  38         formats = []
  39         duration = None
  40         for entry in data.get('media'):
  41             if entry.get('id') == 'm3u8':
  42                 formats = self._extract_m3u8_formats(
  43                     entry.get('url'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  44                 duration = int_or_none(entry.get('duration'))
  45                 break
  46         self._sort_formats(formats)
  47         return {
  48             'id': video_id,
  49             'title': title,
  50             'description': description,
  51             'duration': duration,
  52             'thumbnail': thumbnail,
  53             'timestamp': publish_time,
  54             'formats': formats,
  55         }
  56
  57
  58 class EllenTubeVideoIE(InfoExtractor):
  59     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+)\.html'
  60
  61     _TEST = {
  62         'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
  63         'md5': '2fabc277131bddafdd120e0fc0f974c9',
  64         'info_dict': {
  65             'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
  66             'ext': 'mp4',
  67             'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
  68             'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
  69             'duration': 514,
  70             'timestamp': 1508505120000,
  71             'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
  72         }
  73     }
  74
  75     def _real_extract(self, url):
  76         display_id = self._match_id(url)
  77         webpage = self._download_webpage(url, display_id)
  78         video_id = self._html_search_regex(
  79             r'(?s)<!--\s*CONTENT\s*-->.*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
  80             webpage, 'video id')
  81         return self.url_result('ellentube:%s' % video_id, 'EllenTube')
  82
  83
  84 class EllenTubePlaylistIE(InfoExtractor):
  85     def _extract_videos_from_json(self, data, display_id):
  86         return [self.url_result('ellentube:%s' % elem['id'], 'EllenTube')
  87                 for elem in data if elem.get('type') == 'VIDEO']
  88
  89     def _extract_playlist(self, url, display_id, extract_description=True):
  90         webpage = self._download_webpage(url, display_id)
  91         playlist_data = self._html_search_regex(
  92             r'<div\s+data-component\s*=\s*"Details"(.+)</div>', webpage, 'playlist data')
  93         playlist_title = self._search_regex(
  94             r'"title"\s*:\s*"(.+?)"', playlist_data, 'playlist title')
  95         playlist_description = clean_html(self._search_regex(
  96             r'"description"\s*:\s*"(.+?)"', playlist_data, 'playlist description',
  97             fatal=False)) if extract_description else None
  98         api_search = self._search_regex(
  99             r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request')
 100         api_data = self._download_json(
 101             'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search,
 102             display_id)
 103         return self.playlist_result(
 104             self._extract_videos_from_json(api_data, display_id),
 105             display_id, playlist_title, playlist_description)
 106
 107
 108 class EllenTubeEpisodeIE(EllenTubePlaylistIE):
 109     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P<id>.+)\.html'
 110
 111     _TEST = {
 112         'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html',
 113         'info_dict': {
 114             'id': 'dax-shepard-jordan-fisher-haim',
 115             'title': 'Dax Shepard, \'DWTS\' Team Jordan Fisher & Lindsay Arnold, HAIM',
 116             'description': 'md5:aed85d42892f6126e71ec5ed2aea2a0d'
 117         },
 118         'playlist_count': 6,
 119     }
 120
 121     def _real_extract(self, url):
 122         display_id = self._match_id(url)
 123         return self._extract_playlist(url, display_id)
 124
 125
 126 class EllenTubeStudioIE(EllenTubePlaylistIE):
 127     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P<id>.+)\.html'
 128
 129     _TEST = {
 130         'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html',
 131         'info_dict': {
 132             'id': 'macey-goes-rving0',
 133             'title': 'Macey Goes RVing',
 134         },
 135         'playlist_mincount': 3,
 136     }
 137
 138     def _real_extract(self, url):
 139         display_id = self._match_id(url)
 140         return self._extract_playlist(url, display_id, False)