Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-26 21:59:08 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

[core] utils: fix some cases

Browse source
This commit is contained in:
Allen 2024-12-05 00:43:15 +01:00
parent ec3a0927c4
commit c49aa772cc
No known key found for this signature in database
2 changed files with 11 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
test/test_utils.py
View file

@ -1846,7 +1846,7 @@ Line 1
random text lorem ipsum</p>
<div>
this should be returned
<span>this should also be returned</span>
<SPAN>this should also be returned</SPAN>
<div>
this should also be returned
</div>
@ -1859,10 +1859,6 @@ Line 1
GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML = GET_ELEMENT_BY_TAG_TEST_STRING.strip()[78:119]
GET_ELEMENT_BY_TAG_RES_INNERSPAN_TEXT = GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML[6:-7]
GET_ELEMENT_BY_TAG_TEST_STRING_UPPERCASE = '''
<SPAN id="foo">nice</SPAN>
'''
def test_get_element_text_and_html_by_tag(self):
html = self.GET_ELEMENT_BY_TAG_TEST_STRING
@ -1872,14 +1868,11 @@ Line 1
self.assertEqual(
get_element_text_and_html_by_tag('span', html),
(self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_TEXT, self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML))
self.assertRaises(compat_HTMLParseError, get_element_text_and_html_by_tag, 'article', html)
html = self.GET_ELEMENT_BY_TAG_TEST_STRING_UPPERCASE
self.assertEqual(
get_element_text_and_html_by_tag('SPAN', html),
('nice', html.strip()), html)
(self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_TEXT, self.GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML))
self.assertRaises(compat_HTMLParseError, get_element_text_and_html_by_tag, 'article', html)
def test_iri_to_uri(self):
self.assertEqual(

8
yt_dlp/utils/_utils.py
View file

@ -430,10 +430,14 @@ def get_element_text_and_html_by_tag(tag, html):
return its' content (text) and the whole element (html)
"""
def find_or_raise(haystack, needle, exc):
try:
with contextlib.suppress(ValueError):
return haystack.index(needle)
except ValueError:
with contextlib.suppress(ValueError):
return haystack.index(needle.upper())
raise exc
closing_tag = f'</{tag}>'
whole_start = find_or_raise(
html, f'<{tag}', compat_HTMLParseError(f'opening {tag} tag not found'))