]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rutube.py
debian/control: Update list of extractors.
[youtubedl] / youtube_dl / extractor / rutube.py
1 # encoding: utf-8
2 import re
3 import json
4
5 from .common import InfoExtractor
6 from ..utils import (
7 compat_urlparse,
8 compat_str,
9 ExtractorError,
10 )
11
12
13 class RutubeIE(InfoExtractor):
14 _VALID_URL = r'https?://rutube.ru/video/(?P<long_id>\w+)'
15
16 _TEST = {
17 u'url': u'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
18 u'file': u'3eac3b4561676c17df9132a9a1e62e3e.mp4',
19 u'info_dict': {
20 u'title': u'Раненный кенгуру забежал в аптеку',
21 u'uploader': u'NTDRussian',
22 u'uploader_id': u'29790',
23 },
24 u'params': {
25 # It requires ffmpeg (m3u8 download)
26 u'skip_download': True,
27 },
28 }
29
30 def _get_api_response(self, short_id, subpath):
31 api_url = 'http://rutube.ru/api/play/%s/%s/?format=json' % (subpath, short_id)
32 response_json = self._download_webpage(api_url, short_id,
33 u'Downloading %s json' % subpath)
34 return json.loads(response_json)
35
36 def _real_extract(self, url):
37 mobj = re.match(self._VALID_URL, url)
38 long_id = mobj.group('long_id')
39 webpage = self._download_webpage(url, long_id)
40 og_video = self._og_search_video_url(webpage)
41 short_id = compat_urlparse.urlparse(og_video).path[1:]
42 options = self._get_api_response(short_id, 'options')
43 trackinfo = self._get_api_response(short_id, 'trackinfo')
44 # Some videos don't have the author field
45 author = trackinfo.get('author') or {}
46 m3u8_url = trackinfo['video_balancer'].get('m3u8')
47 if m3u8_url is None:
48 raise ExtractorError(u'Couldn\'t find m3u8 manifest url')
49
50 return {
51 'id': trackinfo['id'],
52 'title': trackinfo['title'],
53 'url': m3u8_url,
54 'ext': 'mp4',
55 'thumbnail': options['thumbnail_url'],
56 'uploader': author.get('name'),
57 'uploader_id': compat_str(author['id']) if author else None,
58 }