Browse Source

[InfoExtractor/common] Correct and test meta tag matching

totalwebcasting
Philipp Hagemeister 10 years ago
parent
commit
bec2248141
2 changed files with 19 additions and 1 deletions
  1. +18
    -0
      test/test_InfoExtractor.py
  2. +1
    -1
      youtube_dl/extractor/common.py

+ 18
- 0
test/test_InfoExtractor.py View File

@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
def test_html_search_meta(self):
ie = self.ie
html = '''
<meta name="a" content="1" />
<meta name='b' content='2'>
<meta name="c" content='3'>
<meta name=d content='4'>
<meta property="e" content='5' >
<meta content="6" name="f">
'''
self.assertEqual(ie._html_search_meta('a', html), '1')
self.assertEqual(ie._html_search_meta('b', html), '2')
self.assertEqual(ie._html_search_meta('c', html), '3')
self.assertEqual(ie._html_search_meta('d', html), '4')
self.assertEqual(ie._html_search_meta('e', html), '5')
self.assertEqual(ie._html_search_meta('f', html), '6')
if __name__ == '__main__':
unittest.main()

+ 1
- 1
youtube_dl/extractor/common.py View File

@ -594,7 +594,7 @@ class InfoExtractor(object):
return self._html_search_regex(
r'''(?isx)<meta
(?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
[^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html):


Loading…
Cancel
Save