itdominator/SolarFM
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Upgrade yt_dlp and download script

Browse Source
This commit is contained in:
itdominator
2025-05-02 16:11:08 -05:00
parent 3a2e8eeb08
commit d68d9ce4f9
1194 changed files with 60099 additions and 44436 deletions
Download Patch File Download Diff File Expand all files Collapse all files

152
plugins/youtube_download/yt_dlp/extractor/rumble.py
View File

@@ -7,15 +7,17 @@ from ..utils import (
ExtractorError,
UnsupportedError,
clean_html,
determine_ext,
extract_attributes,
format_field,
get_element_by_class,
get_elements_html_by_class,
int_or_none,
join_nonempty,
parse_count,
parse_iso8601,
traverse_obj,
unescapeHTML,
urljoin,
)
@@ -33,11 +35,11 @@ class RumbleEmbedIE(InfoExtractor):
'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': r're:https://.+\.jpg',
'duration': 234,
'uploader': 'WMAR',
'live_status': 'not_live',
}
},
}, {
'url': 'https://rumble.com/embed/vslb7v',
'md5': '7418035de1a30a178b8af34dc2b6a52b',
@@ -49,11 +51,11 @@ class RumbleEmbedIE(InfoExtractor):
'upload_date': '20220217',
'channel_url': 'https://rumble.com/c/CyberTechNews',
'channel': 'CTNews',
'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
'thumbnail': r're:https://.+\.jpg',
'duration': 901,
'uploader': 'CTNews',
'live_status': 'not_live',
}
},
}, {
'url': 'https://rumble.com/embed/vunh1h',
'info_dict': {
@@ -73,33 +75,32 @@ class RumbleEmbedIE(InfoExtractor):
{
'url': r're:https://.+\.vtt',
'name': 'English',
'ext': 'vtt'
}
]
'ext': 'vtt',
},
],
},
},
'params': {'skip_download': True}
'params': {'skip_download': True},
}, {
'url': 'https://rumble.com/embed/v1essrt',
'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',
},
'params': {'skip_download': True}
'params': {'skip_download': True},
}, {
'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,
@@ -111,7 +112,23 @@ class RumbleEmbedIE(InfoExtractor):
'uploader': 'Rumble Events',
'live_status': 'was_live',
},
'params': {'skip_download': True}
'params': {'skip_download': True},
}, {
'url': 'https://rumble.com/embed/v6pezdb',
'info_dict': {
'id': 'v6pezdb',
'ext': 'mp4',
'title': '"Es war einmal ein Mädchen" – Ein filmisches Zeitzeugnis aus Leningrad 1944',
'uploader': 'RT DE',
'channel': 'RT DE',
'channel_url': 'https://rumble.com/c/RTDE',
'duration': 309,
'thumbnail': 'https://1a-1791.com/video/fww1/dc/s8/1/n/z/2/y/nz2yy.qR4e-small-Es-war-einmal-ein-Mdchen-Ei.jpg',
'timestamp': 1743703500,
'upload_date': '20250403',
'live_status': 'not_live',
},
'params': {'skip_download': True},
}, {
'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
'only_matching': True,
@@ -129,12 +146,12 @@ class RumbleEmbedIE(InfoExtractor):
'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',
'live_status': 'not_live',
}
},
},
]
@@ -144,7 +161,7 @@ class RumbleEmbedIE(InfoExtractor):
if embeds:
return embeds
return [f'https://rumble.com/embed/{mobj.group("id")}' for mobj in re.finditer(
r'<script>[^<]*\bRumble\(\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)
@@ -166,40 +183,42 @@ class RumbleEmbedIE(InfoExtractor):
live_status = None
formats = []
for ext, ext_info in (video.get('ua') or {}).items():
if isinstance(ext_info, dict):
for height, video_info in ext_info.items():
for format_type, format_info in (video.get('ua') or {}).items():
if isinstance(format_info, dict):
for height, video_info in format_info.items():
if not traverse_obj(video_info, ('meta', 'h', {int_or_none})):
video_info.setdefault('meta', {})['h'] = height
ext_info = ext_info.values()
format_info = format_info.values()
for video_info in ext_info:
for video_info in format_info:
meta = video_info.get('meta') or {}
if not video_info.get('url'):
continue
if ext == 'hls':
# With default query params returns m3u8 variants which are duplicates, without returns tar files
if format_type == 'tar':
continue
if format_type == 'hls':
if meta.get('live') is True and video.get('live') == 1:
live_status = 'post_live'
formats.extend(self._extract_m3u8_formats(
video_info['url'], video_id,
ext='mp4', m3u8_id='hls', fatal=False, live=live_status == 'is_live'))
continue
timeline = ext == 'timeline'
if timeline:
ext = determine_ext(video_info['url'])
is_timeline = format_type == 'timeline'
is_audio = format_type == 'audio'
formats.append({
'ext': ext,
'acodec': 'none' if timeline else None,
'acodec': 'none' if is_timeline else None,
'vcodec': 'none' if is_audio else None,
'url': video_info['url'],
'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'),
'format_id': join_nonempty(format_type, format_field(meta, 'h', '%sp')),
'format_note': 'Timeline' if is_timeline else None,
'fps': None if is_timeline or is_audio else video.get('fps'),
**traverse_obj(meta, {
'tbr': 'bitrate',
'filesize': 'size',
'width': 'w',
'height': 'h',
}, expected_type=lambda x: int(x) or None)
'tbr': ('bitrate', {int_or_none}),
'filesize': ('size', {int_or_none}),
'width': ('w', {int_or_none}),
'height': ('h', {int_or_none}),
}),
})
subtitles = {
@@ -236,7 +255,9 @@ class RumbleEmbedIE(InfoExtractor):
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',
@@ -254,9 +275,10 @@ class RumbleIE(InfoExtractor):
'thumbnail': r're:https://.+\.jpg',
'duration': 103,
'like_count': int,
'dislike_count': int,
'view_count': int,
'live_status': 'not_live',
}
},
}, {
'url': 'http://www.rumble.com/vDMUM1?key=value',
'only_matching': True,
@@ -278,6 +300,9 @@ class RumbleIE(InfoExtractor):
'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',
@@ -296,12 +321,15 @@ class RumbleIE(InfoExtractor):
'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',
@@ -309,17 +337,16 @@ class RumbleIE(InfoExtractor):
'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',
@@ -334,19 +361,20 @@ class RumbleIE(InfoExtractor):
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):
@@ -369,13 +397,15 @@ class RumbleChannelIE(InfoExtractor):
def entries(self, url, playlist_id):
for page in itertools.count(1):
try:
webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note='Downloading page %d' % page)
webpage = self._download_webpage(f'{url}?page={page}', playlist_id, note=f'Downloading page {page}')
except ExtractorError as e:
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):
yield self.url_result('https://rumble.com' + video_url)
for video_url in traverse_obj(
get_elements_html_by_class('videostream__link', webpage), (..., {extract_attributes}, 'href'),
):
yield self.url_result(urljoin('https://rumble.com', video_url))
def _real_extract(self, url):
url, playlist_id = self._match_valid_url(url).groups()