]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/rumble.py
2 from __future__
import unicode_literals
7 from .common
import InfoExtractor
8 from ..compat
import compat_str
, compat_HTTPError
19 class RumbleEmbedIE(InfoExtractor
):
20 _VALID_URL
= r
'https?://(?:www\.)?rumble\.com/embed/(?:[0-9a-z]+\.)?(?P<id>[0-9a-z]+)'
22 'url': 'https://rumble.com/embed/v5pv5f',
23 'md5': '36a18a049856720189f30977ccbb2c34',
27 'title': 'WMAR 2 News Latest Headlines | October 20, 6pm',
28 'timestamp': 1571611968,
29 'upload_date': '20191020',
32 'url': 'https://rumble.com/embed/vslb7v',
33 'md5': '7418035de1a30a178b8af34dc2b6a52b',
37 'title': 'Defense Sec. says US Commitment to NATO Defense \'Ironclad\'',
38 'timestamp': 1645142135,
39 'upload_date': '20220217',
40 'channel_url': 'https://rumble.com/c/CyberTechNews',
42 'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
46 'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
47 'only_matching': True,
51 def _extract_urls(webpage
):
54 for mobj
in re
.finditer(
55 r
'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl
["\']\s*:\s*)["\'](?P
<url
>%s)' % RumbleEmbedIE._VALID_URL,
58 def _real_extract(self, url):
59 video_id = self._match_id(url)
60 video = self._download_json(
61 'https
://rumble
.com
/embedJS
/', video_id,
62 query={'request': 'video', 'v': video_id})
63 title = unescapeHTML(video['title
'])
66 for height, ua in (video.get('ua
') or {}).items():
68 f_url = try_get(ua, lambda x: x[i], compat_str)
70 ext = determine_ext(f_url)
73 'format_id
': '%s-%sp
' % (ext, height),
74 'height
': int_or_none(height),
77 bitrate = try_get(ua, lambda x: x[i + 2]['bitrate
'])
79 f['tbr
'] = int_or_none(bitrate)
81 self._sort_formats(formats)
83 author = video.get('author
') or {}
89 'thumbnail
': video.get('i
'),
90 'timestamp
': parse_iso8601(video.get('pubDate
')),
91 'channel
': author.get('name
'),
92 'channel_url
': author.get('url
'),
93 'duration
': int_or_none(video.get('duration
')),
97 class RumbleChannelIE(InfoExtractor):
98 _VALID_URL = r'(?P
<url
>https?
://(?
:www\
.)?rumble\
.com
/(?
:c|user
)/(?P
<id>[^
&?
#$/]+))'
101 'url': 'https://rumble.com/c/Styxhexenhammer666',
102 'playlist_mincount': 1160,
104 'id': 'Styxhexenhammer666',
107 'url': 'https://rumble.com/user/goldenpoodleharleyeuna',
110 'id': 'goldenpoodleharleyeuna',
114 def entries(self
, url
, playlist_id
):
115 for page
in itertools
.count(1):
117 webpage
= self
._download
_webpage
(f
'{url}?page={page}', playlist_id
, note
='Downloading page %d' % page
)
118 except ExtractorError
as e
:
119 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 404:
122 for video_url
in re
.findall(r
'class=video-item--a\s?href=([^>]+\.html)', webpage
):
123 yield self
.url_result('https://rumble.com' + video_url
)
125 def _real_extract(self
, url
):
126 url
, playlist_id
= self
._match
_valid
_url
(url
).groups()
127 return self
.playlist_result(self
.entries(url
, playlist_id
), playlist_id
=playlist_id
)