]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/eagleplatform.py
[eagleplatform] extract mp4 url and fix thumbnail url
[yt-dlp.git] / youtube_dl / extractor / eagleplatform.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 int_or_none,
10 )
11
12
13 class EaglePlatformIE(InfoExtractor):
14 _VALID_URL = r'''(?x)
15 (?:
16 eagleplatform:(?P<custom_host>[^/]+):|
17 https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
18 )
19 (?P<id>\d+)
20 '''
21 _TESTS = [{
22 # http://lenta.ru/news/2015/03/06/navalny/
23 'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
24 'md5': '70f5187fb620f2c1d503b3b22fd4efe3',
25 'info_dict': {
26 'id': '227304',
27 'ext': 'mp4',
28 'title': 'Навальный вышел на свободу',
29 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
30 'thumbnail': 're:^https?://.*\.jpg$',
31 'duration': 87,
32 'view_count': int,
33 'age_limit': 0,
34 },
35 }, {
36 # http://muz-tv.ru/play/7129/
37 # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
38 'url': 'eagleplatform:media.clipyou.ru:12820',
39 'md5': '90b26344ba442c8e44aa4cf8f301164a',
40 'info_dict': {
41 'id': '12820',
42 'ext': 'mp4',
43 'title': "'O Sole Mio",
44 'thumbnail': 're:^https?://.*\.jpg$',
45 'duration': 216,
46 'view_count': int,
47 },
48 'skip': 'Georestricted',
49 }]
50
51 def _handle_error(self, response):
52 status = int_or_none(response.get('status', 200))
53 if status != 200:
54 raise ExtractorError(' '.join(response['errors']), expected=True)
55
56 def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
57 response = self._download_json(url_or_request, video_id, note)
58 self._handle_error(response)
59 return response['data'][0]
60
61 def _real_extract(self, url):
62 mobj = re.match(self._VALID_URL, url)
63 host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
64
65 player_data = self._download_json(
66 'http://%s/api/player_data?id=%s' % (host, video_id), video_id)
67
68 media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
69
70 title = media['title']
71 description = media.get('description')
72 thumbnail = self._proto_relative_url(media.get('snapshot'))
73 duration = int_or_none(media.get('duration'))
74 view_count = int_or_none(media.get('views'))
75
76 age_restriction = media.get('age_restriction')
77 age_limit = None
78 if age_restriction:
79 age_limit = 0 if age_restriction == 'allow_all' else 18
80
81 secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'])
82
83 m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
84 formats = self._extract_m3u8_formats(
85 m3u8_url, video_id,
86 'mp4', entry_protocol='m3u8_native')
87
88 mp4_url = self._get_video_url(
89 secure_m3u8.replace("m3u8", "mp4").replace("hlsvod", "mp4").replace("hls", "mp4"),
90 video_id, 'Downloading mp4 JSON')
91 formats.append({'url': mp4_url, 'format_id': 'mp4'})
92
93 self._sort_formats(formats)
94
95 return {
96 'id': video_id,
97 'title': title,
98 'description': description,
99 'thumbnail': thumbnail,
100 'duration': duration,
101 'view_count': view_count,
102 'age_limit': age_limit,
103 'formats': formats,
104 }