aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/eagleplatform.py
blob: 0f8c73fd7d330da33afd3c2a3d2cb732e4d3ff33 (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
# coding: utf-8
from __future__ import unicode_literals

import re

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


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',
        'md5': '881ee8460e1b7735a8be938e2ffb362b',
        'info_dict': {
            'id': '227304',
            'ext': 'mp4',
            'title': 'Навальный вышел на свободу',
            'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 87,
            'view_count': int,
            'age_limit': 0,
        },
    }, {
        # http://muz-tv.ru/play/7129/
        # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
        'url': 'eagleplatform:media.clipyou.ru:12820',
        'md5': '358597369cf8ba56675c1df15e7af624',
        'info_dict': {
            'id': '12820',
            'ext': 'mp4',
            'title': "'O Sole Mio",
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 216,
            'view_count': int,
        },
        'skip': 'Georestricted',
    }]

    @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'):
        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')
        formats.extend(m3u8_formats)

        mp4_url = self._get_video_url(
            # 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', 'mp4', secure_m3u8),
            video_id, 'Downloading mp4 JSON')
        mp4_url_basename = url_basename(mp4_url)
        for m3u8_format in m3u8_formats:
            mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url'])
            if mobj:
                http_format = m3u8_format.copy()
                http_format.update({
                    'url': mp4_url.replace(mp4_url_basename, mobj.group(1)),
                    'format_id': m3u8_format['format_id'].replace('hls', 'http'),
                    'protocol': 'http',
                })
                formats.append(http_format)

        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,
        }