From 129dfa5f459f065d8be6205acda3a024127a894f Mon Sep 17 00:00:00 2001 From: sqrtNOT <77981959+sqrtNOT@users.noreply.github.com> Date: Sun, 17 Jul 2022 10:34:33 +0000 Subject: [PATCH] [extractor/WSJArticle] Fix video id extraction (#4268) Closes #4249 Authored by: sqrtNOT --- yt_dlp/extractor/wsj.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/wsj.py b/yt_dlp/extractor/wsj.py index 8be3645e3..9eeed104f 100644 --- a/yt_dlp/extractor/wsj.py +++ b/yt_dlp/extractor/wsj.py @@ -116,5 +116,6 @@ def _real_extract(self, url): article_id = self._match_id(url) webpage = self._download_webpage(url, article_id) video_id = self._search_regex( - r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id') + r'(?:id=["\']video|video-|iframe\.html\?guid=|data-src=["\'])([a-fA-F0-9-]{36})', + webpage, 'video id') return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)