From ad0b857f459a6d390fbf124183916218c52f223a Mon Sep 17 00:00:00 2001 From: tony-hn <25278435+tony-hn@users.noreply.github.com> Date: Thu, 26 Sep 2024 17:53:52 +0100 Subject: [PATCH] [ie/RumbleChannel] Fix extractor (#11049) Closes #10833 Authored by: tony-hn --- yt_dlp/extractor/rumble.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/rumble.py b/yt_dlp/extractor/rumble.py index db780a2cf..74c7e4f17 100644 --- a/yt_dlp/extractor/rumble.py +++ b/yt_dlp/extractor/rumble.py @@ -8,14 +8,17 @@ from ..utils import ( 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, ) @@ -382,8 +385,10 @@ class RumbleChannelIE(InfoExtractor): if isinstance(e.cause, HTTPError) and e.cause.status == 404: break raise - for video_url in re.findall(r'class="[^>"]*videostream__link[^>]+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()