2 from __future__ import unicode_literals
7 from .common import InfoExtractor
15 class IviIE(InfoExtractor):
18 _VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
23 'url': 'http://www.ivi.ru/watch/53141',
24 'md5': '6ff5be2254e796ed346251d117196cf4',
28 'title': 'Иван Васильевич меняет профессию',
29 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
31 'thumbnail': 're:^https?://.*\.jpg$',
33 'skip': 'Only works from Russia',
37 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
38 'md5': '221f56b35e3ed815fde2df71032f4b3e',
42 'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
43 'series': 'Двое из ларца',
46 'episode': 'Дело Гольдберга (1 часть)',
49 'thumbnail': 're:^https?://.*\.jpg$',
51 'skip': 'Only works from Russia',
54 # with MP4-HD720 format
55 'url': 'http://www.ivi.ru/watch/146500',
56 'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
61 'description': 'md5:ffca9372399976a2d260a407cc74cce6',
63 'thumbnail': 're:^https?://.*\.jpg$',
65 'skip': 'Only works from Russia',
71 'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
72 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
74 def _real_extract(self, url):
75 video_id = self._match_id(url)
78 'method': 'da.content.get',
82 'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
88 video_json = self._download_json(
89 'http://api.digitalaccess.ru/api/json/', video_id,
90 'Downloading video JSON', data=json.dumps(data))
92 if 'error' in video_json:
93 error = video_json['error']
94 if error['origin'] == 'NoRedisValidData':
95 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
97 'Unable to download video %s: %s' % (video_id, error['message']),
100 result = video_json['result']
102 quality = qualities(self._KNOWN_FORMATS)
106 'format_id': x.get('content_format'),
107 'quality': quality(x.get('content_format')),
108 } for x in result['files'] if x.get('url')]
110 self._sort_formats(formats)
112 title = result['title']
114 duration = int_or_none(result.get('duration'))
115 compilation = result.get('compilation')
116 episode = title if compilation else None
118 title = '%s - %s' % (compilation, title) if compilation is not None else title
121 'url': preview['url'],
122 'id': preview.get('content_format'),
123 } for preview in result.get('preview', []) if preview.get('url')]
125 webpage = self._download_webpage(url, video_id)
127 season = self._search_regex(
128 r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
129 webpage, 'season', default=None)
130 season_number = int_or_none(self._search_regex(
131 r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
132 webpage, 'season number', default=None))
134 episode_number = int_or_none(self._search_regex(
135 r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
136 webpage, 'episode number', default=None))
138 description = self._og_search_description(webpage, default=None) or self._html_search_meta(
139 'description', webpage, 'description', default=None)
144 'series': compilation,
146 'season_number': season_number,
148 'episode_number': episode_number,
149 'thumbnails': thumbnails,
150 'description': description,
151 'duration': duration,
156 class IviCompilationIE(InfoExtractor):
157 IE_DESC = 'ivi.ru compilations'
158 IE_NAME = 'ivi:compilation'
159 _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
161 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
163 'id': 'dvoe_iz_lartsa',
164 'title': 'Двое из ларца (2006 - 2008)',
166 'playlist_mincount': 24,
168 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
170 'id': 'dvoe_iz_lartsa/season1',
171 'title': 'Двое из ларца (2006 - 2008) 1 сезон',
173 'playlist_mincount': 12,
176 def _extract_entries(self, html, compilation_id):
179 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
180 for serie in re.findall(
181 r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
183 def _real_extract(self, url):
184 mobj = re.match(self._VALID_URL, url)
185 compilation_id = mobj.group('compilationid')
186 season_id = mobj.group('seasonid')
188 if season_id is not None: # Season link
189 season_page = self._download_webpage(
190 url, compilation_id, 'Downloading season %s web page' % season_id)
191 playlist_id = '%s/season%s' % (compilation_id, season_id)
192 playlist_title = self._html_search_meta('title', season_page, 'title')
193 entries = self._extract_entries(season_page, compilation_id)
194 else: # Compilation link
195 compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
196 playlist_id = compilation_id
197 playlist_title = self._html_search_meta('title', compilation_page, 'title')
198 seasons = re.findall(
199 r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
200 if not seasons: # No seasons in this compilation
201 entries = self._extract_entries(compilation_page, compilation_id)
204 for season_id in seasons:
205 season_page = self._download_webpage(
206 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
207 compilation_id, 'Downloading season %s web page' % season_id)
208 entries.extend(self._extract_entries(season_page, compilation_id))
210 return self.playlist_result(entries, playlist_id, playlist_title)