diff options
| author |   Unit 193 <unit193@unit193.net> | 2023-01-30 04:40:57 -0500 |
|---|---|---|
| committer | Unit 193 <unit193@unit193.net> | 2023-01-30 04:40:57 -0500 |
| commit | 919f8ba16a7b82ba1099bd25b2c61c7881a05aa2 (patch) | |
| tree | 50eb34c3286538164a2f2b7048d110dc89b2a971 /gallery_dl/extractor/generic.py | |
| parent | f1051085013c0d702ef974b9b27ea43b3fc73259 (diff) | |
New upstream version 1.24.5.upstream/1.24.5
Diffstat (limited to 'gallery_dl/extractor/generic.py')
| -rw-r--r-- | gallery_dl/extractor/generic.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/gallery_dl/extractor/generic.py b/gallery_dl/extractor/generic.py index 10c7295..9292da3 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) |