]>
Commit | Line | Data |
---|---|---|
70c5802b | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | from .common import InfoExtractor | |
5 | from ..compat import compat_str | |
6 | from ..utils import ( | |
7 | determine_ext, | |
8 | int_or_none, | |
9 | parse_iso8601, | |
10 | try_get, | |
11 | ) | |
12 | ||
13 | ||
14 | class RumbleEmbedIE(InfoExtractor): | |
15 | _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)' | |
16 | _TESTS = [{ | |
17 | 'url': 'https://rumble.com/embed/v5pv5f', | |
18 | 'md5': '36a18a049856720189f30977ccbb2c34', | |
19 | 'info_dict': { | |
20 | 'id': 'v5pv5f', | |
21 | 'ext': 'mp4', | |
22 | 'title': 'WMAR 2 News Latest Headlines | October 20, 6pm', | |
23 | 'timestamp': 1571611968, | |
24 | 'upload_date': '20191020', | |
25 | } | |
26 | }, { | |
27 | 'url': 'https://rumble.com/embed/ufe9n.v5pv5f', | |
28 | 'only_matching': True, | |
29 | }] | |
30 | ||
31 | def _real_extract(self, url): | |
32 | video_id = self._match_id(url) | |
33 | video = self._download_json( | |
34 | 'https://rumble.com/embedJS/', video_id, | |
35 | query={'request': 'video', 'v': video_id}) | |
36 | title = video['title'] | |
37 | ||
38 | formats = [] | |
39 | for height, ua in (video.get('ua') or {}).items(): | |
40 | for i in range(2): | |
41 | f_url = try_get(ua, lambda x: x[i], compat_str) | |
42 | if f_url: | |
43 | ext = determine_ext(f_url) | |
44 | f = { | |
45 | 'ext': ext, | |
46 | 'format_id': '%s-%sp' % (ext, height), | |
47 | 'height': int_or_none(height), | |
48 | 'url': f_url, | |
49 | } | |
50 | bitrate = try_get(ua, lambda x: x[i + 2]['bitrate']) | |
51 | if bitrate: | |
52 | f['tbr'] = int_or_none(bitrate) | |
53 | formats.append(f) | |
54 | self._sort_formats(formats) | |
55 | ||
56 | author = video.get('author') or {} | |
57 | ||
58 | return { | |
59 | 'id': video_id, | |
60 | 'title': title, | |
61 | 'formats': formats, | |
62 | 'thumbnail': video.get('i'), | |
63 | 'timestamp': parse_iso8601(video.get('pubDate')), | |
64 | 'channel': author.get('name'), | |
65 | 'channel_url': author.get('url'), | |
66 | 'duration': int_or_none(video.get('duration')), | |
67 | } |