]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ivi.py
cb51cef2d45f9096a50a4716874219abaae63642
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+)'
20 _GEO_COUNTRIES
= ['RU']
25 'url': 'http://www.ivi.ru/watch/53141',
26 'md5': '6ff5be2254e796ed346251d117196cf4',
30 'title': 'Иван Васильевич меняет профессию',
31 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
33 'thumbnail': r
're:^https?://.*\.jpg$',
35 'skip': 'Only works from Russia',
39 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
40 'md5': '221f56b35e3ed815fde2df71032f4b3e',
44 'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
45 'series': 'Двое из ларца',
48 'episode': 'Дело Гольдберга (1 часть)',
51 'thumbnail': r
're:^https?://.*\.jpg$',
53 'skip': 'Only works from Russia',
56 # with MP4-HD720 format
57 'url': 'http://www.ivi.ru/watch/146500',
58 'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
63 'description': 'md5:ffca9372399976a2d260a407cc74cce6',
65 'thumbnail': r
're:^https?://.*\.jpg$',
67 'skip': 'Only works from Russia',
73 'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
74 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
76 def _real_extract(self
, url
):
77 video_id
= self
._match
_id
(url
)
80 'method': 'da.content.get',
84 'referrer': 'http://www.ivi.ru/watch/%s' % video_id
,
90 video_json
= self
._download
_json
(
91 'http://api.digitalaccess.ru/api/json/', video_id
,
92 'Downloading video JSON', data
=json
.dumps(data
))
94 if 'error' in video_json
:
95 error
= video_json
['error']
96 origin
= error
['origin']
97 if origin
== 'NotAllowedForLocation':
98 self
.raise_geo_restricted(
99 msg
=error
['message'], countries
=self
._GEO
_COUNTRIES
)
100 elif origin
== 'NoRedisValidData':
101 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
102 raise ExtractorError(
103 'Unable to download video %s: %s' % (video_id
, error
['message']),
106 result
= video_json
['result']
108 quality
= qualities(self
._KNOWN
_FORMATS
)
112 'format_id': x
.get('content_format'),
113 'quality': quality(x
.get('content_format')),
114 } for x
in result
['files'] if x
.get('url')]
116 self
._sort
_formats
(formats
)
118 title
= result
['title']
120 duration
= int_or_none(result
.get('duration'))
121 compilation
= result
.get('compilation')
122 episode
= title
if compilation
else None
124 title
= '%s - %s' % (compilation
, title
) if compilation
is not None else title
127 'url': preview
['url'],
128 'id': preview
.get('content_format'),
129 } for preview
in result
.get('preview', []) if preview
.get('url')]
131 webpage
= self
._download
_webpage
(url
, video_id
)
133 season
= self
._search
_regex
(
134 r
'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
135 webpage
, 'season', default
=None)
136 season_number
= int_or_none(self
._search
_regex
(
137 r
'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
138 webpage
, 'season number', default
=None))
140 episode_number
= int_or_none(self
._search
_regex
(
141 r
'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
142 webpage
, 'episode number', default
=None))
144 description
= self
._og
_search
_description
(webpage
, default
=None) or self
._html
_search
_meta
(
145 'description', webpage
, 'description', default
=None)
150 'series': compilation
,
152 'season_number': season_number
,
154 'episode_number': episode_number
,
155 'thumbnails': thumbnails
,
156 'description': description
,
157 'duration': duration
,
162 class IviCompilationIE(InfoExtractor
):
163 IE_DESC
= 'ivi.ru compilations'
164 IE_NAME
= 'ivi:compilation'
165 _VALID_URL
= r
'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
167 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
169 'id': 'dvoe_iz_lartsa',
170 'title': 'Двое из ларца (2006 - 2008)',
172 'playlist_mincount': 24,
174 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
176 'id': 'dvoe_iz_lartsa/season1',
177 'title': 'Двое из ларца (2006 - 2008) 1 сезон',
179 'playlist_mincount': 12,
182 def _extract_entries(self
, html
, compilation_id
):
185 'http://www.ivi.ru/watch/%s/%s' % (compilation_id
, serie
), IviIE
.ie_key())
186 for serie
in re
.findall(
187 r
'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id
, html
)]
189 def _real_extract(self
, url
):
190 mobj
= re
.match(self
._VALID
_URL
, url
)
191 compilation_id
= mobj
.group('compilationid')
192 season_id
= mobj
.group('seasonid')
194 if season_id
is not None: # Season link
195 season_page
= self
._download
_webpage
(
196 url
, compilation_id
, 'Downloading season %s web page' % season_id
)
197 playlist_id
= '%s/season%s' % (compilation_id
, season_id
)
198 playlist_title
= self
._html
_search
_meta
('title', season_page
, 'title')
199 entries
= self
._extract
_entries
(season_page
, compilation_id
)
200 else: # Compilation link
201 compilation_page
= self
._download
_webpage
(url
, compilation_id
, 'Downloading compilation web page')
202 playlist_id
= compilation_id
203 playlist_title
= self
._html
_search
_meta
('title', compilation_page
, 'title')
204 seasons
= re
.findall(
205 r
'<a href="/watch/%s/season(\d+)' % compilation_id
, compilation_page
)
206 if not seasons
: # No seasons in this compilation
207 entries
= self
._extract
_entries
(compilation_page
, compilation_id
)
210 for season_id
in seasons
:
211 season_page
= self
._download
_webpage
(
212 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id
, season_id
),
213 compilation_id
, 'Downloading season %s web page' % season_id
)
214 entries
.extend(self
._extract
_entries
(season_page
, compilation_id
))
216 return self
.playlist_result(entries
, playlist_id
, playlist_title
)