]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/ivi.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
16 class IviIE(InfoExtractor
):
19 _VALID_URL
= r
'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<videoid>\d+)'
24 'url': 'http://www.ivi.ru/watch/53141',
25 'md5': '6ff5be2254e796ed346251d117196cf4',
29 'title': 'Иван Васильевич меняет профессию',
30 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
32 'thumbnail': 'http://thumbs.ivi.ru/f20.vcp.digitalaccess.ru/contents/d/1/c3c885163a082c29bceeb7b5a267a6.jpg',
34 'skip': 'Only works from Russia',
38 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
39 'md5': '221f56b35e3ed815fde2df71032f4b3e',
43 'title': 'Двое из ларца - Серия 1',
45 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg',
47 'skip': 'Only works from Russia',
52 _known_formats
= ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
55 _known_thumbnails
= ['Thumb-120x90', 'Thumb-160', 'Thumb-640x480']
57 def _extract_description(self
, html
):
58 m
= re
.search(r
'<meta name="description" content="(?P<description>[^"]+)"/>', html
)
59 return m
.group('description') if m
is not None else None
61 def _extract_comment_count(self
, html
):
62 m
= re
.search('(?s)<a href="#" id="view-comments" class="action-button dim gradient">\s*Комментарии:\s*(?P<commentcount>\d+)\s*</a>', html
)
63 return int(m
.group('commentcount')) if m
is not None else 0
65 def _real_extract(self
, url
):
66 mobj
= re
.match(self
._VALID
_URL
, url
)
67 video_id
= mobj
.group('videoid')
69 api_url
= 'http://api.digitalaccess.ru/api/json/'
71 data
= {'method': 'da.content.get',
72 'params': [video_id
, {'site': 's183',
73 'referrer': 'http://www.ivi.ru/watch/%s' % video_id
,
79 request
= compat_urllib_request
.Request(api_url
, json
.dumps(data
))
81 video_json_page
= self
._download
_webpage
(request
, video_id
, 'Downloading video JSON')
82 video_json
= json
.loads(video_json_page
)
84 if 'error' in video_json
:
85 error
= video_json
['error']
86 if error
['origin'] == 'NoRedisValidData':
87 raise ExtractorError('Video %s does not exist' % video_id
, expected
=True)
88 raise ExtractorError('Unable to download video %s: %s' % (video_id
, error
['message']), expected
=True)
90 result
= video_json
['result']
94 'format_id': x
['content_format'],
95 'preference': self
._known
_formats
.index(x
['content_format']),
96 } for x
in result
['files'] if x
['content_format'] in self
._known
_formats
]
98 self
._sort
_formats
(formats
)
101 raise ExtractorError('No media links available for %s' % video_id
)
103 duration
= result
['duration']
104 compilation
= result
['compilation']
105 title
= result
['title']
107 title
= '%s - %s' % (compilation
, title
) if compilation
is not None else title
109 previews
= result
['preview']
110 previews
.sort(key
=lambda fmt
: self
._known
_thumbnails
.index(fmt
['content_format']))
111 thumbnail
= previews
[-1]['url'] if len(previews
) > 0 else None
113 video_page
= self
._download
_webpage
(url
, video_id
, 'Downloading video page')
114 description
= self
._extract
_description
(video_page
)
115 comment_count
= self
._extract
_comment
_count
(video_page
)
120 'thumbnail': thumbnail
,
121 'description': description
,
122 'duration': duration
,
123 'comment_count': comment_count
,
128 class IviCompilationIE(InfoExtractor
):
129 IE_DESC
= 'ivi.ru compilations'
130 IE_NAME
= 'ivi:compilation'
131 _VALID_URL
= r
'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
133 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
135 'id': 'dvoe_iz_lartsa',
136 'title': 'Двое из ларца (2006 - 2008)',
138 'playlist_mincount': 24,
140 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
142 'id': 'dvoe_iz_lartsa/season1',
143 'title': 'Двое из ларца (2006 - 2008) 1 сезон',
145 'playlist_mincount': 12,
148 def _extract_entries(self
, html
, compilation_id
):
149 return [self
.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id
, serie
), 'Ivi')
150 for serie
in re
.findall(r
'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id
, html
)]
152 def _real_extract(self
, url
):
153 mobj
= re
.match(self
._VALID
_URL
, url
)
154 compilation_id
= mobj
.group('compilationid')
155 season_id
= mobj
.group('seasonid')
157 if season_id
is not None: # Season link
158 season_page
= self
._download
_webpage
(url
, compilation_id
, 'Downloading season %s web page' % season_id
)
159 playlist_id
= '%s/season%s' % (compilation_id
, season_id
)
160 playlist_title
= self
._html
_search
_meta
('title', season_page
, 'title')
161 entries
= self
._extract
_entries
(season_page
, compilation_id
)
162 else: # Compilation link
163 compilation_page
= self
._download
_webpage
(url
, compilation_id
, 'Downloading compilation web page')
164 playlist_id
= compilation_id
165 playlist_title
= self
._html
_search
_meta
('title', compilation_page
, 'title')
166 seasons
= re
.findall(r
'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id
, compilation_page
)
167 if len(seasons
) == 0: # No seasons in this compilation
168 entries
= self
._extract
_entries
(compilation_page
, compilation_id
)
171 for season_id
in seasons
:
172 season_page
= self
._download
_webpage
(
173 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id
, season_id
),
174 compilation_id
, 'Downloading season %s web page' % season_id
)
175 entries
.extend(self
._extract
_entries
(season_page
, compilation_id
))
177 return self
.playlist_result(entries
, playlist_id
, playlist_title
)