From 8cfeed78b1e646e8295e6de562195dd6a86e981e Mon Sep 17 00:00:00 2001 From: thatfuckingbird <67429906+thatfuckingbird@users.noreply.github.com> Date: Sat, 21 Jan 2023 22:32:42 +0100 Subject: [PATCH] [generic] fix regex for non-src image URLs --- gallery_dl/extractor/generic.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/gallery_dl/extractor/generic.py b/gallery_dl/extractor/generic.py index 10c72951..9292da3d 100644 --- a/gallery_dl/extractor/generic.py +++ b/gallery_dl/extractor/generic.py @@ -150,7 +150,7 @@ class GenericExtractor(Extractor): https://en.wikipedia.org/wiki/List_of_file_formats Compared to the "pattern" class variable, here we must exclude also - other special characters (space, ", ', >), since we are looking for + other special characters (space, ", ', <, >), since we are looking for urls in html tags. """ @@ -158,7 +158,7 @@ class GenericExtractor(Extractor): (?:[^?&#"'>\s]+) # anything until dot+extension \.(?:jpe?g|jpe|png|gif |web[mp]|mp4|mkv|og[gmv]|opus) # dot + image/video extensions - (?:[^"'>\s]*)? # optional query and fragment + (?:[^"'<>\s]*)? # optional query and fragment """ imageurls_src = re.findall(imageurl_pattern_src, page)