Raphaël G. Git Repositories - youtubedl/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     extract_attributes,
   8     float_or_none,
   9     int_or_none,
  10     try_get,
  11 )
  12
  13
  14 class EllenTubeBaseIE(InfoExtractor):
  15     def _extract_data_config(self, webpage, video_id):
  16         details = self._search_regex(
  17             r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?></div>)', webpage,
  18             'details')
  19         return self._parse_json(
  20             extract_attributes(details)['data-config'], video_id)
  21
  22     def _extract_video(self, data, video_id):
  23         title = data['title']
  24
  25         formats = []
  26         duration = None
  27         for entry in data.get('media'):
  28             if entry.get('id') == 'm3u8':
  29                 formats = self._extract_m3u8_formats(
  30                     entry['url'], video_id, 'mp4',
  31                     entry_protocol='m3u8_native', m3u8_id='hls')
  32                 duration = int_or_none(entry.get('duration'))
  33                 break
  34         self._sort_formats(formats)
  35
  36         def get_insight(kind):
  37             return int_or_none(try_get(
  38                 data, lambda x: x['insight']['%ss' % kind]))
  39
  40         return {
  41             'extractor_key': EllenTubeIE.ie_key(),
  42             'id': video_id,
  43             'title': title,
  44             'description': data.get('description'),
  45             'duration': duration,
  46             'thumbnail': data.get('thumbnail'),
  47             'timestamp': float_or_none(data.get('publishTime'), scale=1000),
  48             'view_count': get_insight('view'),
  49             'like_count': get_insight('like'),
  50             'formats': formats,
  51         }
  52
  53
  54 class EllenTubeIE(EllenTubeBaseIE):
  55     _VALID_URL = r'''(?x)
  56                         (?:
  57                             ellentube:|
  58                             https://api-prod\.ellentube\.com/ellenapi/api/item/
  59                         )
  60                         (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
  61                     '''
  62     _TESTS = [{
  63         'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3',
  64         'md5': '2fabc277131bddafdd120e0fc0f974c9',
  65         'info_dict': {
  66             'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
  67             'ext': 'mp4',
  68             'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
  69             'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
  70             'thumbnail': r're:^https?://.+?',
  71             'duration': 514,
  72             'timestamp': 1508505120,
  73             'upload_date': '20171020',
  74             'view_count': int,
  75             'like_count': int,
  76         }
  77     }, {
  78         'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
  79         'only_matching': True,
  80     }]
  81
  82     def _real_extract(self, url):
  83         video_id = self._match_id(url)
  84         data = self._download_json(
  85             'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id,
  86             video_id)
  87         return self._extract_video(data, video_id)
  88
  89
  90 class EllenTubeVideoIE(EllenTubeBaseIE):
  91     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+?)\.html'
  92     _TEST = {
  93         'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
  94         'only_matching': True,
  95     }
  96
  97     def _real_extract(self, url):
  98         display_id = self._match_id(url)
  99         webpage = self._download_webpage(url, display_id)
 100         video_id = self._extract_data_config(webpage, display_id)['id']
 101         return self.url_result(
 102             'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(),
 103             video_id=video_id)
 104
 105
 106 class EllenTubePlaylistIE(EllenTubeBaseIE):
 107     _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P<id>.+?)\.html'
 108     _TESTS = [{
 109         'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html',
 110         'info_dict': {
 111             'id': 'dax-shepard-jordan-fisher-haim',
 112             'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM",
 113             'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c',
 114         },
 115         'playlist_count': 6,
 116     }, {
 117         'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html',
 118         'only_matching': True,
 119     }]
 120
 121     def _real_extract(self, url):
 122         display_id = self._match_id(url)
 123         webpage = self._download_webpage(url, display_id)
 124         data = self._extract_data_config(webpage, display_id)['data']
 125         feed = self._download_json(
 126             'https://api-prod.ellentube.com/ellenapi/api/feed/?%s'
 127             % data['filter'], display_id)
 128         entries = [
 129             self._extract_video(elem, elem['id'])
 130             for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')]
 131         return self.playlist_result(
 132             entries, display_id, data.get('title'),
 133             clean_html(data.get('description')))