aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/eagleplatform.py
blob: 5e1de04a1609d5d8e6301f5f26da6267e1b85cf6 (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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_HTTPError,
    compat_str,
)
from ..utils import (
    ExtractorError,
    int_or_none,
)


class EaglePlatformIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                    (?:
                        eagleplatform:(?P<custom_host>[^/]+):|
                        https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
                    )
                    (?P<id>\d+)
                '''
    _TESTS = [{
        # http://lenta.ru/news/2015/03/06/navalny/
        'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
        # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
        'info_dict': {
            'id': '227304',
            'ext': 'mp4',
            'title': 'Навальный вышел на свободу',
            'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 87,
            'view_count': int,
            'age_limit': 0,
        },
    }, {
        # http://muz-tv.ru/play/7129/
        # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
        'url': 'eagleplatform:media.clipyou.ru:12820',
        'md5': '358597369cf8ba56675c1df15e7af624',
        'info_dict': {
            'id': '12820',
            'ext': 'mp4',
            'title': "'O Sole Mio",
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 216,
            'view_count': int,
        },
        'skip': 'Georestricted',
    }]

    @staticmethod
    def _extract_url(webpage):
        # Regular iframe embedding
        mobj = re.search(
            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1',
            webpage)
        if mobj is not None:
            return mobj.group('url')
        PLAYER_JS_RE = r'''
                        <script[^>]+
                            src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
                        .+?
                    '''
        # "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
        mobj = re.search(
            r'''(?xs)
                    %s
                    <div[^>]+
                        class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
                        data-id=["\'](?P<id>\d+)
            ''' % PLAYER_JS_RE, webpage)
        if mobj is not None:
            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
        # Generalization of "Javascript code usage", "Combined usage" and
        # "Usage without attaching to DOM" embeddings (see
        # http://dultonmedia.github.io/eplayer/)
        mobj = re.search(
            r'''(?xs)
                    %s
                    <script>
                    .+?
                    new\s+EaglePlayer\(
                        (?:[^,]+\s*,\s*)?
                        {
                            .+?
                            \bid\s*:\s*["\']?(?P<id>\d+)
                            .+?
                        }
                    \s*\)
                    .+?
                    </script>
            ''' % PLAYER_JS_RE, webpage)
        if mobj is not None:
            return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()

    @staticmethod
    def _handle_error(response):
        status = int_or_none(response.get('status', 200))
        if status != 200:
            raise ExtractorError(' '.join(response['errors']), expected=True)

    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
        try:
            response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
        except ExtractorError as ee:
            if isinstance(ee.cause, compat_HTTPError):
                response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
                self._handle_error(response)
            raise
        return response

    def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
        return self._download_json(url_or_request, video_id, note)['data'][0]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')

        player_data = self._download_json(
            'http://%s/api/player_data?id=%s' % (host, video_id), video_id)

        media = player_data['data']['playlist']['viewports'][0]['medialist'][0]

        title = media['title']
        description = media.get('description')
        thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
        duration = int_or_none(media.get('duration'))
        view_count = int_or_none(media.get('views'))

        age_restriction = media.get('age_restriction')
        age_limit = None
        if age_restriction:
            age_limit = 0 if age_restriction == 'allow_all' else 18

        secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')

        formats = []

        m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
        m3u8_formats = self._extract_m3u8_formats(
            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
            m3u8_id='hls', fatal=False)
        formats.extend(m3u8_formats)

        m3u8_formats_dict = {}
        for f in m3u8_formats:
            if f.get('height') is not None:
                m3u8_formats_dict[f['height']] = f

        mp4_data = self._download_json(
            # Secure mp4 URL is constructed according to Player.prototype.mp4 from
            # http://lentaru.media.eagleplatform.com/player/player.js
            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
            video_id, 'Downloading mp4 JSON', fatal=False)
        if mp4_data:
            for format_id, format_url in mp4_data.get('data', {}).items():
                if not isinstance(format_url, compat_str):
                    continue
                height = int_or_none(format_id)
                if height is not None and m3u8_formats_dict.get(height):
                    f = m3u8_formats_dict[height].copy()
                    f.update({
                        'format_id': f['format_id'].replace('hls', 'http'),
                        'protocol': 'http',
                    })
                else:
                    f = {
                        'format_id': 'http-%s' % format_id,
                        'height': int_or_none(format_id),
                    }
                f['url'] = format_url
                formats.append(f)

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'duration': duration,
            'view_count': view_count,
            'age_limit': age_limit,
            'formats': formats,
        }