commit 609ff8ca19f1c4c168a81121074b91cc0f0d4c47
parent b6c9fe416243373bcb59eb8aa5ef0baca8f3c97c
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date: Wed, 5 Jul 2017 23:23:35 +0800
[utils] Support attributes with no values in get_elements_by_attribute()
Diffstat:
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/test/test_utils.py b/test/test_utils.py
@@ -1228,6 +1228,12 @@ part 3</font></u>
self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
+ html = '''
+ <div itemprop="author" itemscope>foo</div>
+ '''
+
+ self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
+
def test_get_elements_by_class(self):
html = '''
<span class="foo bar">nice</span><span class="foo bar">also nice</span>
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
@@ -365,9 +365,9 @@ def get_elements_by_attribute(attribute, value, html, escape_value=True):
retlist = []
for m in re.finditer(r'''(?xs)
<([a-zA-Z0-9:._-]+)
- (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
+ (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s+%s=['"]?%s['"]?
- (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
+ (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
\s*>
(?P<content>.*?)
</\1>