youtube_dl/extractor/rutube.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6 import itertools
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     compat_str,
  11     unified_strdate,
  12     ExtractorError,
  13 )
  14
  15
  16 class RutubeIE(InfoExtractor):
  17     IE_NAME = 'rutube'
  18     IE_DESC = 'Rutube videos'
  19     _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
  20
  21     _TEST = {
  22         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
  23         'file': '3eac3b4561676c17df9132a9a1e62e3e.mp4',
  24         'info_dict': {
  25             'title': 'Раненный кенгуру забежал в аптеку',
  26             'uploader': 'NTDRussian',
  27             'uploader_id': '29790',
  28         },
  29         'params': {
  30             # It requires ffmpeg (m3u8 download)
  31             'skip_download': True,
  32         },
  33     }
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('id')
  38
  39         api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
  40                                               video_id, 'Downloading video JSON')
  41         video = json.loads(api_response)
  42
  43         api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
  44                                               video_id, 'Downloading trackinfo JSON')
  45         trackinfo = json.loads(api_response)
  46
  47         # Some videos don't have the author field
  48         author = trackinfo.get('author') or {}
  49         m3u8_url = trackinfo['video_balancer'].get('m3u8')
  50         if m3u8_url is None:
  51             raise ExtractorError('Couldn\'t find m3u8 manifest url')
  52
  53         return {
  54             'id': video['id'],
  55             'title': video['title'],
  56             'description': video['description'],
  57             'duration': video['duration'],
  58             'view_count': video['hits'],
  59             'url': m3u8_url,
  60             'ext': 'mp4',
  61             'thumbnail': video['thumbnail_url'],
  62             'uploader': author.get('name'),
  63             'uploader_id': compat_str(author['id']) if author else None,
  64             'upload_date': unified_strdate(video['created_ts']),
  65             'age_limit': 18 if video['is_adult'] else 0,
  66         }
  67
  68
  69 class RutubeChannelIE(InfoExtractor):
  70     IE_NAME = 'rutube:channel'
  71     IE_DESC = 'Rutube channels'
  72     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
  73
  74     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
  75
  76     def _extract_videos(self, channel_id, channel_title=None):
  77         entries = []
  78         for pagenum in itertools.count(1):
  79             api_response = self._download_webpage(
  80                 self._PAGE_TEMPLATE % (channel_id, pagenum),
  81                 channel_id, 'Downloading page %s' % pagenum)
  82             page = json.loads(api_response)
  83             results = page['results']
  84             if not results:
  85                 break
  86             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
  87             if not page['has_next']:
  88                 break
  89         return self.playlist_result(entries, channel_id, channel_title)
  90
  91     def _real_extract(self, url):
  92         mobj = re.match(self._VALID_URL, url)
  93         channel_id = mobj.group('id')
  94         return self._extract_videos(channel_id)
  95
  96
  97 class RutubeMovieIE(RutubeChannelIE):
  98     IE_NAME = 'rutube:movie'
  99     IE_DESC = 'Rutube movies'
 100     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 101
 102     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 103     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 104
 105     def _real_extract(self, url):
 106         mobj = re.match(self._VALID_URL, url)
 107         movie_id = mobj.group('id')
 108         api_response = self._download_webpage(
 109             self._MOVIE_TEMPLATE % movie_id, movie_id,
 110             'Downloading movie JSON')
 111         movie = json.loads(api_response)
 112         movie_name = movie['name']
 113         return self._extract_videos(movie_id, movie_name)
 114
 115
 116 class RutubePersonIE(RutubeChannelIE):
 117     IE_NAME = 'rutube:person'
 118     IE_DESC = 'Rutube person videos'
 119     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 120
 121     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'