]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/ivi.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
15 class IviIE(InfoExtractor
):
18 _VALID_URL
= r
'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
20 _GEO_COUNTRIES
= ['RU']
21 _LIGHT_KEY
= b
'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'
22 _LIGHT_URL
= 'https://api.ivi.ru/light/'
27 'url': 'http://www.ivi.ru/watch/53141',
28 'md5': '6ff5be2254e796ed346251d117196cf4',
32 'title': 'Иван Васильевич меняет профессию',
33 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
35 'thumbnail': r
're:^https?://.*\.jpg$',
37 'skip': 'Only works from Russia',
41 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
42 'md5': '221f56b35e3ed815fde2df71032f4b3e',
46 'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
47 'series': 'Двое из ларца',
50 'episode': 'Дело Гольдберга (1 часть)',
53 'thumbnail': r
're:^https?://.*\.jpg$',
55 'skip': 'Only works from Russia',
58 # with MP4-HD720 format
59 'url': 'http://www.ivi.ru/watch/146500',
60 'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
65 'description': 'md5:ffca9372399976a2d260a407cc74cce6',
67 'thumbnail': r
're:^https?://.*\.jpg$',
69 'skip': 'Only works from Russia',
72 'url': 'https://www.ivi.tv/watch/33560/',
73 'only_matching': True,
79 'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
80 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
82 def _real_extract(self
, url
):
83 video_id
= self
._match
_id
(url
)
86 'method': 'da.content.get',
90 'referrer': 'http://www.ivi.ru/watch/%s' % video_id
,
97 from Crypto
.Cipher
import Blowfish
98 from Crypto
.Hash
import CMAC
100 timestamp
= self
._download
_json
(
101 self
._LIGHT
_URL
, video_id
,
102 'Downloading timestamp JSON', data
=json
.dumps({
103 'method': 'da.timestamp.get',
105 }).encode())['result']
110 'sign': CMAC
.new(self
._LIGHT
_KEY
, timestamp
.encode() + data
, Blowfish
).hexdigest(),
116 video_json
= self
._download
_json
(
117 self
._LIGHT
_URL
, video_id
,
118 'Downloading video JSON', data
=data
, query
=query
)
120 error
= video_json
.get('error')
122 origin
= error
['origin']
123 if origin
== 'NotAllowedForLocation':
124 self
.raise_geo_restricted(
125 msg
=error
['message'], countries
=self
._GEO
_COUNTRIES
)
126 elif origin
== 'NoRedisValidData':
127 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
128 elif origin
== 'NotAllowedError':
129 raise ExtractorError('pycryptodome not found. Please install it.', expected
=True)
130 raise ExtractorError(
131 'Unable to download video %s: %s' % (video_id
, error
['message']),
134 result
= video_json
['result']
135 title
= result
['title']
137 quality
= qualities(self
._KNOWN
_FORMATS
)
140 for f
in result
.get('files', []):
142 content_format
= f
.get('content_format')
143 if not f_url
or '-MDRM-' in content_format
or '-FPS-' in content_format
:
147 'format_id': content_format
,
148 'quality': quality(content_format
),
149 'filesize': int_or_none(f
.get('size_in_bytes')),
151 self
._sort
_formats
(formats
)
153 compilation
= result
.get('compilation')
154 episode
= title
if compilation
else None
156 title
= '%s - %s' % (compilation
, title
) if compilation
is not None else title
159 'url': preview
['url'],
160 'id': preview
.get('content_format'),
161 } for preview
in result
.get('preview', []) if preview
.get('url')]
163 webpage
= self
._download
_webpage
(url
, video_id
)
165 season
= self
._search
_regex
(
166 r
'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
167 webpage
, 'season', default
=None)
168 season_number
= int_or_none(self
._search
_regex
(
169 r
'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
170 webpage
, 'season number', default
=None))
172 episode_number
= int_or_none(self
._search
_regex
(
173 r
'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
174 webpage
, 'episode number', default
=None))
176 description
= self
._og
_search
_description
(webpage
, default
=None) or self
._html
_search
_meta
(
177 'description', webpage
, 'description', default
=None)
182 'series': compilation
,
184 'season_number': season_number
,
186 'episode_number': episode_number
,
187 'thumbnails': thumbnails
,
188 'description': description
,
189 'duration': int_or_none(result
.get('duration')),
194 class IviCompilationIE(InfoExtractor
):
195 IE_DESC
= 'ivi.ru compilations'
196 IE_NAME
= 'ivi:compilation'
197 _VALID_URL
= r
'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
199 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
201 'id': 'dvoe_iz_lartsa',
202 'title': 'Двое из ларца (2006 - 2008)',
204 'playlist_mincount': 24,
206 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
208 'id': 'dvoe_iz_lartsa/season1',
209 'title': 'Двое из ларца (2006 - 2008) 1 сезон',
211 'playlist_mincount': 12,
214 def _extract_entries(self
, html
, compilation_id
):
217 'http://www.ivi.ru/watch/%s/%s' % (compilation_id
, serie
), IviIE
.ie_key())
218 for serie
in re
.findall(
219 r
'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id
, html
)]
221 def _real_extract(self
, url
):
222 mobj
= re
.match(self
._VALID
_URL
, url
)
223 compilation_id
= mobj
.group('compilationid')
224 season_id
= mobj
.group('seasonid')
226 if season_id
is not None: # Season link
227 season_page
= self
._download
_webpage
(
228 url
, compilation_id
, 'Downloading season %s web page' % season_id
)
229 playlist_id
= '%s/season%s' % (compilation_id
, season_id
)
230 playlist_title
= self
._html
_search
_meta
('title', season_page
, 'title')
231 entries
= self
._extract
_entries
(season_page
, compilation_id
)
232 else: # Compilation link
233 compilation_page
= self
._download
_webpage
(url
, compilation_id
, 'Downloading compilation web page')
234 playlist_id
= compilation_id
235 playlist_title
= self
._html
_search
_meta
('title', compilation_page
, 'title')
236 seasons
= re
.findall(
237 r
'<a href="/watch/%s/season(\d+)' % compilation_id
, compilation_page
)
238 if not seasons
: # No seasons in this compilation
239 entries
= self
._extract
_entries
(compilation_page
, compilation_id
)
242 for season_id
in seasons
:
243 season_page
= self
._download
_webpage
(
244 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id
, season_id
),
245 compilation_id
, 'Downloading season %s web page' % season_id
)
246 entries
.extend(self
._extract
_entries
(season_page
, compilation_id
))
248 return self
.playlist_result(entries
, playlist_id
, playlist_title
)