youtube_dlc/extractor/yandexvideo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     int_or_none,
   8     try_get,
   9     url_or_none,
  10 )
  11
  12
  13 class YandexVideoIE(InfoExtractor):
  14     _VALID_URL = r'''(?x)
  15                     https?://
  16                         (?:
  17                             yandex\.ru(?:/(?:portal/(?:video|efir)|efir))?/?\?.*?stream_id=|
  18                             frontend\.vh\.yandex\.ru/player/
  19                         )
  20                         (?P<id>(?:[\da-f]{32}|[\w-]{12}))
  21                     '''
  22     _TESTS = [{
  23         'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
  24         'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
  25         'info_dict': {
  26             'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
  27             'ext': 'mp4',
  28             'title': 'Русский Вудсток - главный рок-фест в истории СССР / вДудь',
  29             'description': 'md5:7d6b8d4bc4a3b9a56499916c1ea5b5fa',
  30             'thumbnail': r're:^https?://',
  31             'timestamp': 1549972939,
  32             'duration': 5575,
  33             'age_limit': 18,
  34             'upload_date': '20190212',
  35             'view_count': int,
  36             'like_count': int,
  37             'dislike_count': int,
  38         },
  39     }, {
  40         'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
  41         'only_matching': True,
  42     }, {
  43         'url': 'https://yandex.ru/?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
  44         'only_matching': True,
  45     }, {
  46         'url': 'https://frontend.vh.yandex.ru/player/4dbb262b4fe5cf15a215de4f34eee34d?from=morda',
  47         'only_matching': True,
  48     }, {
  49         # vod-episode, series episode
  50         'url': 'https://yandex.ru/portal/video?stream_id=45b11db6e4b68797919c93751a938cee',
  51         'only_matching': True,
  52     }, {
  53         # episode, sports
  54         'url': 'https://yandex.ru/?stream_channel=1538487871&stream_id=4132a07f71fb0396be93d74b3477131d',
  55         'only_matching': True,
  56     }, {
  57         # DASH with DRM
  58         'url': 'https://yandex.ru/portal/video?from=morda&stream_id=485a92d94518d73a9d0ff778e13505f8',
  59         'only_matching': True,
  60     }, {
  61         'url': 'https://yandex.ru/efir?stream_active=watching&stream_id=v7a2dZ-v5mSI&from_block=efir_newtab',
  62         'only_matching': True,
  63     }]
  64
  65     def _real_extract(self, url):
  66         video_id = self._match_id(url)
  67
  68         player = try_get((self._download_json(
  69             'https://frontend.vh.yandex.ru/graphql', video_id, data=('''{
  70   player(content_id: "%s") {
  71     computed_title
  72     content_url
  73     description
  74     dislikes
  75     duration
  76     likes
  77     program_title
  78     release_date
  79     release_date_ut
  80     release_year
  81     restriction_age
  82     season
  83     start_time
  84     streams
  85     thumbnail
  86     title
  87     views_count
  88   }
  89 }''' % video_id).encode(), fatal=False)), lambda x: x['player']['content'])
  90         if not player or player.get('error'):
  91             player = self._download_json(
  92                 'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
  93                 video_id, query={
  94                     'stream_options': 'hires',
  95                     'disable_trackings': 1,
  96                 })
  97         content = player['content']
  98
  99         title = content.get('title') or content['computed_title']
 100
 101         formats = []
 102         streams = content.get('streams') or []
 103         streams.append({'url': content.get('content_url')})
 104         for stream in streams:
 105             content_url = url_or_none(stream.get('url'))
 106             if not content_url:
 107                 continue
 108             ext = determine_ext(content_url)
 109             if ext == 'ismc':
 110                 continue
 111             elif ext == 'm3u8':
 112                 formats.extend(self._extract_m3u8_formats(
 113                     content_url, video_id, 'mp4',
 114                     'm3u8_native', m3u8_id='hls', fatal=False))
 115             elif ext == 'mpd':
 116                 formats.extend(self._extract_mpd_formats(
 117                     content_url, video_id, mpd_id='dash', fatal=False))
 118             else:
 119                 formats.append({'url': content_url})
 120
 121         self._sort_formats(formats)
 122
 123         timestamp = (int_or_none(content.get('release_date'))
 124                      or int_or_none(content.get('release_date_ut'))
 125                      or int_or_none(content.get('start_time')))
 126         season = content.get('season') or {}
 127
 128         return {
 129             'id': video_id,
 130             'title': title,
 131             'description': content.get('description'),
 132             'thumbnail': content.get('thumbnail'),
 133             'timestamp': timestamp,
 134             'duration': int_or_none(content.get('duration')),
 135             'series': content.get('program_title'),
 136             'age_limit': int_or_none(content.get('restriction_age')),
 137             'view_count': int_or_none(content.get('views_count')),
 138             'like_count': int_or_none(content.get('likes')),
 139             'dislike_count': int_or_none(content.get('dislikes')),
 140             'season_number': int_or_none(season.get('season_number')),
 141             'season_id': season.get('id'),
 142             'release_year': int_or_none(content.get('release_year')),
 143             'formats': formats,
 144         }