From b440b35c2f32db9b06c3052702ab5023b06c0cb1 Mon Sep 17 00:00:00 2001 From: JustAnotherArchivist Date: Thu, 7 Oct 2021 16:05:46 +0000 Subject: [PATCH] Handle ancient /?v= URLs --- youtube-extract | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube-extract b/youtube-extract index e5c2656..887e527 100755 --- a/youtube-extract +++ b/youtube-extract @@ -44,7 +44,7 @@ noisePattern = '|'.join([ r'//www\.youtube\.com/results/?(\?|$)', r'//www\.youtube\.com/premium/?\?', r'//www\.youtube\.com/new([/?]|$)', - r'//www\.youtube\.com/?(\?|$)', + r'//www\.youtube\.com/?(\?(?!(\S*&)?v=)|$)', r'//www\.youtube\.com/embed/("|%22|' r"'|%27" r')(%20)?(\+|%3B)', # JS extraction stuff r'//www\.youtube\.com/service_ajax$', r'//www\.youtube\.com/watch(\?v=)?$',