mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-03-09 12:50:23 -05:00
Code Activity

[parsing] fix return value

Browse source
This commit is contained in:
Marcel 2022-11-27 16:56:45 +01:00
parent 7a67a2028f
commit 29278a3323
No known key found for this signature in database
GPG key ID: 7813C97693AD6AAE
2 changed files with 15 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
test/test_parsing.py
View file

@ -195,7 +195,7 @@ class StrictParser(MatchingElementParser):
<span>ignore</span>
'''
items = get_elements_text_and_html_by_tag('img', test_string)
self.assertListEqual(items, [('', '<img src="a.png">'), ('', '<img src="b.png" />')])
self.assertEqual(items, [('', '<img src="a.png">'), ('', '<img src="b.png" />')])
self.assertEqual(
StrictParser.get_element_text_and_html_by_tag('use', '<use><img></use>'),
@ -245,16 +245,26 @@ def test_relaxed_html_parsing(self):
parser = HTMLTagParser()
self.assertEqual(parser.taglist('</p>', reset=True), [])
self.assertEqual(parser.taglist('<div><p>', reset=True), [Tag('div'), Tag('p')])
tags = parser.taglist('<div><p>', reset=True)
self.assertEqual(tags, [Tag('div'), Tag('p')])
self.assertEqual(tags[0].text_and_html(), ('', '<div>'))
self.assertEqual(tags[1].text_and_html(), ('', '<p>'))
tags = parser.taglist('<div><p></div></p>', reset=True)
self.assertEqual(tags, [Tag('div'), Tag('p')])
self.assertEqual(tags[0].text_and_html(), ('<p>', '<div><p></div>'))
self.assertEqual(tags[1].text_and_html(), ('</div>', '<p></div></p>'))
tags = parser.taglist('<div><p>/p></div>', reset=True)
self.assertEqual(tags, [Tag('div'), Tag('p')])
self.assertEqual(tags[0].text_and_html(), ('<p>/p>', '<div><p>/p></div>'))
self.assertEqual(tags[1].text_and_html(), ('', '<p>'))
tags = parser.taglist('<div><p>paragraph</p<ignored></div>', reset=True)
self.assertEqual(tags, [Tag('div'), Tag('p')])
self.assertEqual(tags[0].text_and_html(),
('<p>paragraph</p<ignored>', '<div><p>paragraph</p<ignored></div>'))
self.assertEqual(tags[1].text_and_html(), ('paragraph', '<p>paragraph</p<ignored>'))
tags = parser.taglist('<img width="300px">must be empty</img>', reset=True)
@ -315,7 +325,7 @@ def test_tag_return_order(self):
[Tag('t5'), Tag('t6')]],
[Tag('t7'), Tag('t8')]]))
def test_within_html_comment(self):
def test_html_comment_ranges(self):
def mark_comments(_string, char='^', nochar='-'):
cmts = HTMLCommentRanges(_string)
return "".join(char if _idx in cmts else nochar for _idx in range(len(_string)))

4
yt_dlp/parsing.py
View file

@ -318,7 +318,7 @@ def get_elements_text_and_html_by_attribute(cls, *args, **kwargs):
@classmethod
def get_elements_by_attribute(cls, *args, **kwargs):
return [tag.text_and_html()[0] for tag in cls.tags_by_attribute(*args, **kwargs)]
return [tag.text() for tag in cls.tags_by_attribute(*args, **kwargs)]
@classmethod
def get_elements_html_by_attribute(cls, *args, **kwargs):
@ -349,7 +349,7 @@ def get_elements_html_by_class(cls, class_name, html):
@classmethod
def get_elements_text_and_html_by_class(cls, class_name, html):
value = cls.class_value_regex(class_name)
return [tag.text() for tag
return [tag.text_and_html() for tag
in cls.tags_by_attribute('class', value, html, escape_value=False)]
@classmethod