2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_HTTPError
15 class EaglePlatformIE(InfoExtractor):
18 eagleplatform:(?P<custom_host>[^/]+):|
19 https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
24 # http://lenta.ru/news/2015/03/06/navalny/
25 'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
26 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
30 'title': 'Навальный вышел на свободу',
31 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
32 'thumbnail': 're:^https?://.*\.jpg$',
38 # http://muz-tv.ru/play/7129/
39 # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
40 'url': 'eagleplatform:media.clipyou.ru:12820',
41 'md5': '358597369cf8ba56675c1df15e7af624',
45 'title': "'O Sole Mio",
46 'thumbnail': 're:^https?://.*\.jpg$',
50 'skip': 'Georestricted',
54 def _handle_error(response):
55 status = int_or_none(response.get('status', 200))
57 raise ExtractorError(' '.join(response['errors']), expected=True)
59 def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
61 response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
62 except ExtractorError as ee:
63 if isinstance(ee.cause, compat_HTTPError):
64 response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
65 self._handle_error(response)
69 def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
70 return self._download_json(url_or_request, video_id, note)['data'][0]
72 def _real_extract(self, url):
73 mobj = re.match(self._VALID_URL, url)
74 host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
76 player_data = self._download_json(
77 'http://%s/api/player_data?id=%s' % (host, video_id), video_id)
79 media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
81 title = media['title']
82 description = media.get('description')
83 thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
84 duration = int_or_none(media.get('duration'))
85 view_count = int_or_none(media.get('views'))
87 age_restriction = media.get('age_restriction')
90 age_limit = 0 if age_restriction == 'allow_all' else 18
92 secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
96 m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
97 m3u8_formats = self._extract_m3u8_formats(
99 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
100 formats.extend(m3u8_formats)
102 mp4_url = self._get_video_url(
103 # Secure mp4 URL is constructed according to Player.prototype.mp4 from
104 # http://lentaru.media.eagleplatform.com/player/player.js
105 re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4', secure_m3u8),
106 video_id, 'Downloading mp4 JSON')
107 mp4_url_basename = url_basename(mp4_url)
108 for m3u8_format in m3u8_formats:
109 mobj = re.search('/([^/]+)/index\.m3u8', m3u8_format['url'])
111 http_format = m3u8_format.copy()
112 video_url = mp4_url.replace(mp4_url_basename, mobj.group(1))
113 if not self._is_valid_url(video_url, video_id):
117 'format_id': m3u8_format['format_id'].replace('hls', 'http'),
120 formats.append(http_format)
122 self._sort_formats(formats)
127 'description': description,
128 'thumbnail': thumbnail,
129 'duration': duration,
130 'view_count': view_count,
131 'age_limit': age_limit,