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 )
  11 from ..utils import (
  12     determine_ext,
  13     unified_strdate,
  14 )
  15
  16
  17 class RutubeIE(InfoExtractor):
  18     IE_NAME = 'rutube'
  19     IE_DESC = 'Rutube videos'
  20     _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
  21
  22     _TESTS = [{
  23         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
  24         'info_dict': {
  25             'id': '3eac3b4561676c17df9132a9a1e62e3e',
  26             'ext': 'mp4',
  27             'title': 'Раненный кенгуру забежал в аптеку',
  28             'description': 'http://www.ntdtv.ru ',
  29             'duration': 80,
  30             'uploader': 'NTDRussian',
  31             'uploader_id': '29790',
  32             'upload_date': '20131016',
  33             'age_limit': 0,
  34         },
  35         'params': {
  36             # It requires ffmpeg (m3u8 download)
  37             'skip_download': True,
  38         },
  39     }, {
  40         'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
  44         'only_matching': True,
  45     }]
  46
  47     @staticmethod
  48     def _extract_urls(webpage):
  49         return [mobj.group('url') for mobj in re.finditer(
  50             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
  51             webpage)]
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55         video = self._download_json(
  56             'http://rutube.ru/api/video/%s/?format=json' % video_id,
  57             video_id, 'Downloading video JSON')
  58
  59         # Some videos don't have the author field
  60         author = video.get('author') or {}
  61
  62         options = self._download_json(
  63             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
  64             video_id, 'Downloading options JSON')
  65
  66         formats = []
  67         for format_id, format_url in options['video_balancer'].items():
  68             ext = determine_ext(format_url)
  69             if ext == 'm3u8':
  70                 formats.extend(self._extract_m3u8_formats(
  71                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
  72             elif ext == 'f4m':
  73                 formats.extend(self._extract_f4m_formats(
  74                     format_url, video_id, f4m_id=format_id, fatal=False))
  75             else:
  76                 formats.append({
  77                     'url': format_url,
  78                     'format_id': format_id,
  79                 })
  80         self._sort_formats(formats)
  81
  82         return {
  83             'id': video['id'],
  84             'title': video['title'],
  85             'description': video['description'],
  86             'duration': video['duration'],
  87             'view_count': video['hits'],
  88             'formats': formats,
  89             'thumbnail': video['thumbnail_url'],
  90             'uploader': author.get('name'),
  91             'uploader_id': compat_str(author['id']) if author else None,
  92             'upload_date': unified_strdate(video['created_ts']),
  93             'age_limit': 18 if video['is_adult'] else 0,
  94         }
  95
  96
  97 class RutubeEmbedIE(InfoExtractor):
  98     IE_NAME = 'rutube:embed'
  99     IE_DESC = 'Rutube embedded videos'
 100     _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
 101
 102     _TESTS = [{
 103         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
 104         'info_dict': {
 105             'id': 'a10e53b86e8f349080f718582ce4c661',
 106             'ext': 'mp4',
 107             'upload_date': '20131223',
 108             'uploader_id': '297833',
 109             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 110             'uploader': 'subziro89 ILya',
 111             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 112         },
 113         'params': {
 114             'skip_download': 'Requires ffmpeg',
 115         },
 116     }, {
 117         'url': 'http://rutube.ru/play/embed/8083783',
 118         'only_matching': True,
 119     }]
 120
 121     def _real_extract(self, url):
 122         embed_id = self._match_id(url)
 123         webpage = self._download_webpage(url, embed_id)
 124
 125         canonical_url = self._html_search_regex(
 126             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 127             'Canonical URL')
 128         return self.url_result(canonical_url, 'Rutube')
 129
 130
 131 class RutubeChannelIE(InfoExtractor):
 132     IE_NAME = 'rutube:channel'
 133     IE_DESC = 'Rutube channels'
 134     _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
 135     _TESTS = [{
 136         'url': 'http://rutube.ru/tags/video/1800/',
 137         'info_dict': {
 138             'id': '1800',
 139         },
 140         'playlist_mincount': 68,
 141     }]
 142
 143     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 144
 145     def _extract_videos(self, channel_id, channel_title=None):
 146         entries = []
 147         for pagenum in itertools.count(1):
 148             page = self._download_json(
 149                 self._PAGE_TEMPLATE % (channel_id, pagenum),
 150                 channel_id, 'Downloading page %s' % pagenum)
 151             results = page['results']
 152             if not results:
 153                 break
 154             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
 155             if not page['has_next']:
 156                 break
 157         return self.playlist_result(entries, channel_id, channel_title)
 158
 159     def _real_extract(self, url):
 160         mobj = re.match(self._VALID_URL, url)
 161         channel_id = mobj.group('id')
 162         return self._extract_videos(channel_id)
 163
 164
 165 class RutubeMovieIE(RutubeChannelIE):
 166     IE_NAME = 'rutube:movie'
 167     IE_DESC = 'Rutube movies'
 168     _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 169     _TESTS = []
 170
 171     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 172     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 173
 174     def _real_extract(self, url):
 175         movie_id = self._match_id(url)
 176         movie = self._download_json(
 177             self._MOVIE_TEMPLATE % movie_id, movie_id,
 178             'Downloading movie JSON')
 179         movie_name = movie['name']
 180         return self._extract_videos(movie_id, movie_name)
 181
 182
 183 class RutubePersonIE(RutubeChannelIE):
 184     IE_NAME = 'rutube:person'
 185     IE_DESC = 'Rutube person videos'
 186     _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
 187     _TESTS = [{
 188         'url': 'http://rutube.ru/video/person/313878/',
 189         'info_dict': {
 190             'id': '313878',
 191         },
 192         'playlist_mincount': 37,
 193     }]
 194
 195     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'