]>
Commit | Line | Data |
---|---|---|
70c5802b | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
f1d42a83 | 4 | import itertools |
62852977 | 5 | import re |
6 | ||
70c5802b | 7 | from .common import InfoExtractor |
f1d42a83 | 8 | from ..compat import compat_str, compat_HTTPError |
70c5802b | 9 | from ..utils import ( |
10 | determine_ext, | |
11 | int_or_none, | |
12 | parse_iso8601, | |
13 | try_get, | |
f1d42a83 | 14 | ExtractorError, |
70c5802b | 15 | ) |
16 | ||
17 | ||
18 | class RumbleEmbedIE(InfoExtractor): | |
19 | _VALID_URL = r'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)' | |
20 | _TESTS = [{ | |
21 | 'url': 'https://rumble.com/embed/v5pv5f', | |
22 | 'md5': '36a18a049856720189f30977ccbb2c34', | |
23 | 'info_dict': { | |
24 | 'id': 'v5pv5f', | |
25 | 'ext': 'mp4', | |
26 | 'title': 'WMAR 2 News Latest Headlines | October 20, 6pm', | |
27 | 'timestamp': 1571611968, | |
28 | 'upload_date': '20191020', | |
29 | } | |
30 | }, { | |
31 | 'url': 'https://rumble.com/embed/ufe9n.v5pv5f', | |
32 | 'only_matching': True, | |
33 | }] | |
34 | ||
62852977 | 35 | @staticmethod |
36 | def _extract_urls(webpage): | |
37 | return [ | |
38 | mobj.group('url') | |
39 | for mobj in re.finditer( | |
40 | r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL, | |
41 | webpage)] | |
42 | ||
70c5802b | 43 | def _real_extract(self, url): |
44 | video_id = self._match_id(url) | |
45 | video = self._download_json( | |
46 | 'https://rumble.com/embedJS/', video_id, | |
47 | query={'request': 'video', 'v': video_id}) | |
48 | title = video['title'] | |
49 | ||
50 | formats = [] | |
51 | for height, ua in (video.get('ua') or {}).items(): | |
52 | for i in range(2): | |
53 | f_url = try_get(ua, lambda x: x[i], compat_str) | |
54 | if f_url: | |
55 | ext = determine_ext(f_url) | |
56 | f = { | |
57 | 'ext': ext, | |
58 | 'format_id': '%s-%sp' % (ext, height), | |
59 | 'height': int_or_none(height), | |
60 | 'url': f_url, | |
61 | } | |
62 | bitrate = try_get(ua, lambda x: x[i + 2]['bitrate']) | |
63 | if bitrate: | |
64 | f['tbr'] = int_or_none(bitrate) | |
65 | formats.append(f) | |
66 | self._sort_formats(formats) | |
67 | ||
68 | author = video.get('author') or {} | |
69 | ||
70 | return { | |
71 | 'id': video_id, | |
72 | 'title': title, | |
73 | 'formats': formats, | |
74 | 'thumbnail': video.get('i'), | |
75 | 'timestamp': parse_iso8601(video.get('pubDate')), | |
76 | 'channel': author.get('name'), | |
77 | 'channel_url': author.get('url'), | |
78 | 'duration': int_or_none(video.get('duration')), | |
79 | } | |
f1d42a83 AG |
80 | |
81 | ||
82 | class RumbleChannelIE(InfoExtractor): | |
83 | _VALID_URL = r'(?P<url>https?://(?:www\.)?rumble\.com/(?:c|user)/(?P<id>[^&?#$/]+))' | |
84 | ||
85 | _TESTS = [{ | |
86 | 'url': 'https://rumble.com/c/Styxhexenhammer666', | |
87 | 'playlist_mincount': 1160, | |
88 | 'info_dict': { | |
89 | 'id': 'Styxhexenhammer666', | |
90 | }, | |
91 | }, { | |
92 | 'url': 'https://rumble.com/user/goldenpoodleharleyeuna', | |
93 | 'playlist_count': 4, | |
94 | 'info_dict': { | |
95 | 'id': 'goldenpoodleharleyeuna', | |
96 | }, | |
97 | }] | |
98 | ||
99 | def entries(self, url, playlist_id): | |
100 | for page in itertools.count(1): | |
101 | try: | |
102 | webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page) | |
103 | except ExtractorError as e: | |
104 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: | |
105 | break | |
106 | raise | |
107 | for video_url in re.findall(r'class=video-item--a\s?href=([^>]+\.html)', webpage): | |
108 | yield self.url_result('https://rumble.com' + video_url) | |
109 | ||
110 | def _real_extract(self, url): | |
111 | url, playlist_id = self._match_valid_url(url).groups() | |
112 | return self.playlist_result(self.entries(url, playlist_id), playlist_id=playlist_id) |