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     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/(?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         formats = []
  55         for format_id, format_url in options['video_balancer'].items():
  56             ext = determine_ext(format_url)
  57             if ext == 'm3u8':
  58                 m3u8_formats = self._extract_m3u8_formats(
  59                     format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
  60                 if m3u8_formats:
  61                     formats.extend(m3u8_formats)
  62             elif ext == 'f4m':
  63                 f4m_formats = self._extract_f4m_formats(
  64                     format_url, video_id, f4m_id=format_id, fatal=False)
  65                 if f4m_formats:
  66                     formats.extend(f4m_formats)
  67             else:
  68                 formats.append({
  69                     'url': format_url,
  70                     'format_id': format_id,
  71                 })
  72         self._sort_formats(formats)
  73
  74         return {
  75             'id': video['id'],
  76             'title': video['title'],
  77             'description': video['description'],
  78             'duration': video['duration'],
  79             'view_count': video['hits'],
  80             'formats': formats,
  81             'thumbnail': video['thumbnail_url'],
  82             'uploader': author.get('name'),
  83             'uploader_id': compat_str(author['id']) if author else None,
  84             'upload_date': unified_strdate(video['created_ts']),
  85             'age_limit': 18 if video['is_adult'] else 0,
  86         }
  87
  88
  89 class RutubeEmbedIE(InfoExtractor):
  90     IE_NAME = 'rutube:embed'
  91     IE_DESC = 'Rutube embedded videos'
  92     _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
  93
  94     _TESTS = [{
  95         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
  96         'info_dict': {
  97             'id': 'a10e53b86e8f349080f718582ce4c661',
  98             'ext': 'mp4',
  99             'upload_date': '20131223',
 100             'uploader_id': '297833',
 101             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
 102             'uploader': 'subziro89 ILya',
 103             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
 104         },
 105         'params': {
 106             'skip_download': 'Requires ffmpeg',
 107         },
 108     }, {
 109         'url': 'http://rutube.ru/play/embed/8083783',
 110         'only_matching': True,
 111     }]
 112
 113     def _real_extract(self, url):
 114         embed_id = self._match_id(url)
 115         webpage = self._download_webpage(url, embed_id)
 116
 117         canonical_url = self._html_search_regex(
 118             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
 119             'Canonical URL')
 120         return self.url_result(canonical_url, 'Rutube')
 121
 122
 123 class RutubeChannelIE(InfoExtractor):
 124     IE_NAME = 'rutube:channel'
 125     IE_DESC = 'Rutube channels'
 126     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
 127     _TESTS = [{
 128         'url': 'http://rutube.ru/tags/video/1800/',
 129         'info_dict': {
 130             'id': '1800',
 131         },
 132         'playlist_mincount': 68,
 133     }]
 134
 135     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 136
 137     def _extract_videos(self, channel_id, channel_title=None):
 138         entries = []
 139         for pagenum in itertools.count(1):
 140             page = self._download_json(
 141                 self._PAGE_TEMPLATE % (channel_id, pagenum),
 142                 channel_id, 'Downloading page %s' % pagenum)
 143             results = page['results']
 144             if not results:
 145                 break
 146             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
 147             if not page['has_next']:
 148                 break
 149         return self.playlist_result(entries, channel_id, channel_title)
 150
 151     def _real_extract(self, url):
 152         mobj = re.match(self._VALID_URL, url)
 153         channel_id = mobj.group('id')
 154         return self._extract_videos(channel_id)
 155
 156
 157 class RutubeMovieIE(RutubeChannelIE):
 158     IE_NAME = 'rutube:movie'
 159     IE_DESC = 'Rutube movies'
 160     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 161     _TESTS = []
 162
 163     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 164     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 165
 166     def _real_extract(self, url):
 167         movie_id = self._match_id(url)
 168         movie = self._download_json(
 169             self._MOVIE_TEMPLATE % movie_id, movie_id,
 170             'Downloading movie JSON')
 171         movie_name = movie['name']
 172         return self._extract_videos(movie_id, movie_name)
 173
 174
 175 class RutubePersonIE(RutubeChannelIE):
 176     IE_NAME = 'rutube:person'
 177     IE_DESC = 'Rutube person videos'
 178     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 179     _TESTS = [{
 180         'url': 'http://rutube.ru/video/person/313878/',
 181         'info_dict': {
 182             'id': '313878',
 183         },
 184         'playlist_mincount': 37,
 185     }]
 186
 187     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'