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 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             'description': 'http://www.ntdtv.ru ',
  27             'duration': 80,
  28             'uploader': 'NTDRussian',
  29             'uploader_id': '29790',
  30             'upload_date': '20131016',
  31         },
  32         'params': {
  33             # It requires ffmpeg (m3u8 download)
  34             'skip_download': True,
  35         },
  36     }
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         video_id = mobj.group('id')
  41
  42         api_response = self._download_webpage('http://rutube.ru/api/video/%s/?format=json' % video_id,
  43                                               video_id, 'Downloading video JSON')
  44         video = json.loads(api_response)
  45
  46         api_response = self._download_webpage('http://rutube.ru/api/play/trackinfo/%s/?format=json' % video_id,
  47                                               video_id, 'Downloading trackinfo JSON')
  48         trackinfo = json.loads(api_response)
  49
  50         # Some videos don't have the author field
  51         author = trackinfo.get('author') or {}
  52         m3u8_url = trackinfo['video_balancer'].get('m3u8')
  53         if m3u8_url is None:
  54             raise ExtractorError('Couldn\'t find m3u8 manifest url')
  55
  56         return {
  57             'id': video['id'],
  58             'title': video['title'],
  59             'description': video['description'],
  60             'duration': video['duration'],
  61             'view_count': video['hits'],
  62             'url': m3u8_url,
  63             'ext': 'mp4',
  64             'thumbnail': video['thumbnail_url'],
  65             'uploader': author.get('name'),
  66             'uploader_id': compat_str(author['id']) if author else None,
  67             'upload_date': unified_strdate(video['created_ts']),
  68             'age_limit': 18 if video['is_adult'] else 0,
  69         }
  70
  71
  72 class RutubeChannelIE(InfoExtractor):
  73     IE_NAME = 'rutube:channel'
  74     IE_DESC = 'Rutube channels'
  75     _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
  76
  77     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
  78
  79     def _extract_videos(self, channel_id, channel_title=None):
  80         entries = []
  81         for pagenum in itertools.count(1):
  82             api_response = self._download_webpage(
  83                 self._PAGE_TEMPLATE % (channel_id, pagenum),
  84                 channel_id, 'Downloading page %s' % pagenum)
  85             page = json.loads(api_response)
  86             results = page['results']
  87             if not results:
  88                 break
  89             entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
  90             if not page['has_next']:
  91                 break
  92         return self.playlist_result(entries, channel_id, channel_title)
  93
  94     def _real_extract(self, url):
  95         mobj = re.match(self._VALID_URL, url)
  96         channel_id = mobj.group('id')
  97         return self._extract_videos(channel_id)
  98
  99
 100 class RutubeMovieIE(RutubeChannelIE):
 101     IE_NAME = 'rutube:movie'
 102     IE_DESC = 'Rutube movies'
 103     _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
 104
 105     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
 106     _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
 107
 108     def _real_extract(self, url):
 109         mobj = re.match(self._VALID_URL, url)
 110         movie_id = mobj.group('id')
 111         api_response = self._download_webpage(
 112             self._MOVIE_TEMPLATE % movie_id, movie_id,
 113             'Downloading movie JSON')
 114         movie = json.loads(api_response)
 115         movie_name = movie['name']
 116         return self._extract_videos(movie_id, movie_name)
 117
 118
 119 class RutubePersonIE(RutubeChannelIE):
 120     IE_NAME = 'rutube:person'
 121     IE_DESC = 'Rutube person videos'
 122     _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
 123
 124     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'