aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/mitele.py
blob: 42759eae87cecd940c7b8edd8b9aabbb578e9039 (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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
# coding: utf-8
from __future__ import unicode_literals

import json
import uuid

from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..compat import (
    compat_str,
    compat_urlparse,
)
from ..utils import (
    int_or_none,
    extract_attributes,
    determine_ext,
    smuggle_url,
    parse_duration,
)


class MiTeleBaseIE(InfoExtractor):
    def _get_player_info(self, url, webpage):
        player_data = extract_attributes(self._search_regex(
            r'(?s)(<ms-video-player.+?</ms-video-player>)',
            webpage, 'ms video player'))
        video_id = player_data['data-media-id']
        if player_data.get('data-cms-id') == 'ooyala':
            return self.url_result(
                'ooyala:%s' % video_id, ie=OoyalaIE.ie_key(), video_id=video_id)
        config_url = compat_urlparse.urljoin(url, player_data['data-config'])
        config = self._download_json(
            config_url, video_id, 'Downloading config JSON')
        mmc_url = config['services']['mmc']

        duration = None
        formats = []
        for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
            mmc = self._download_json(
                m_url, video_id, 'Downloading mmc JSON')
            if not duration:
                duration = int_or_none(mmc.get('duration'))
            for location in mmc['locations']:
                gat = self._proto_relative_url(location.get('gat'), 'http:')
                gcp = location.get('gcp')
                ogn = location.get('ogn')
                if None in (gat, gcp, ogn):
                    continue
                token_data = {
                    'gcp': gcp,
                    'ogn': ogn,
                    'sta': 0,
                }
                media = self._download_json(
                    gat, video_id, data=json.dumps(token_data).encode('utf-8'),
                    headers={
                        'Content-Type': 'application/json;charset=utf-8',
                        'Referer': url,
                    })
                stream = media.get('stream') or media.get('file')
                if not stream:
                    continue
                ext = determine_ext(stream)
                if ext == 'f4m':
                    formats.extend(self._extract_f4m_formats(
                        stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
                        video_id, f4m_id='hds', fatal=False))
                elif ext == 'm3u8':
                    formats.extend(self._extract_m3u8_formats(
                        stream, video_id, 'mp4', 'm3u8_native',
                        m3u8_id='hls', fatal=False))
        self._sort_formats(formats)

        return {
            'id': video_id,
            'formats': formats,
            'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
            'duration': duration,
        }


class MiTeleIE(InfoExtractor):
    IE_DESC = 'mitele.es'
    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'

    _TESTS = [{
        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
        'info_dict': {
            'id': '57b0dfb9c715da65618b4afa',
            'ext': 'mp4',
            'title': 'Tor, la web invisible',
            'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
            'series': 'Diario de',
            'season': 'La redacción',
            'season_number': 14,
            'season_id': 'diario_de_t14_11981',
            'episode': 'Programa 144',
            'episode_number': 3,
            'thumbnail': r're:(?i)^https?://.*\.jpg$',
            'duration': 2913,
        },
        'add_ie': ['Ooyala'],
    }, {
        # no explicit title
        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
        'info_dict': {
            'id': '57b0de3dc915da14058b4876',
            'ext': 'mp4',
            'title': 'Cuarto Milenio Temporada 6 Programa 226',
            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
            'series': 'Cuarto Milenio',
            'season': 'Temporada 6',
            'season_number': 6,
            'season_id': 'cuarto_milenio_t06_12715',
            'episode': 'Programa 226',
            'episode_number': 24,
            'thumbnail': r're:(?i)^https?://.*\.jpg$',
            'duration': 7313,
        },
        'params': {
            'skip_download': True,
        },
        'add_ie': ['Ooyala'],
    }, {
        'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
        'only_matching': True,
    }]

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

        gigya_url = self._search_regex(
            r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s+src="([^"]*)">[^>]*</script>',
            webpage, 'gigya', default=None)
        gigya_sc = self._download_webpage(
            compat_urlparse.urljoin('http://www.mitele.es/', gigya_url),
            video_id, 'Downloading gigya script')

        # Get a appKey/uuid for getting the session key
        appKey = self._search_regex(
            r'constant\s*\(\s*["\']_appGridApplicationKey["\']\s*,\s*["\']([0-9a-f]+)',
            gigya_sc, 'appKey')

        session_json = self._download_json(
            'https://appgrid-api.cloud.accedo.tv/session',
            video_id, 'Downloading session keys', query={
                'appKey': appKey,
                'uuid': compat_str(uuid.uuid4()),
            })

        paths = self._download_json(
            'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration',
            video_id, 'Downloading paths JSON',
            query={'sessionKey': compat_str(session_json['sessionKey'])})

        ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
        source = self._download_json(
            'http://%s%s%s/docs/%s' % (
                ooyala_s['base_url'], ooyala_s['full_path'],
                ooyala_s['provider_id'], video_id),
            video_id, 'Downloading data JSON', query={
                'include_titles': 'Series,Season',
                'product_name': 'test',
                'format': 'full',
            })['hits']['hits'][0]['_source']

        embedCode = source['offers'][0]['embed_codes'][0]
        titles = source['localizable_titles'][0]

        title = titles.get('title_medium') or titles['title_long']

        description = titles.get('summary_long') or titles.get('summary_medium')

        def get(key1, key2):
            value1 = source.get(key1)
            if not value1 or not isinstance(value1, list):
                return
            if not isinstance(value1[0], dict):
                return
            return value1[0].get(key2)

        series = get('localizable_titles_series', 'title_medium')

        season = get('localizable_titles_season', 'title_medium')
        season_number = int_or_none(source.get('season_number'))
        season_id = source.get('season_id')

        episode = titles.get('title_sort_name')
        episode_number = int_or_none(source.get('episode_number'))

        duration = parse_duration(get('videos', 'duration'))

        return {
            '_type': 'url_transparent',
            # for some reason only HLS is supported
            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
            'id': video_id,
            'title': title,
            'description': description,
            'series': series,
            'season': season,
            'season_number': season_number,
            'season_id': season_id,
            'episode': episode,
            'episode_number': episode_number,
            'duration': duration,
            'thumbnail': get('images', 'url'),
        }