0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-16 01:25:06 +00:00

[utils] Fix find_element by class (#11402)

Fix d710a6ca7c

Authored by: bashonly
This commit is contained in:
bashonly 2024-10-29 23:24:17 +00:00 committed by GitHub
parent f101e5d34c
commit f93c16395c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -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): def find_element(*, tag=None, id=None, cls=None, attr=None, value=None, html=False):
# deliberately using `id=` and `cls=` for ease of readability # 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' assert tag or id or cls or (attr and value), 'One of tag, id, cls or (attr AND value) is required'
if not tag: ANY_TAG = r'[\w:.-]+'
tag = r'[\w:.-]+'
if attr and value: if attr and value:
assert not cls, 'Cannot match both attr and cls' assert not cls, 'Cannot match both attr and cls'
assert not id, 'Cannot match both attr and id' assert not id, 'Cannot match both attr and id'
func = get_element_html_by_attribute if html else get_element_by_attribute 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: elif cls:
assert not id, 'Cannot match both cls and id' 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: elif id:
func = get_element_html_by_id if html else get_element_by_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)) index = int(bool(html))
return lambda html: get_element_text_and_html_by_tag(tag, html)[index] return lambda html: get_element_text_and_html_by_tag(tag, html)[index]