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

   1 # encoding: 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     ExtractorError,
  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/(?P<id>[\da-z]{32})'
  21
  22     _TEST = {
  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
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43         video = self._download_json(
  44             'http://rutube.ru/api/video/%s/?format=json' % video_id,
  45             video_id, 'Downloading video JSON')
  46
  47         # Some videos don't have the author field
  48         author = video.get('author') or {}
  49
  50         options = self._download_json(
  51             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
  52             video_id, 'Downloading options JSON')
  53
  54         m3u8_url = options['video_balancer'].get('m3u8')
  55         if m3u8_url is None:
  56             raise ExtractorError('Couldn\'t find m3u8 manifest url')
  57         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
  58
  59         return {
  60             'id': video['id'],
  61             'title': video['title'],
  62             'description': video['description'],
  63             'duration': video['duration'],
  64             'view_count': video['hits'],
  65             'formats': formats,
  66             'thumbnail': video['thumbnail_url'],
  67             'uploader': author.get('name'),
  68             'uploader_id': compat_str(author['id']) if author else None,
  69             'upload_date': unified_strdate(video['created_ts']),
  70             'age_limit': 18 if video['is_adult'] else 0,
  71         }
  72
  73
  74 class RutubeEmbedIE(InfoExtractor):
  75     IE_NAME = 'rutube:embed'
  76     IE_DESC = 'Rutube embedded videos'
  77     _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)'
  78
  79     _TEST = {
  80         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
  81         'info_dict': {
  82             'id': 'a10e53b86e8f349080f718582ce4c661',
  83             'ext': 'mp4',
  84             'upload_date': '20131223',
  85             'uploader_id': '297833',
  86             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
  87             'uploader': 'subziro89 ILya',
  88             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
  89         },
  90         'params': {
  91             'skip_download': 'Requires ffmpeg',
  92         },
  93     }
  94
  95     def _real_extract(self, url):
  96         embed_id = self._match_id(url)
  97         webpage = self._download_webpage(url, embed_id)
  98
  99         canonical_url = self._html_search_regex(
 100             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 101             'Canonical URL')
 102         return self.url_result(canonical_url, 'Rutube')
 103
 104
 105 class RutubeChannelIE(InfoExtractor):
 106     IE_NAME = 'rutube:channel'
 107     IE_DESC = 'Rutube channels'
 108     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
 109     _TESTS = [{
 110         'url': 'http://rutube.ru/tags/video/1800/',
 111         'info_dict': {
 112             'id': '1800',
 113         },
 114         'playlist_mincount': 68,
 115     }]
 116
 117     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 118
 119     def _extract_videos(self, channel_id, channel_title=None):
 120         entries = []
 121         for pagenum in itertools.count(1):
 122             page = self._download_json(
 123                 self._PAGE_TEMPLATE % (channel_id, pagenum),
 124                 channel_id, 'Downloading page %s' % pagenum)
 125             results = page['results']
 126             if not results:
 127                 break
 128             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
 129             if not page['has_next']:
 130                 break
 131         return self.playlist_result(entries, channel_id, channel_title)
 132
 133     def _real_extract(self, url):
 134         mobj = re.match(self._VALID_URL, url)
 135         channel_id = mobj.group('id')
 136         return self._extract_videos(channel_id)
 137
 138
 139 class RutubeMovieIE(RutubeChannelIE):
 140     IE_NAME = 'rutube:movie'
 141     IE_DESC = 'Rutube movies'
 142     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 143     _TESTS = []
 144
 145     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 146     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 147
 148     def _real_extract(self, url):
 149         movie_id = self._match_id(url)
 150         movie = self._download_json(
 151             self._MOVIE_TEMPLATE % movie_id, movie_id,
 152             'Downloading movie JSON')
 153         movie_name = movie['name']
 154         return self._extract_videos(movie_id, movie_name)
 155
 156
 157 class RutubePersonIE(RutubeChannelIE):
 158     IE_NAME = 'rutube:person'
 159     IE_DESC = 'Rutube person videos'
 160     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 161     _TESTS = [{
 162         'url': 'http://rutube.ru/video/person/313878/',
 163         'info_dict': {
 164             'id': '313878',
 165         },
 166         'playlist_mincount': 37,
 167     }]
 168
 169     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'