Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-27 21:59:17 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

[core] utils: fix get_element_by_*

Browse source
This commit is contained in:
Allen 2024-12-04 23:10:45 +01:00
parent 354cb4026c
commit d9195b5133
No known key found for this signature in database
2 changed files with 21 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
test/test_utils.py
View file

@ -1769,6 +1769,10 @@ Line 1
<div itemprop="author" itemscope>foo</div> <div itemprop="author" itemscope>foo</div>
''' '''
GET_ELEMENT_BY_ATTRIBUTE_TEST_STRING_UPPERCASE = '''
<DIV itemprop="author" itemscope>foo</DIV>
'''
def test_get_element_by_attribute(self): def test_get_element_by_attribute(self):
html = self.GET_ELEMENT_BY_CLASS_TEST_STRING html = self.GET_ELEMENT_BY_CLASS_TEST_STRING
@ -1780,6 +1784,10 @@ Line 1
self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo') self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
html = self.GET_ELEMENT_BY_ATTRIBUTE_TEST_STRING_UPPERCASE
self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
def test_get_element_html_by_attribute(self): def test_get_element_html_by_attribute(self):
html = self.GET_ELEMENT_BY_CLASS_TEST_STRING html = self.GET_ELEMENT_BY_CLASS_TEST_STRING
@ -1851,6 +1859,11 @@ Line 1
GET_ELEMENT_BY_TAG_RES_INNERSPAN_HTML = GET_ELEMENT_BY_TAG_TEST_STRING.strip()[78:119] 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_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): def test_get_element_text_and_html_by_tag(self):
html = self.GET_ELEMENT_BY_TAG_TEST_STRING html = self.GET_ELEMENT_BY_TAG_TEST_STRING
@ -1860,8 +1873,15 @@ Line 1
self.assertEqual( self.assertEqual(
get_element_text_and_html_by_tag('span', html), 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.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) 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)
def test_iri_to_uri(self): def test_iri_to_uri(self):
self.assertEqual( self.assertEqual(
iri_to_uri('https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b'), iri_to_uri('https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b'),

2
yt_dlp/utils/_utils.py
View file

@ -442,7 +442,7 @@ def get_element_text_and_html_by_tag(tag, html):
content_start += whole_start + 1 content_start += whole_start + 1
with HTMLBreakOnClosingTagParser() as parser: with HTMLBreakOnClosingTagParser() as parser:
parser.feed(html[whole_start:content_start]) parser.feed(html[whole_start:content_start])
if not parser.tagstack or parser.tagstack[0] != tag: if not parser.tagstack or parser.tagstack[0] != tag.lower():
raise compat_HTMLParseError(f'parser did not match opening {tag} tag') raise compat_HTMLParseError(f'parser did not match opening {tag} tag')
offset = content_start offset = content_start
while offset < len(html): while offset < len(html):