yt_dlp/extractor/ellentube.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     extract_attributes,
   5     float_or_none,
   6     int_or_none,
   7     try_get,
   8 )
   9
  10
  11 class EllenTubeBaseIE(InfoExtractor):
  12     def _extract_data_config(self, webpage, video_id):
  13         details = self._search_regex(
  14             r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?></div>)', webpage,
  15             'details')
  16         return self._parse_json(
  17             extract_attributes(details)['data-config'], video_id)
  18
  19     def _extract_video(self, data, video_id):
  20         title = data['title']
  21
  22         formats = []
  23         duration = None
  24         for entry in data.get('media'):
  25             if entry.get('id') == 'm3u8':
  26                 formats, subtitles = self._extract_m3u8_formats_and_subtitles(
  27                     entry['url'], video_id, 'mp4',
  28                     entry_protocol='m3u8_native', m3u8_id='hls')
  29                 duration = int_or_none(entry.get('duration'))
  30                 break
  31
  32         def get_insight(kind):
  33             return int_or_none(try_get(
  34                 data, lambda x: x['insight']['%ss' % kind]))
  35
  36         return {
  37             'extractor_key': EllenTubeIE.ie_key(),
  38             'id': video_id,
  39             'title': title,
  40             'description': data.get('description'),
  41             'duration': duration,
  42             'thumbnail': data.get('thumbnail'),
  43             'timestamp': float_or_none(data.get('publishTime'), scale=1000),
  44             'view_count': get_insight('view'),
  45             'like_count': get_insight('like'),
  46             'formats': formats,
  47             'subtitles': subtitles,
  48         }
  49
  50
  51 class EllenTubeIE(EllenTubeBaseIE):
  52     _VALID_URL = r'''(?x)
  53                         (?:
  54                             ellentube:|
  55                             https://api-prod\.ellentube\.com/ellenapi/api/item/
  56                         )
  57                         (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
  58                     '''
  59     _TESTS = [{
  60         'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3',
  61         'md5': '2fabc277131bddafdd120e0fc0f974c9',
  62         'info_dict': {
  63             'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
  64             'ext': 'mp4',
  65             'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
  66             'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
  67             'thumbnail': r're:^https?://.+?',
  68             'duration': 514,
  69             'timestamp': 1508505120,
  70             'upload_date': '20171020',
  71             'view_count': int,
  72             'like_count': int,
  73         }
  74     }, {
  75         'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
  76         'only_matching': True,
  77     }]
  78
  79     def _real_extract(self, url):
  80         video_id = self._match_id(url)
  81         data = self._download_json(
  82             'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id,
  83             video_id)
  84         return self._extract_video(data, video_id)
  85
  86
  87 class EllenTubeVideoIE(EllenTubeBaseIE):
  88     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+?)\.html'
  89     _TEST = {
  90         'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
  91         'only_matching': True,
  92     }
  93
  94     def _real_extract(self, url):
  95         display_id = self._match_id(url)
  96         webpage = self._download_webpage(url, display_id)
  97         video_id = self._extract_data_config(webpage, display_id)['id']
  98         return self.url_result(
  99             'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(),
 100             video_id=video_id)
 101
 102
 103 class EllenTubePlaylistIE(EllenTubeBaseIE):
 104     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P<id>.+?)\.html'
 105     _TESTS = [{
 106         'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html',
 107         'info_dict': {
 108             'id': 'dax-shepard-jordan-fisher-haim',
 109             'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM",
 110             'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c',
 111         },
 112         'playlist_count': 6,
 113     }, {
 114         'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html',
 115         'only_matching': True,
 116     }]
 117
 118     def _real_extract(self, url):
 119         display_id = self._match_id(url)
 120         webpage = self._download_webpage(url, display_id)
 121         data = self._extract_data_config(webpage, display_id)['data']
 122         feed = self._download_json(
 123             'https://api-prod.ellentube.com/ellenapi/api/feed/?%s'
 124             % data['filter'], display_id)
 125         entries = [
 126             self._extract_video(elem, elem['id'])
 127             for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')]
 128         return self.playlist_result(
 129             entries, display_id, data.get('title'),
 130             clean_html(data.get('description')))