aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/ivi.py
blob: cb51cef2d45f9096a50a4716874219abaae63642 (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
210
211
212
213
214
215
216
# coding: utf-8
from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    qualities,
)


class IviIE(InfoExtractor):
    IE_DESC = 'ivi.ru'
    IE_NAME = 'ivi'
    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
    _GEO_BYPASS = False
    _GEO_COUNTRIES = ['RU']

    _TESTS = [
        # Single movie
        {
            'url': 'http://www.ivi.ru/watch/53141',
            'md5': '6ff5be2254e796ed346251d117196cf4',
            'info_dict': {
                'id': '53141',
                'ext': 'mp4',
                'title': 'Иван Васильевич меняет профессию',
                'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                'duration': 5498,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        },
        # Serial's series
        {
            'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
            'md5': '221f56b35e3ed815fde2df71032f4b3e',
            'info_dict': {
                'id': '9549',
                'ext': 'mp4',
                'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
                'series': 'Двое из ларца',
                'season': 'Сезон 1',
                'season_number': 1,
                'episode': 'Дело Гольдберга (1 часть)',
                'episode_number': 1,
                'duration': 2655,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        },
        {
            # with MP4-HD720 format
            'url': 'http://www.ivi.ru/watch/146500',
            'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
            'info_dict': {
                'id': '146500',
                'ext': 'mp4',
                'title': 'Кукла',
                'description': 'md5:ffca9372399976a2d260a407cc74cce6',
                'duration': 5599,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        }
    ]

    # Sorted by quality
    _KNOWN_FORMATS = (
        'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
        'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')

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

        data = {
            'method': 'da.content.get',
            'params': [
                video_id, {
                    'site': 's183',
                    'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
                    'contentid': video_id
                }
            ]
        }

        video_json = self._download_json(
            'http://api.digitalaccess.ru/api/json/', video_id,
            'Downloading video JSON', data=json.dumps(data))

        if 'error' in video_json:
            error = video_json['error']
            origin = error['origin']
            if origin == 'NotAllowedForLocation':
                self.raise_geo_restricted(
                    msg=error['message'], countries=self._GEO_COUNTRIES)
            elif origin == 'NoRedisValidData':
                raise ExtractorError('Video %s does not exist' % video_id, expected=True)
            raise ExtractorError(
                'Unable to download video %s: %s' % (video_id, error['message']),
                expected=True)

        result = video_json['result']

        quality = qualities(self._KNOWN_FORMATS)

        formats = [{
            'url': x['url'],
            'format_id': x.get('content_format'),
            'quality': quality(x.get('content_format')),
        } for x in result['files'] if x.get('url')]

        self._sort_formats(formats)

        title = result['title']

        duration = int_or_none(result.get('duration'))
        compilation = result.get('compilation')
        episode = title if compilation else None

        title = '%s - %s' % (compilation, title) if compilation is not None else title

        thumbnails = [{
            'url': preview['url'],
            'id': preview.get('content_format'),
        } for preview in result.get('preview', []) if preview.get('url')]

        webpage = self._download_webpage(url, video_id)

        season = self._search_regex(
            r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
            webpage, 'season', default=None)
        season_number = int_or_none(self._search_regex(
            r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
            webpage, 'season number', default=None))

        episode_number = int_or_none(self._search_regex(
            r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
            webpage, 'episode number', default=None))

        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
            'description', webpage, 'description', default=None)

        return {
            'id': video_id,
            'title': title,
            'series': compilation,
            'season': season,
            'season_number': season_number,
            'episode': episode,
            'episode_number': episode_number,
            'thumbnails': thumbnails,
            'description': description,
            'duration': duration,
            'formats': formats,
        }


class IviCompilationIE(InfoExtractor):
    IE_DESC = 'ivi.ru compilations'
    IE_NAME = 'ivi:compilation'
    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
    _TESTS = [{
        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
        'info_dict': {
            'id': 'dvoe_iz_lartsa',
            'title': 'Двое из ларца (2006 - 2008)',
        },
        'playlist_mincount': 24,
    }, {
        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
        'info_dict': {
            'id': 'dvoe_iz_lartsa/season1',
            'title': 'Двое из ларца (2006 - 2008) 1 сезон',
        },
        'playlist_mincount': 12,
    }]

    def _extract_entries(self, html, compilation_id):
        return [
            self.url_result(
                'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
            for serie in re.findall(
                r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        compilation_id = mobj.group('compilationid')
        season_id = mobj.group('seasonid')

        if season_id is not None:  # Season link
            season_page = self._download_webpage(
                url, compilation_id, 'Downloading season %s web page' % season_id)
            playlist_id = '%s/season%s' % (compilation_id, season_id)
            playlist_title = self._html_search_meta('title', season_page, 'title')
            entries = self._extract_entries(season_page, compilation_id)
        else:  # Compilation link
            compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
            playlist_id = compilation_id
            playlist_title = self._html_search_meta('title', compilation_page, 'title')
            seasons = re.findall(
                r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
            if not seasons:  # No seasons in this compilation
                entries = self._extract_entries(compilation_page, compilation_id)
            else:
                entries = []
                for season_id in seasons:
                    season_page = self._download_webpage(
                        'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
                        compilation_id, 'Downloading season %s web page' % season_id)
                    entries.extend(self._extract_entries(season_page, compilation_id))

        return self.playlist_result(entries, playlist_id, playlist_title)