]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/rutube.py
[extractor] Deprecate `_sort_formats`
[yt-dlp.git] / yt_dlp / extractor / rutube.py
CommitLineData
1547c8cc 1import itertools
bfd14b1b
JMF
2
3from .common import InfoExtractor
1cc79574 4from ..compat import (
bfd14b1b 5 compat_str,
1cc79574
PH
6)
7from ..utils import (
41371968 8 determine_ext,
c3dd44e0 9 bool_or_none,
debed8d7 10 int_or_none,
4dfbf869 11 parse_qs,
c3dd44e0
S
12 try_get,
13 unified_timestamp,
3052a30d 14 url_or_none,
bfd14b1b
JMF
15)
16
17
48b81374 18class RutubeBaseIE(InfoExtractor):
4c0e0dc9
S
19 def _download_api_info(self, video_id, query=None):
20 if not query:
21 query = {}
22 query['format'] = 'json'
23 return self._download_json(
24 'http://rutube.ru/api/video/%s/' % video_id,
25 video_id, 'Downloading video JSON',
26 'Unable to download video JSON', query=query)
27
28 @staticmethod
29 def _extract_info(video, video_id=None, require_title=True):
48b81374
S
30 title = video['title'] if require_title else video.get('title')
31
32 age_limit = video.get('is_adult')
33 if age_limit is not None:
34 age_limit = 18 if age_limit is True else 0
35
36 uploader_id = try_get(video, lambda x: x['author']['id'])
37 category = try_get(video, lambda x: x['category']['name'])
38
39 return {
4c0e0dc9 40 'id': video.get('id') or video_id if video_id else video['id'],
48b81374
S
41 'title': title,
42 'description': video.get('description'),
43 'thumbnail': video.get('thumbnail_url'),
44 'duration': int_or_none(video.get('duration')),
45 'uploader': try_get(video, lambda x: x['author']['name']),
46 'uploader_id': compat_str(uploader_id) if uploader_id else None,
47 'timestamp': unified_timestamp(video.get('created_ts')),
48 'category': [category] if category else None,
49 'age_limit': age_limit,
50 'view_count': int_or_none(video.get('hits')),
51 'comment_count': int_or_none(video.get('comments_count')),
c3dd44e0 52 'is_live': bool_or_none(video.get('is_livestream')),
48b81374
S
53 }
54
4c0e0dc9
S
55 def _download_and_extract_info(self, video_id, query=None):
56 return self._extract_info(
57 self._download_api_info(video_id, query=query), video_id)
58
59 def _download_api_options(self, video_id, query=None):
60 if not query:
61 query = {}
62 query['format'] = 'json'
63 return self._download_json(
64 'http://rutube.ru/api/play/options/%s/' % video_id,
65 video_id, 'Downloading options JSON',
66 'Unable to download options JSON',
67 headers=self.geo_verification_headers(), query=query)
68
69 def _extract_formats(self, options, video_id):
70 formats = []
71 for format_id, format_url in options['video_balancer'].items():
72 ext = determine_ext(format_url)
73 if ext == 'm3u8':
74 formats.extend(self._extract_m3u8_formats(
75 format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
76 elif ext == 'f4m':
77 formats.extend(self._extract_f4m_formats(
78 format_url, video_id, f4m_id=format_id, fatal=False))
79 else:
80 formats.append({
81 'url': format_url,
82 'format_id': format_id,
83 })
4c0e0dc9
S
84 return formats
85
86 def _download_and_extract_formats(self, video_id, query=None):
87 return self._extract_formats(
88 self._download_api_options(video_id, query=query), video_id)
89
48b81374
S
90
91class RutubeIE(RutubeBaseIE):
1547c8cc 92 IE_NAME = 'rutube'
37e3b90d 93 IE_DESC = 'Rutube videos'
bc82f228 94 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
d42763a4 95 _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
bfd14b1b 96
2d3b7027 97 _TESTS = [{
1547c8cc 98 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
4c0e0dc9 99 'md5': '1d24f180fac7a02f3900712e5a5764d6',
1547c8cc 100 'info_dict': {
c72477bd 101 'id': '3eac3b4561676c17df9132a9a1e62e3e',
4c0e0dc9 102 'ext': 'mp4',
1547c8cc 103 'title': 'Раненный кенгуру забежал в аптеку',
00ff8f92 104 'description': 'http://www.ntdtv.ru ',
4c0e0dc9 105 'duration': 81,
1547c8cc 106 'uploader': 'NTDRussian',
107 'uploader_id': '29790',
48b81374 108 'timestamp': 1381943602,
00ff8f92 109 'upload_date': '20131016',
c8d1be77 110 'age_limit': 0,
bfd14b1b 111 },
2d3b7027
S
112 }, {
113 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
114 'only_matching': True,
bc82f228
S
115 }, {
116 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
117 'only_matching': True,
debed8d7 118 }, {
119 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
120 'only_matching': True,
48b81374
S
121 }, {
122 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
123 'only_matching': True,
2d3b7027 124 }]
bfd14b1b 125
debed8d7 126 @classmethod
127 def suitable(cls, url):
48b81374 128 return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
debed8d7 129
bfd14b1b 130 def _real_extract(self, url):
1cc79574 131 video_id = self._match_id(url)
4c0e0dc9
S
132 info = self._download_and_extract_info(video_id)
133 info['formats'] = self._download_and_extract_formats(video_id)
48b81374 134 return info
1547c8cc 135
136
4c0e0dc9 137class RutubeEmbedIE(RutubeBaseIE):
7a1818c9
PH
138 IE_NAME = 'rutube:embed'
139 IE_DESC = 'Rutube embedded videos'
25042f73 140 _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
7a1818c9 141
f52183a8 142 _TESTS = [{
7a1818c9
PH
143 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
144 'info_dict': {
145 'id': 'a10e53b86e8f349080f718582ce4c661',
4c0e0dc9 146 'ext': 'mp4',
48b81374 147 'timestamp': 1387830582,
7a1818c9
PH
148 'upload_date': '20131223',
149 'uploader_id': '297833',
150 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
151 'uploader': 'subziro89 ILya',
152 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
153 },
154 'params': {
48b81374 155 'skip_download': True,
7a1818c9 156 },
f52183a8
S
157 }, {
158 'url': 'http://rutube.ru/play/embed/8083783',
159 'only_matching': True,
4c0e0dc9
S
160 }, {
161 # private video
162 'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
163 'only_matching': True,
f52183a8 164 }]
7a1818c9
PH
165
166 def _real_extract(self, url):
167 embed_id = self._match_id(url)
4c0e0dc9
S
168 # Query may contain private videos token and should be passed to API
169 # requests (see #19163)
4dfbf869 170 query = parse_qs(url)
4c0e0dc9
S
171 options = self._download_api_options(embed_id, query)
172 video_id = options['effective_video']
173 formats = self._extract_formats(options, video_id)
174 info = self._download_and_extract_info(video_id, query)
175 info.update({
176 'extractor_key': 'Rutube',
177 'formats': formats,
178 })
179 return info
7a1818c9
PH
180
181
48b81374
S
182class RutubePlaylistBaseIE(RutubeBaseIE):
183 def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
184 return self._PAGE_TEMPLATE % (playlist_id, page_num)
185
186 def _entries(self, playlist_id, *args, **kwargs):
187 next_page_url = None
188 for pagenum in itertools.count(1):
189 page = self._download_json(
190 next_page_url or self._next_page_url(
191 pagenum, playlist_id, *args, **kwargs),
192 playlist_id, 'Downloading page %s' % pagenum)
193
194 results = page.get('results')
195 if not results or not isinstance(results, list):
196 break
197
198 for result in results:
3052a30d
S
199 video_url = url_or_none(result.get('video_url'))
200 if not video_url:
48b81374 201 continue
4c0e0dc9 202 entry = self._extract_info(result, require_title=False)
48b81374
S
203 entry.update({
204 '_type': 'url',
205 'url': video_url,
206 'ie_key': RutubeIE.ie_key(),
207 })
208 yield entry
209
210 next_page_url = page.get('next')
211 if not next_page_url or not page.get('has_next'):
212 break
213
214 def _extract_playlist(self, playlist_id, *args, **kwargs):
215 return self.playlist_result(
216 self._entries(playlist_id, *args, **kwargs),
217 playlist_id, kwargs.get('playlist_name'))
218
219 def _real_extract(self, url):
220 return self._extract_playlist(self._match_id(url))
221
222
13debc86
AG
223class RutubeTagsIE(RutubePlaylistBaseIE):
224 IE_NAME = 'rutube:tags'
225 IE_DESC = 'Rutube tags'
5886b38d 226 _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
22a6f150
PH
227 _TESTS = [{
228 'url': 'http://rutube.ru/tags/video/1800/',
229 'info_dict': {
230 'id': '1800',
231 },
232 'playlist_mincount': 68,
233 }]
1547c8cc 234
235 _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
236
1547c8cc 237
48b81374 238class RutubeMovieIE(RutubePlaylistBaseIE):
1547c8cc 239 IE_NAME = 'rutube:movie'
37e3b90d 240 IE_DESC = 'Rutube movies'
5886b38d 241 _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
1547c8cc 242
243 _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
244 _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
245
246 def _real_extract(self, url):
1cc79574 247 movie_id = self._match_id(url)
18c95c1a 248 movie = self._download_json(
37e3b90d
PH
249 self._MOVIE_TEMPLATE % movie_id, movie_id,
250 'Downloading movie JSON')
48b81374
S
251 return self._extract_playlist(
252 movie_id, playlist_name=movie.get('name'))
e3a9f32f 253
254
48b81374 255class RutubePersonIE(RutubePlaylistBaseIE):
e3a9f32f 256 IE_NAME = 'rutube:person'
257 IE_DESC = 'Rutube person videos'
5886b38d 258 _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
22a6f150
PH
259 _TESTS = [{
260 'url': 'http://rutube.ru/video/person/313878/',
261 'info_dict': {
262 'id': '313878',
263 },
264 'playlist_mincount': 37,
265 }]
e3a9f32f 266
37e3b90d 267 _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
debed8d7 268
269
48b81374 270class RutubePlaylistIE(RutubePlaylistBaseIE):
debed8d7 271 IE_NAME = 'rutube:playlist'
272 IE_DESC = 'Rutube playlists'
48b81374 273 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
debed8d7 274 _TESTS = [{
48b81374 275 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
debed8d7 276 'info_dict': {
48b81374 277 'id': '3097',
debed8d7 278 },
48b81374
S
279 'playlist_count': 27,
280 }, {
281 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
282 'only_matching': True,
debed8d7 283 }]
284
48b81374 285 _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
debed8d7 286
f12a6e88
S
287 @classmethod
288 def suitable(cls, url):
3fb4e21b 289 from ..utils import int_or_none, parse_qs
290
f12a6e88
S
291 if not super(RutubePlaylistIE, cls).suitable(url):
292 return False
4dfbf869 293 params = parse_qs(url)
48b81374 294 return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
debed8d7 295
48b81374
S
296 def _next_page_url(self, page_num, playlist_id, item_kind):
297 return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
debed8d7 298
48b81374 299 def _real_extract(self, url):
4dfbf869 300 qs = parse_qs(url)
48b81374
S
301 playlist_kind = qs['pl_type'][0]
302 playlist_id = qs['pl_id'][0]
303 return self._extract_playlist(playlist_id, item_kind=playlist_kind)
13debc86
AG
304
305
306class RutubeChannelIE(RutubePlaylistBaseIE):
307 IE_NAME = 'rutube:channel'
308 IE_DESC = 'Rutube channel'
309 _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
310 _TESTS = [{
311 'url': 'https://rutube.ru/channel/639184/videos/',
312 'info_dict': {
313 'id': '639184',
314 },
315 'playlist_mincount': 133,
316 }]
317
318 _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'