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         },
  34         'params': {
  35             # It requires ffmpeg (m3u8 download)
  36             'skip_download': True,
  37         },
  38     }
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         video = self._download_json(
  43             'http://rutube.ru/api/video/%s/?format=json' % video_id,
  44             video_id, 'Downloading video JSON')
  45
  46         # Some videos don't have the author field
  47         author = video.get('author') or {}
  48
  49         options = self._download_json(
  50             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
  51             video_id, 'Downloading options JSON')
  52
  53         m3u8_url = options['video_balancer'].get('m3u8')
  54         if m3u8_url is None:
  55             raise ExtractorError('Couldn\'t find m3u8 manifest url')
  56         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
  57
  58         return {
  59             'id': video['id'],
  60             'title': video['title'],
  61             'description': video['description'],
  62             'duration': video['duration'],
  63             'view_count': video['hits'],
  64             'formats': formats,
  65             'thumbnail': video['thumbnail_url'],
  66             'uploader': author.get('name'),
  67             'uploader_id': compat_str(author['id']) if author else None,
  68             'upload_date': unified_strdate(video['created_ts']),
  69             'age_limit': 18 if video['is_adult'] else 0,
  70         }
  71
  72
  73 class RutubeChannelIE(InfoExtractor):
  74     IE_NAME = 'rutube:channel'
  75     IE_DESC = 'Rutube channels'
  76     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
  77     _TESTS = [{
  78         'url': 'http://rutube.ru/tags/video/1800/',
  79         'info_dict': {
  80             'id': '1800',
  81         },
  82         'playlist_mincount': 68,
  83     }]
  84
  85     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
  86
  87     def _extract_videos(self, channel_id, channel_title=None):
  88         entries = []
  89         for pagenum in itertools.count(1):
  90             page = self._download_json(
  91                 self._PAGE_TEMPLATE % (channel_id, pagenum),
  92                 channel_id, 'Downloading page %s' % pagenum)
  93             results = page['results']
  94             if not results:
  95                 break
  96             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
  97             if not page['has_next']:
  98                 break
  99         return self.playlist_result(entries, channel_id, channel_title)
 100
 101     def _real_extract(self, url):
 102         mobj = re.match(self._VALID_URL, url)
 103         channel_id = mobj.group('id')
 104         return self._extract_videos(channel_id)
 105
 106
 107 class RutubeMovieIE(RutubeChannelIE):
 108     IE_NAME = 'rutube:movie'
 109     IE_DESC = 'Rutube movies'
 110     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 111     _TESTS = []
 112
 113     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 114     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 115
 116     def _real_extract(self, url):
 117         movie_id = self._match_id(url)
 118         movie = self._download_json(
 119             self._MOVIE_TEMPLATE % movie_id, movie_id,
 120             'Downloading movie JSON')
 121         movie_name = movie['name']
 122         return self._extract_videos(movie_id, movie_name)
 123
 124
 125 class RutubePersonIE(RutubeChannelIE):
 126     IE_NAME = 'rutube:person'
 127     IE_DESC = 'Rutube person videos'
 128     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 129     _TESTS = [{
 130         'url': 'http://rutube.ru/video/person/313878/',
 131         'info_dict': {
 132             'id': '313878',
 133         },
 134         'playlist_mincount': 37,
 135     }]
 136
 137     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'