aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/yandexvideo.py
blob: 6a166ec9b92897578f52e9c5ae20bf078b9e8f05 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    int_or_none,
    try_get,
    url_or_none,
)


class YandexVideoIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    https?://
                        (?:
                            yandex\.ru(?:/(?:portal/(?:video|efir)|efir))?/?\?.*?stream_id=|
                            frontend\.vh\.yandex\.ru/player/
                        )
                        (?P<id>(?:[\da-f]{32}|[\w-]{12}))
                    '''
    _TESTS = [{
        'url': 'https://yandex.ru/portal/video?stream_id=4dbb36ec4e0526d58f9f2dc8f0ecf374',
        'md5': 'e02a05bfaf0d9615ef07ae3a10f4faf4',
        'info_dict': {
            'id': '4dbb36ec4e0526d58f9f2dc8f0ecf374',
            'ext': 'mp4',
            'title': 'Русский Вудсток - главный рок-фест в истории СССР / вДудь',
            'description': 'md5:7d6b8d4bc4a3b9a56499916c1ea5b5fa',
            'thumbnail': r're:^https?://',
            'timestamp': 1549972939,
            'duration': 5575,
            'age_limit': 18,
            'upload_date': '20190212',
            'view_count': int,
            'like_count': int,
            'dislike_count': int,
        },
    }, {
        'url': 'https://yandex.ru/portal/efir?stream_id=4dbb262b4fe5cf15a215de4f34eee34d&from=morda',
        'only_matching': True,
    }, {
        'url': 'https://yandex.ru/?stream_id=4dbb262b4fe5cf15a215de4f34eee34d',
        'only_matching': True,
    }, {
        'url': 'https://frontend.vh.yandex.ru/player/4dbb262b4fe5cf15a215de4f34eee34d?from=morda',
        'only_matching': True,
    }, {
        # vod-episode, series episode
        'url': 'https://yandex.ru/portal/video?stream_id=45b11db6e4b68797919c93751a938cee',
        'only_matching': True,
    }, {
        # episode, sports
        'url': 'https://yandex.ru/?stream_channel=1538487871&stream_id=4132a07f71fb0396be93d74b3477131d',
        'only_matching': True,
    }, {
        # DASH with DRM
        'url': 'https://yandex.ru/portal/video?from=morda&stream_id=485a92d94518d73a9d0ff778e13505f8',
        'only_matching': True,
    }, {
        'url': 'https://yandex.ru/efir?stream_active=watching&stream_id=v7a2dZ-v5mSI&from_block=efir_newtab',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        player = try_get((self._download_json(
            'https://frontend.vh.yandex.ru/graphql', video_id, data=('''{
  player(content_id: "%s") {
    computed_title
    content_url
    description
    dislikes
    duration
    likes
    program_title
    release_date
    release_date_ut
    release_year
    restriction_age
    season
    start_time
    streams
    thumbnail
    title
    views_count
  }
}''' % video_id).encode(), fatal=False)), lambda x: x['player']['content'])
        if not player or player.get('error'):
            player = self._download_json(
                'https://frontend.vh.yandex.ru/v23/player/%s.json' % video_id,
                video_id, query={
                    'stream_options': 'hires',
                    'disable_trackings': 1,
                })
        content = player['content']

        title = content.get('title') or content['computed_title']

        formats = []
        streams = content.get('streams') or []
        streams.append({'url': content.get('content_url')})
        for stream in streams:
            content_url = url_or_none(stream.get('url'))
            if not content_url:
                continue
            ext = determine_ext(content_url)
            if ext == 'ismc':
                continue
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    content_url, video_id, 'mp4',
                    'm3u8_native', m3u8_id='hls', fatal=False))
            elif ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    content_url, video_id, mpd_id='dash', fatal=False))
            else:
                formats.append({'url': content_url})

        self._sort_formats(formats)

        timestamp = (int_or_none(content.get('release_date'))
                     or int_or_none(content.get('release_date_ut'))
                     or int_or_none(content.get('start_time')))
        season = content.get('season') or {}

        return {
            'id': video_id,
            'title': title,
            'description': content.get('description'),
            'thumbnail': content.get('thumbnail'),
            'timestamp': timestamp,
            'duration': int_or_none(content.get('duration')),
            'series': content.get('program_title'),
            'age_limit': int_or_none(content.get('restriction_age')),
            'view_count': int_or_none(content.get('views_count')),
            'like_count': int_or_none(content.get('likes')),
            'dislike_count': int_or_none(content.get('dislikes')),
            'season_number': int_or_none(season.get('season_number')),
            'season_id': season.get('id'),
            'release_year': int_or_none(content.get('release_year')),
            'formats': formats,
        }