]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/rutube.py
Allow extractors to specify section_start/end for clips
[yt-dlp.git] / yt_dlp / extractor / rutube.py
CommitLineData
bfd14b1b 1import re
1547c8cc 2import itertools
bfd14b1b
JMF
3
4from .common import InfoExtractor
1cc79574 5from ..compat import (
bfd14b1b 6 compat_str,
1cc79574
PH
7)
8from ..utils import (
41371968 9 determine_ext,
c3dd44e0 10 bool_or_none,
debed8d7 11 int_or_none,
4dfbf869 12 parse_qs,
c3dd44e0
S
13 try_get,
14 unified_timestamp,
3052a30d 15 url_or_none,
bfd14b1b
JMF
16)
17
18
48b81374 19class RutubeBaseIE(InfoExtractor):
4c0e0dc9
S
20 def _download_api_info(self, video_id, query=None):
21 if not query:
22 query = {}
23 query['format'] = 'json'
24 return self._download_json(
25 'http://rutube.ru/api/video/%s/' % video_id,
26 video_id, 'Downloading video JSON',
27 'Unable to download video JSON', query=query)
28
29 @staticmethod
30 def _extract_info(video, video_id=None, require_title=True):
48b81374
S
31 title = video['title'] if require_title else video.get('title')
32
33 age_limit = video.get('is_adult')
34 if age_limit is not None:
35 age_limit = 18 if age_limit is True else 0
36
37 uploader_id = try_get(video, lambda x: x['author']['id'])
38 category = try_get(video, lambda x: x['category']['name'])
39
40 return {
4c0e0dc9 41 'id': video.get('id') or video_id if video_id else video['id'],
48b81374
S
42 'title': title,
43 'description': video.get('description'),
44 'thumbnail': video.get('thumbnail_url'),
45 'duration': int_or_none(video.get('duration')),
46 'uploader': try_get(video, lambda x: x['author']['name']),
47 'uploader_id': compat_str(uploader_id) if uploader_id else None,
48 'timestamp': unified_timestamp(video.get('created_ts')),
49 'category': [category] if category else None,
50 'age_limit': age_limit,
51 'view_count': int_or_none(video.get('hits')),
52 'comment_count': int_or_none(video.get('comments_count')),
c3dd44e0 53 'is_live': bool_or_none(video.get('is_livestream')),
48b81374
S
54 }
55
4c0e0dc9
S
56 def _download_and_extract_info(self, video_id, query=None):
57 return self._extract_info(
58 self._download_api_info(video_id, query=query), video_id)
59
60 def _download_api_options(self, video_id, query=None):
61 if not query:
62 query = {}
63 query['format'] = 'json'
64 return self._download_json(
65 'http://rutube.ru/api/play/options/%s/' % video_id,
66 video_id, 'Downloading options JSON',
67 'Unable to download options JSON',
68 headers=self.geo_verification_headers(), query=query)
69
70 def _extract_formats(self, options, video_id):
71 formats = []
72 for format_id, format_url in options['video_balancer'].items():
73 ext = determine_ext(format_url)
74 if ext == 'm3u8':
75 formats.extend(self._extract_m3u8_formats(
76 format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
77 elif ext == 'f4m':
78 formats.extend(self._extract_f4m_formats(
79 format_url, video_id, f4m_id=format_id, fatal=False))
80 else:
81 formats.append({
82 'url': format_url,
83 'format_id': format_id,
84 })
85 self._sort_formats(formats)
86 return formats
87
88 def _download_and_extract_formats(self, video_id, query=None):
89 return self._extract_formats(
90 self._download_api_options(video_id, query=query), video_id)
91
48b81374
S
92
93class RutubeIE(RutubeBaseIE):
1547c8cc 94 IE_NAME = 'rutube'
37e3b90d 95 IE_DESC = 'Rutube videos'
bc82f228 96 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
bfd14b1b 97
2d3b7027 98 _TESTS = [{
1547c8cc 99 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
4c0e0dc9 100 'md5': '1d24f180fac7a02f3900712e5a5764d6',
1547c8cc 101 'info_dict': {
c72477bd 102 'id': '3eac3b4561676c17df9132a9a1e62e3e',
4c0e0dc9 103 'ext': 'mp4',
1547c8cc 104 'title': 'Раненный кенгуру забежал в аптеку',
00ff8f92 105 'description': 'http://www.ntdtv.ru ',
4c0e0dc9 106 'duration': 81,
1547c8cc 107 'uploader': 'NTDRussian',
108 'uploader_id': '29790',
48b81374 109 'timestamp': 1381943602,
00ff8f92 110 'upload_date': '20131016',
c8d1be77 111 'age_limit': 0,
bfd14b1b 112 },
2d3b7027
S
113 }, {
114 'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
115 'only_matching': True,
bc82f228
S
116 }, {
117 'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
118 'only_matching': True,
debed8d7 119 }, {
120 'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
121 'only_matching': True,
48b81374
S
122 }, {
123 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
124 'only_matching': True,
2d3b7027 125 }]
bfd14b1b 126
debed8d7 127 @classmethod
128 def suitable(cls, url):
48b81374 129 return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
debed8d7 130
eb3079b6
S
131 @staticmethod
132 def _extract_urls(webpage):
133 return [mobj.group('url') for mobj in re.finditer(
134 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
135 webpage)]
136
bfd14b1b 137 def _real_extract(self, url):
1cc79574 138 video_id = self._match_id(url)
4c0e0dc9
S
139 info = self._download_and_extract_info(video_id)
140 info['formats'] = self._download_and_extract_formats(video_id)
48b81374 141 return info
1547c8cc 142
143
4c0e0dc9 144class RutubeEmbedIE(RutubeBaseIE):
7a1818c9
PH
145 IE_NAME = 'rutube:embed'
146 IE_DESC = 'Rutube embedded videos'
25042f73 147 _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
7a1818c9 148
f52183a8 149 _TESTS = [{
7a1818c9
PH
150 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
151 'info_dict': {
152 'id': 'a10e53b86e8f349080f718582ce4c661',
4c0e0dc9 153 'ext': 'mp4',
48b81374 154 'timestamp': 1387830582,
7a1818c9
PH
155 'upload_date': '20131223',
156 'uploader_id': '297833',
157 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
158 'uploader': 'subziro89 ILya',
159 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
160 },
161 'params': {
48b81374 162 'skip_download': True,
7a1818c9 163 },
f52183a8
S
164 }, {
165 'url': 'http://rutube.ru/play/embed/8083783',
166 'only_matching': True,
4c0e0dc9
S
167 }, {
168 # private video
169 'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
170 'only_matching': True,
f52183a8 171 }]
7a1818c9
PH
172
173 def _real_extract(self, url):
174 embed_id = self._match_id(url)
4c0e0dc9
S
175 # Query may contain private videos token and should be passed to API
176 # requests (see #19163)
4dfbf869 177 query = parse_qs(url)
4c0e0dc9
S
178 options = self._download_api_options(embed_id, query)
179 video_id = options['effective_video']
180 formats = self._extract_formats(options, video_id)
181 info = self._download_and_extract_info(video_id, query)
182 info.update({
183 'extractor_key': 'Rutube',
184 'formats': formats,
185 })
186 return info
7a1818c9
PH
187
188
48b81374
S
189class RutubePlaylistBaseIE(RutubeBaseIE):
190 def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
191 return self._PAGE_TEMPLATE % (playlist_id, page_num)
192
193 def _entries(self, playlist_id, *args, **kwargs):
194 next_page_url = None
195 for pagenum in itertools.count(1):
196 page = self._download_json(
197 next_page_url or self._next_page_url(
198 pagenum, playlist_id, *args, **kwargs),
199 playlist_id, 'Downloading page %s' % pagenum)
200
201 results = page.get('results')
202 if not results or not isinstance(results, list):
203 break
204
205 for result in results:
3052a30d
S
206 video_url = url_or_none(result.get('video_url'))
207 if not video_url:
48b81374 208 continue
4c0e0dc9 209 entry = self._extract_info(result, require_title=False)
48b81374
S
210 entry.update({
211 '_type': 'url',
212 'url': video_url,
213 'ie_key': RutubeIE.ie_key(),
214 })
215 yield entry
216
217 next_page_url = page.get('next')
218 if not next_page_url or not page.get('has_next'):
219 break
220
221 def _extract_playlist(self, playlist_id, *args, **kwargs):
222 return self.playlist_result(
223 self._entries(playlist_id, *args, **kwargs),
224 playlist_id, kwargs.get('playlist_name'))
225
226 def _real_extract(self, url):
227 return self._extract_playlist(self._match_id(url))
228
229
13debc86
AG
230class RutubeTagsIE(RutubePlaylistBaseIE):
231 IE_NAME = 'rutube:tags'
232 IE_DESC = 'Rutube tags'
5886b38d 233 _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
22a6f150
PH
234 _TESTS = [{
235 'url': 'http://rutube.ru/tags/video/1800/',
236 'info_dict': {
237 'id': '1800',
238 },
239 'playlist_mincount': 68,
240 }]
1547c8cc 241
242 _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
243
1547c8cc 244
48b81374 245class RutubeMovieIE(RutubePlaylistBaseIE):
1547c8cc 246 IE_NAME = 'rutube:movie'
37e3b90d 247 IE_DESC = 'Rutube movies'
5886b38d 248 _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
22a6f150 249 _TESTS = []
1547c8cc 250
251 _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
252 _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
253
254 def _real_extract(self, url):
1cc79574 255 movie_id = self._match_id(url)
18c95c1a 256 movie = self._download_json(
37e3b90d
PH
257 self._MOVIE_TEMPLATE % movie_id, movie_id,
258 'Downloading movie JSON')
48b81374
S
259 return self._extract_playlist(
260 movie_id, playlist_name=movie.get('name'))
e3a9f32f 261
262
48b81374 263class RutubePersonIE(RutubePlaylistBaseIE):
e3a9f32f 264 IE_NAME = 'rutube:person'
265 IE_DESC = 'Rutube person videos'
5886b38d 266 _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
22a6f150
PH
267 _TESTS = [{
268 'url': 'http://rutube.ru/video/person/313878/',
269 'info_dict': {
270 'id': '313878',
271 },
272 'playlist_mincount': 37,
273 }]
e3a9f32f 274
37e3b90d 275 _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
debed8d7 276
277
48b81374 278class RutubePlaylistIE(RutubePlaylistBaseIE):
debed8d7 279 IE_NAME = 'rutube:playlist'
280 IE_DESC = 'Rutube playlists'
48b81374 281 _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
debed8d7 282 _TESTS = [{
48b81374 283 'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
debed8d7 284 'info_dict': {
48b81374 285 'id': '3097',
debed8d7 286 },
48b81374
S
287 'playlist_count': 27,
288 }, {
289 'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
290 'only_matching': True,
debed8d7 291 }]
292
48b81374 293 _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
debed8d7 294
f12a6e88
S
295 @classmethod
296 def suitable(cls, url):
3fb4e21b 297 from ..utils import int_or_none, parse_qs
298
f12a6e88
S
299 if not super(RutubePlaylistIE, cls).suitable(url):
300 return False
4dfbf869 301 params = parse_qs(url)
48b81374 302 return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
debed8d7 303
48b81374
S
304 def _next_page_url(self, page_num, playlist_id, item_kind):
305 return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
debed8d7 306
48b81374 307 def _real_extract(self, url):
4dfbf869 308 qs = parse_qs(url)
48b81374
S
309 playlist_kind = qs['pl_type'][0]
310 playlist_id = qs['pl_id'][0]
311 return self._extract_playlist(playlist_id, item_kind=playlist_kind)
13debc86
AG
312
313
314class RutubeChannelIE(RutubePlaylistBaseIE):
315 IE_NAME = 'rutube:channel'
316 IE_DESC = 'Rutube channel'
317 _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
318 _TESTS = [{
319 'url': 'https://rutube.ru/channel/639184/videos/',
320 'info_dict': {
321 'id': '639184',
322 },
323 'playlist_mincount': 133,
324 }]
325
326 _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'