diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index b7de04e638..8535d28307 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -5165,6 +5165,7 @@ class _UnsafeExtensionError(Exception): 'ico', 'image', 'jng', + 'jpe', 'jpeg', 'jxl', 'svg', diff --git a/yt_dlp/utils/traversal.py b/yt_dlp/utils/traversal.py index df3ff406f5..0eef817eaa 100644 --- a/yt_dlp/utils/traversal.py +++ b/yt_dlp/utils/traversal.py @@ -391,14 +391,13 @@ def find_element(*, tag: str, html=False): ... def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=False): # deliberately using `id=` and `cls=` for ease of readability assert tag or id or cls or (attr and value), 'One of tag, id, cls or (attr AND value) is required' - if not tag: - tag = r'[\w:.-]+' + ANY_TAG = r'[\w:.-]+' if attr and value: assert not cls, 'Cannot match both attr and cls' assert not id, 'Cannot match both attr and id' func = get_element_html_by_attribute if html else get_element_by_attribute - return functools.partial(func, attr, value, tag=tag) + return functools.partial(func, attr, value, tag=tag or ANY_TAG) elif cls: assert not id, 'Cannot match both cls and id' @@ -408,7 +407,7 @@ def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=Fal elif id: func = get_element_html_by_id if html else get_element_by_id - return functools.partial(func, id, tag=tag) + return functools.partial(func, id, tag=tag or ANY_TAG) index = int(bool(html)) return lambda html: get_element_text_and_html_by_tag(tag, html)[index]