Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rutube.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import itertools
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_str,
  10     compat_parse_qs,
  11     compat_urllib_parse_urlparse,
  12 )
  13 from ..utils import (
  14     determine_ext,
  15     bool_or_none,
  16     int_or_none,
  17     try_get,
  18     unified_timestamp,
  19 )
  20
  21
  22 class RutubeBaseIE(InfoExtractor):
  23     def _extract_video(self, video, video_id=None, require_title=True):
  24         title = video['title'] if require_title else video.get('title')
  25
  26         age_limit = video.get('is_adult')
  27         if age_limit is not None:
  28             age_limit = 18 if age_limit is True else 0
  29
  30         uploader_id = try_get(video, lambda x: x['author']['id'])
  31         category = try_get(video, lambda x: x['category']['name'])
  32
  33         return {
  34             'id': video.get('id') or video_id,
  35             'title': title,
  36             'description': video.get('description'),
  37             'thumbnail': video.get('thumbnail_url'),
  38             'duration': int_or_none(video.get('duration')),
  39             'uploader': try_get(video, lambda x: x['author']['name']),
  40             'uploader_id': compat_str(uploader_id) if uploader_id else None,
  41             'timestamp': unified_timestamp(video.get('created_ts')),
  42             'category': [category] if category else None,
  43             'age_limit': age_limit,
  44             'view_count': int_or_none(video.get('hits')),
  45             'comment_count': int_or_none(video.get('comments_count')),
  46             'is_live': bool_or_none(video.get('is_livestream')),
  47         }
  48
  49
  50 class RutubeIE(RutubeBaseIE):
  51     IE_NAME = 'rutube'
  52     IE_DESC = 'Rutube videos'
  53     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  54
  55     _TESTS = [{
  56         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
  57         'md5': '79938ade01294ef7e27574890d0d3769',
  58         'info_dict': {
  59             'id': '3eac3b4561676c17df9132a9a1e62e3e',
  60             'ext': 'flv',
  61             'title': 'Раненный кенгуру забежал в аптеку',
  62             'description': 'http://www.ntdtv.ru ',
  63             'duration': 80,
  64             'uploader': 'NTDRussian',
  65             'uploader_id': '29790',
  66             'timestamp': 1381943602,
  67             'upload_date': '20131016',
  68             'age_limit': 0,
  69         },
  70     }, {
  71         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
  72         'only_matching': True,
  73     }, {
  74         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
  75         'only_matching': True,
  76     }, {
  77         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
  78         'only_matching': True,
  79     }, {
  80         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
  81         'only_matching': True,
  82     }]
  83
  84     @classmethod
  85     def suitable(cls, url):
  86         return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
  87
  88     @staticmethod
  89     def _extract_urls(webpage):
  90         return [mobj.group('url') for mobj in re.finditer(
  91             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
  92             webpage)]
  93
  94     def _real_extract(self, url):
  95         video_id = self._match_id(url)
  96
  97         video = self._download_json(
  98             'http://rutube.ru/api/video/%s/?format=json' % video_id,
  99             video_id, 'Downloading video JSON')
 100
 101         info = self._extract_video(video, video_id)
 102
 103         options = self._download_json(
 104             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
 105             video_id, 'Downloading options JSON')
 106
 107         formats = []
 108         for format_id, format_url in options['video_balancer'].items():
 109             ext = determine_ext(format_url)
 110             if ext == 'm3u8':
 111                 formats.extend(self._extract_m3u8_formats(
 112                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
 113             elif ext == 'f4m':
 114                 formats.extend(self._extract_f4m_formats(
 115                     format_url, video_id, f4m_id=format_id, fatal=False))
 116             else:
 117                 formats.append({
 118                     'url': format_url,
 119                     'format_id': format_id,
 120                 })
 121         self._sort_formats(formats)
 122
 123         info['formats'] = formats
 124         return info
 125
 126
 127 class RutubeEmbedIE(InfoExtractor):
 128     IE_NAME = 'rutube:embed'
 129     IE_DESC = 'Rutube embedded videos'
 130     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 131
 132     _TESTS = [{
 133         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 134         'info_dict': {
 135             'id': 'a10e53b86e8f349080f718582ce4c661',
 136             'ext': 'flv',
 137             'timestamp': 1387830582,
 138             'upload_date': '20131223',
 139             'uploader_id': '297833',
 140             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 141             'uploader': 'subziro89 ILya',
 142             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 143         },
 144         'params': {
 145             'skip_download': True,
 146         },
 147     }, {
 148         'url': 'http://rutube.ru/play/embed/8083783',
 149         'only_matching': True,
 150     }]
 151
 152     def _real_extract(self, url):
 153         embed_id = self._match_id(url)
 154         webpage = self._download_webpage(url, embed_id)
 155
 156         canonical_url = self._html_search_regex(
 157             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 158             'Canonical URL')
 159         return self.url_result(canonical_url, RutubeIE.ie_key())
 160
 161
 162 class RutubePlaylistBaseIE(RutubeBaseIE):
 163     def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
 164         return self._PAGE_TEMPLATE % (playlist_id, page_num)
 165
 166     def _entries(self, playlist_id, *args, **kwargs):
 167         next_page_url = None
 168         for pagenum in itertools.count(1):
 169             page = self._download_json(
 170                 next_page_url or self._next_page_url(
 171                     pagenum, playlist_id, *args, **kwargs),
 172                 playlist_id, 'Downloading page %s' % pagenum)
 173
 174             results = page.get('results')
 175             if not results or not isinstance(results, list):
 176                 break
 177
 178             for result in results:
 179                 video_url = result.get('video_url')
 180                 if not video_url or not isinstance(video_url, compat_str):
 181                     continue
 182                 entry = self._extract_video(result, require_title=False)
 183                 entry.update({
 184                     '_type': 'url',
 185                     'url': video_url,
 186                     'ie_key': RutubeIE.ie_key(),
 187                 })
 188                 yield entry
 189
 190             next_page_url = page.get('next')
 191             if not next_page_url or not page.get('has_next'):
 192                 break
 193
 194     def _extract_playlist(self, playlist_id, *args, **kwargs):
 195         return self.playlist_result(
 196             self._entries(playlist_id, *args, **kwargs),
 197             playlist_id, kwargs.get('playlist_name'))
 198
 199     def _real_extract(self, url):
 200         return self._extract_playlist(self._match_id(url))
 201
 202
 203 class RutubeChannelIE(RutubePlaylistBaseIE):
 204     IE_NAME = 'rutube:channel'
 205     IE_DESC = 'Rutube channels'
 206     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 207     _TESTS = [{
 208         'url': 'http://rutube.ru/tags/video/1800/',
 209         'info_dict': {
 210             'id': '1800',
 211         },
 212         'playlist_mincount': 68,
 213     }]
 214
 215     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 216
 217
 218 class RutubeMovieIE(RutubePlaylistBaseIE):
 219     IE_NAME = 'rutube:movie'
 220     IE_DESC = 'Rutube movies'
 221     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 222     _TESTS = []
 223
 224     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 225     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 226
 227     def _real_extract(self, url):
 228         movie_id = self._match_id(url)
 229         movie = self._download_json(
 230             self._MOVIE_TEMPLATE % movie_id, movie_id,
 231             'Downloading movie JSON')
 232         return self._extract_playlist(
 233             movie_id, playlist_name=movie.get('name'))
 234
 235
 236 class RutubePersonIE(RutubePlaylistBaseIE):
 237     IE_NAME = 'rutube:person'
 238     IE_DESC = 'Rutube person videos'
 239     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 240     _TESTS = [{
 241         'url': 'http://rutube.ru/video/person/313878/',
 242         'info_dict': {
 243             'id': '313878',
 244         },
 245         'playlist_mincount': 37,
 246     }]
 247
 248     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
 249
 250
 251 class RutubePlaylistIE(RutubePlaylistBaseIE):
 252     IE_NAME = 'rutube:playlist'
 253     IE_DESC = 'Rutube playlists'
 254     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
 255     _TESTS = [{
 256         'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
 257         'info_dict': {
 258             'id': '3097',
 259         },
 260         'playlist_count': 27,
 261     }, {
 262         'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
 263         'only_matching': True,
 264     }]
 265
 266     _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
 267
 268     @classmethod
 269     def suitable(cls, url):
 270         if not super(RutubePlaylistIE, cls).suitable(url):
 271             return False
 272         params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
 273         return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
 274
 275     def _next_page_url(self, page_num, playlist_id, item_kind):
 276         return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
 277
 278     def _real_extract(self, url):
 279         qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
 280         playlist_kind = qs['pl_type'][0]
 281         playlist_id = qs['pl_id'][0]
 282         return self._extract_playlist(playlist_id, item_kind=playlist_kind)