import re
from .common import InfoExtractor
-from ..compat import compat_HTTPError
+from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
UnsupportedError,
clean_html,
determine_ext,
+ format_field,
get_element_by_class,
int_or_none,
+ join_nonempty,
parse_count,
parse_iso8601,
traverse_obj,
'upload_date': '20191020',
'channel_url': 'https://rumble.com/c/WMAR',
'channel': 'WMAR',
- 'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.OvCc-small-WMAR-2-News-Latest-Headline.jpg',
+ 'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.qR4e-small-WMAR-2-News-Latest-Headline.jpg',
'duration': 234,
'uploader': 'WMAR',
'live_status': 'not_live',
'info_dict': {
'id': 'v1essrt',
'ext': 'mp4',
- 'title': 'startswith:lofi hip hop radio - beats to relax/study',
+ 'title': 'startswith:lofi hip hop radio 📚 - beats to relax/study to',
'timestamp': 1661519399,
'upload_date': '20220826',
'channel_url': 'https://rumble.com/c/LofiGirl',
'channel': 'Lofi Girl',
'thumbnail': r're:https://.+\.jpg',
- 'duration': None,
'uploader': 'Lofi Girl',
'live_status': 'is_live',
},
'url': 'https://rumble.com/embed/v1amumr',
'info_dict': {
'id': 'v1amumr',
- 'ext': 'webm',
+ 'ext': 'mp4',
'fps': 60,
'title': 'Turning Point USA 2022 Student Action Summit DAY 1 - Rumble Exclusive Live',
'timestamp': 1658518457,
'duration': 92,
'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
'channel_url': 'https://rumble.com/c/RichSementa',
- 'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.OvCc-small-911-Audio-From-The-Man-Who-.jpg',
+ 'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.qR4e-small-911-Audio-From-The-Man-Who-.jpg',
'timestamp': 1654892716,
'uploader': 'Mr Producer Media',
'upload_date': '20220610',
if embeds:
return embeds
return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
- r'<script>\s*Rumble\(\s*"play"\s*,\s*{\s*[\'"]video[\'"]\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]
+ r'<script>[^<]*\bRumble\(\s*"play"\s*,\s*{[^}]*[\'"]?video[\'"]?\s*:\s*[\'"](?P<id>[0-9a-z]+)[\'"]', webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
formats = []
for ext, ext_info in (video.get('ua') or {}).items():
- for height, video_info in (ext_info or {}).items():
+ if isinstance(ext_info, dict):
+ for height, video_info in ext_info.items():
+ if not traverse_obj(video_info, ('meta', 'h', {int_or_none})):
+ video_info.setdefault('meta', {})['h'] = height
+ ext_info = ext_info.values()
+
+ for video_info in ext_info:
meta = video_info.get('meta') or {}
if not video_info.get('url'):
continue
'ext': ext,
'acodec': 'none' if timeline else None,
'url': video_info['url'],
- 'format_id': '%s-%sp' % (ext, height),
+ 'format_id': join_nonempty(ext, format_field(meta, 'h', '%sp')),
'format_note': 'Timeline' if timeline else None,
'fps': None if timeline else video.get('fps'),
**traverse_obj(meta, {
class RumbleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rumble\.com/(?P<id>v(?!ideos)[\w.-]+)[^/]*$'
- _EMBED_REGEX = [r'<a class=video-item--a href=(?P<url>/v[\w.-]+\.html)>']
+ _EMBED_REGEX = [
+ r'<a class=video-item--a href=(?P<url>/v[\w.-]+\.html)>',
+ r'<a[^>]+class="videostream__link link"[^>]+href=(?P<url>/v[\w.-]+\.html)[^>]*>']
_TESTS = [{
'add_ie': ['RumbleEmbed'],
'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
'thumbnail': r're:https://.+\.jpg',
'duration': 103,
'like_count': int,
+ 'dislike_count': int,
'view_count': int,
'live_status': 'not_live',
}
'channel_url': 'https://rumble.com/c/Redacted',
'live_status': 'not_live',
'thumbnail': 'https://sp.rmbl.ws/s8/1/d/x/2/O/dx2Oi.qR4e-small-The-U.S.-CANNOT-hide-this-i.jpg',
+ 'like_count': int,
+ 'dislike_count': int,
+ 'view_count': int,
+ },
+ }, {
+ 'url': 'https://rumble.com/v2e7fju-the-covid-twitter-files-drop-protecting-fauci-while-censoring-the-truth-wma.html',
+ 'info_dict': {
+ 'id': 'v2blzyy',
+ 'ext': 'mp4',
+ 'live_status': 'was_live',
+ 'release_timestamp': 1679446804,
+ 'description': 'md5:2ac4908ccfecfb921f8ffa4b30c1e636',
+ 'release_date': '20230322',
+ 'timestamp': 1679445692,
+ 'duration': 4435,
+ 'upload_date': '20230322',
+ 'title': 'The Covid Twitter Files Drop: Protecting Fauci While Censoring The Truth w/Matt Taibbi',
+ 'uploader': 'Kim Iversen',
+ 'channel_url': 'https://rumble.com/c/KimIversen',
+ 'channel': 'Kim Iversen',
+ 'thumbnail': 'https://sp.rmbl.ws/s8/1/6/b/w/O/6bwOi.qR4e-small-The-Covid-Twitter-Files-Dro.jpg',
+ 'like_count': int,
+ 'dislike_count': int,
+ 'view_count': int,
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://rumble.com/videos?page=2',
- 'playlist_count': 25,
+ 'playlist_mincount': 24,
'info_dict': {
'id': 'videos?page=2',
'title': 'All videos',
'age_limit': 0,
},
}, {
- 'url': 'https://rumble.com/live-videos',
- 'playlist_mincount': 19,
+ 'url': 'https://rumble.com/browse/live',
+ 'playlist_mincount': 25,
'info_dict': {
- 'id': 'live-videos',
- 'title': 'Live Videos',
- 'description': 'Live videos on Rumble.com',
+ 'id': 'live',
+ 'title': 'Browse',
'age_limit': 0,
},
}, {
'url': 'https://rumble.com/search/video?q=rumble&sort=views',
- 'playlist_count': 24,
+ 'playlist_mincount': 24,
'info_dict': {
'id': 'video?q=rumble&sort=views',
'title': 'Search results for: rumble',
if not url_info:
raise UnsupportedError(url)
- release_ts_str = self._search_regex(
- r'(?:Livestream begins|Streamed on):\s+<time datetime="([^"]+)',
- webpage, 'release date', fatal=False, default=None)
- view_count_str = self._search_regex(r'<span class="media-heading-info">([\d,]+) Views',
- webpage, 'view count', fatal=False, default=None)
-
- return self.url_result(
- url_info['url'], ie_key=url_info['ie_key'], url_transparent=True,
- view_count=parse_count(view_count_str),
- release_timestamp=parse_iso8601(release_ts_str),
- like_count=parse_count(get_element_by_class('rumbles-count', webpage)),
- description=clean_html(get_element_by_class('media-description', webpage)),
- )
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': url_info['ie_key'],
+ 'url': url_info['url'],
+ 'release_timestamp': parse_iso8601(self._search_regex(
+ r'(?:Livestream begins|Streamed on):\s+<time datetime="([^"]+)', webpage, 'release date', default=None)),
+ 'view_count': int_or_none(self._search_regex(
+ r'"userInteractionCount"\s*:\s*(\d+)', webpage, 'view count', default=None)),
+ 'like_count': parse_count(self._search_regex(
+ r'<span data-js="rumbles_up_votes">\s*([\d,.KM]+)', webpage, 'like count', default=None)),
+ 'dislike_count': parse_count(self._search_regex(
+ r'<span data-js="rumbles_down_votes">\s*([\d,.KM]+)', webpage, 'dislike count', default=None)),
+ 'description': clean_html(get_element_by_class('media-description', webpage))
+ }
class RumbleChannelIE(InfoExtractor):
try:
webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page)
except ExtractorError as e:
- if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+ if isinstance(e.cause, HTTPError) and e.cause.status == 404:
break
raise
- for video_url in re.findall(r'class=video-item--a\s?href=([^>]+\.html)', webpage):
+ for video_url in re.findall(r'class="[^>"]*videostream__link[^>]+href="([^"]+\.html)"', webpage):
yield self.url_result('https://rumble.com' + video_url)
def _real_extract(self, url):
projects / yt-dlp.git / blobdiff