]>
Commit | Line | Data |
---|---|---|
cf143c4d | 1 | # coding: utf-8 |
ceb2b7d2 | 2 | from __future__ import unicode_literals |
77aa6b32 | 3 | |
4 | import re | |
5 | import json | |
6 | ||
7 | from .common import InfoExtractor | |
1cc79574 | 8 | from ..utils import ( |
77aa6b32 | 9 | ExtractorError, |
ab3176af | 10 | int_or_none, |
cf143c4d | 11 | qualities, |
77aa6b32 | 12 | ) |
13 | ||
14 | ||
15 | class IviIE(InfoExtractor): | |
ceb2b7d2 | 16 | IE_DESC = 'ivi.ru' |
17 | IE_NAME = 'ivi' | |
022218f2 | 18 | _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)' |
42dcdbe1 S |
19 | _GEO_BYPASS = False |
20 | _GEO_COUNTRIES = ['RU'] | |
656c2001 RA |
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/' | |
77aa6b32 | 23 | |
24 | _TESTS = [ | |
25 | # Single movie | |
26 | { | |
ceb2b7d2 | 27 | 'url': 'http://www.ivi.ru/watch/53141', |
ceb2b7d2 | 28 | 'md5': '6ff5be2254e796ed346251d117196cf4', |
29 | 'info_dict': { | |
84dd7031 S |
30 | 'id': '53141', |
31 | 'ext': 'mp4', | |
ceb2b7d2 | 32 | 'title': 'Иван Васильевич меняет профессию', |
33 | 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f', | |
34 | 'duration': 5498, | |
ec85ded8 | 35 | 'thumbnail': r're:^https?://.*\.jpg$', |
77aa6b32 | 36 | }, |
ceb2b7d2 | 37 | 'skip': 'Only works from Russia', |
77aa6b32 | 38 | }, |
dfb1b146 | 39 | # Serial's series |
77aa6b32 | 40 | { |
6ebb46c1 S |
41 | 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549', |
42 | 'md5': '221f56b35e3ed815fde2df71032f4b3e', | |
ceb2b7d2 | 43 | 'info_dict': { |
6ebb46c1 | 44 | 'id': '9549', |
84dd7031 | 45 | 'ext': 'mp4', |
ab3176af S |
46 | 'title': 'Двое из ларца - Дело Гольдберга (1 часть)', |
47 | 'series': 'Двое из ларца', | |
1463c5b9 S |
48 | 'season': 'Сезон 1', |
49 | 'season_number': 1, | |
ab3176af S |
50 | 'episode': 'Дело Гольдберга (1 часть)', |
51 | 'episode_number': 1, | |
6ebb46c1 | 52 | 'duration': 2655, |
ec85ded8 | 53 | 'thumbnail': r're:^https?://.*\.jpg$', |
77aa6b32 | 54 | }, |
ceb2b7d2 | 55 | 'skip': 'Only works from Russia', |
cf143c4d S |
56 | }, |
57 | { | |
58 | # with MP4-HD720 format | |
59 | 'url': 'http://www.ivi.ru/watch/146500', | |
60 | 'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e', | |
61 | 'info_dict': { | |
62 | 'id': '146500', | |
63 | 'ext': 'mp4', | |
64 | 'title': 'Кукла', | |
65 | 'description': 'md5:ffca9372399976a2d260a407cc74cce6', | |
66 | 'duration': 5599, | |
ec85ded8 | 67 | 'thumbnail': r're:^https?://.*\.jpg$', |
cf143c4d S |
68 | }, |
69 | 'skip': 'Only works from Russia', | |
022218f2 S |
70 | }, |
71 | { | |
72 | 'url': 'https://www.ivi.tv/watch/33560/', | |
73 | 'only_matching': True, | |
74 | }, | |
77aa6b32 | 75 | ] |
ceb2b7d2 | 76 | |
77aa6b32 | 77 | # Sorted by quality |
cf143c4d S |
78 | _KNOWN_FORMATS = ( |
79 | 'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', | |
80 | 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080') | |
77aa6b32 | 81 | |
82 | def _real_extract(self, url): | |
63be3b89 | 83 | video_id = self._match_id(url) |
77aa6b32 | 84 | |
656c2001 | 85 | data = json.dumps({ |
63be3b89 S |
86 | 'method': 'da.content.get', |
87 | 'params': [ | |
88 | video_id, { | |
1bba88ef | 89 | 'site': 's%d', |
63be3b89 S |
90 | 'referrer': 'http://www.ivi.ru/watch/%s' % video_id, |
91 | 'contentid': video_id | |
77aa6b32 | 92 | } |
63be3b89 | 93 | ] |
656c2001 | 94 | }).encode() |
77aa6b32 | 95 | |
76d9eca4 RA |
96 | for site in (353, 183): |
97 | content_data = data % site | |
98 | if site == 353: | |
99 | try: | |
100 | from Cryptodome.Cipher import Blowfish | |
101 | from Cryptodome.Hash import CMAC | |
102 | pycryptodomex_found = True | |
103 | except ImportError: | |
104 | pycryptodomex_found = False | |
105 | continue | |
106 | ||
107 | timestamp = (self._download_json( | |
108 | self._LIGHT_URL, video_id, | |
109 | 'Downloading timestamp JSON', data=json.dumps({ | |
110 | 'method': 'da.timestamp.get', | |
111 | 'params': [] | |
112 | }).encode(), fatal=False) or {}).get('result') | |
113 | if not timestamp: | |
114 | continue | |
115 | ||
116 | query = { | |
117 | 'ts': timestamp, | |
118 | 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(), | |
119 | } | |
120 | else: | |
121 | query = {} | |
1bba88ef | 122 | |
76d9eca4 | 123 | video_json = self._download_json( |
1bba88ef | 124 | self._LIGHT_URL, video_id, |
76d9eca4 RA |
125 | 'Downloading video JSON', data=content_data, query=query) |
126 | ||
127 | error = video_json.get('error') | |
128 | if error: | |
129 | origin = error.get('origin') | |
130 | message = error.get('message') or error.get('user_message') | |
131 | extractor_msg = 'Unable to download video %s' | |
132 | if origin == 'NotAllowedForLocation': | |
133 | self.raise_geo_restricted(message, self._GEO_COUNTRIES) | |
134 | elif origin == 'NoRedisValidData': | |
135 | extractor_msg = 'Video %s does not exist' | |
136 | elif site == 353: | |
137 | continue | |
138 | elif not pycryptodomex_found: | |
9e4e8646 RA |
139 | raise ExtractorError( |
140 | 'pycryptodome not found. Please install it.', | |
141 | expected=True) | |
76d9eca4 RA |
142 | elif message: |
143 | extractor_msg += ': ' + message | |
144 | raise ExtractorError(extractor_msg % video_id, expected=True) | |
145 | else: | |
146 | break | |
77aa6b32 | 147 | |
ceb2b7d2 | 148 | result = video_json['result'] |
656c2001 | 149 | title = result['title'] |
77aa6b32 | 150 | |
cf143c4d S |
151 | quality = qualities(self._KNOWN_FORMATS) |
152 | ||
656c2001 RA |
153 | formats = [] |
154 | for f in result.get('files', []): | |
155 | f_url = f.get('url') | |
156 | content_format = f.get('content_format') | |
157 | if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format: | |
158 | continue | |
159 | formats.append({ | |
160 | 'url': f_url, | |
161 | 'format_id': content_format, | |
162 | 'quality': quality(content_format), | |
163 | 'filesize': int_or_none(f.get('size_in_bytes')), | |
164 | }) | |
bf5b0a1b PH |
165 | self._sort_formats(formats) |
166 | ||
ab3176af S |
167 | compilation = result.get('compilation') |
168 | episode = title if compilation else None | |
169 | ||
5f6a1245 | 170 | title = '%s - %s' % (compilation, title) if compilation is not None else title |
77aa6b32 | 171 | |
ab3176af S |
172 | thumbnails = [{ |
173 | 'url': preview['url'], | |
174 | 'id': preview.get('content_format'), | |
175 | } for preview in result.get('preview', []) if preview.get('url')] | |
176 | ||
177 | webpage = self._download_webpage(url, video_id) | |
178 | ||
1463c5b9 S |
179 | season = self._search_regex( |
180 | r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)', | |
181 | webpage, 'season', default=None) | |
182 | season_number = int_or_none(self._search_regex( | |
183 | r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"', | |
184 | webpage, 'season number', default=None)) | |
185 | ||
ab3176af | 186 | episode_number = int_or_none(self._search_regex( |
3d897cc7 | 187 | r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)', |
ab3176af | 188 | webpage, 'episode number', default=None)) |
77aa6b32 | 189 | |
ab3176af S |
190 | description = self._og_search_description(webpage, default=None) or self._html_search_meta( |
191 | 'description', webpage, 'description', default=None) | |
77aa6b32 | 192 | |
193 | return { | |
194 | 'id': video_id, | |
195 | 'title': title, | |
ab3176af | 196 | 'series': compilation, |
1463c5b9 S |
197 | 'season': season, |
198 | 'season_number': season_number, | |
ab3176af S |
199 | 'episode': episode, |
200 | 'episode_number': episode_number, | |
201 | 'thumbnails': thumbnails, | |
77aa6b32 | 202 | 'description': description, |
656c2001 | 203 | 'duration': int_or_none(result.get('duration')), |
77aa6b32 | 204 | 'formats': formats, |
205 | } | |
206 | ||
207 | ||
208 | class IviCompilationIE(InfoExtractor): | |
ceb2b7d2 | 209 | IE_DESC = 'ivi.ru compilations' |
210 | IE_NAME = 'ivi:compilation' | |
84dd7031 | 211 | _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$' |
22a6f150 PH |
212 | _TESTS = [{ |
213 | 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa', | |
214 | 'info_dict': { | |
215 | 'id': 'dvoe_iz_lartsa', | |
216 | 'title': 'Двое из ларца (2006 - 2008)', | |
217 | }, | |
218 | 'playlist_mincount': 24, | |
219 | }, { | |
220 | 'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1', | |
221 | 'info_dict': { | |
222 | 'id': 'dvoe_iz_lartsa/season1', | |
223 | 'title': 'Двое из ларца (2006 - 2008) 1 сезон', | |
224 | }, | |
225 | 'playlist_mincount': 12, | |
226 | }] | |
77aa6b32 | 227 | |
228 | def _extract_entries(self, html, compilation_id): | |
c6270b2e S |
229 | return [ |
230 | self.url_result( | |
231 | 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key()) | |
232 | for serie in re.findall( | |
233 | r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)] | |
77aa6b32 | 234 | |
235 | def _real_extract(self, url): | |
236 | mobj = re.match(self._VALID_URL, url) | |
237 | compilation_id = mobj.group('compilationid') | |
238 | season_id = mobj.group('seasonid') | |
239 | ||
5f6a1245 | 240 | if season_id is not None: # Season link |
c6270b2e S |
241 | season_page = self._download_webpage( |
242 | url, compilation_id, 'Downloading season %s web page' % season_id) | |
77aa6b32 | 243 | playlist_id = '%s/season%s' % (compilation_id, season_id) |
ceb2b7d2 | 244 | playlist_title = self._html_search_meta('title', season_page, 'title') |
77aa6b32 | 245 | entries = self._extract_entries(season_page, compilation_id) |
5f6a1245 | 246 | else: # Compilation link |
ceb2b7d2 | 247 | compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') |
77aa6b32 | 248 | playlist_id = compilation_id |
ceb2b7d2 | 249 | playlist_title = self._html_search_meta('title', compilation_page, 'title') |
c6270b2e S |
250 | seasons = re.findall( |
251 | r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page) | |
252 | if not seasons: # No seasons in this compilation | |
77aa6b32 | 253 | entries = self._extract_entries(compilation_page, compilation_id) |
254 | else: | |
255 | entries = [] | |
256 | for season_id in seasons: | |
ceb2b7d2 | 257 | season_page = self._download_webpage( |
258 | 'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id), | |
259 | compilation_id, 'Downloading season %s web page' % season_id) | |
77aa6b32 | 260 | entries.extend(self._extract_entries(season_page, compilation_id)) |
261 | ||
5f6a1245 | 262 | return self.playlist_result(entries, playlist_id, playlist_title) |