def test_article_metadata_key_lowercase(self):
# Keys of metadata should be lowercase.
reader = readers.HTMLReader({})
content, metadata = reader.read(
_path('article_with_uppercase_metadata.html'))
self.assertIn('category', metadata, 'Key should be lowercase.')
self.assertEqual('Yeah', metadata.get('category'),
'Value keeps cases.')
def test_article_with_comments(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(_path('article_with_comments.html'))
self.assertEqual('''
Body content
<!-- This comment is included (including extra whitespace) -->
''', content)
def test_article_with_null_attributes(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(
_path('article_with_null_attributes.html'))
self.assertEqual('''
Ensure that empty attributes are copied properly.
<input name="test" disabled style="" />
''', content)
def test_article_with_keywords(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(_path('article_with_keywords.html'))
expected = {
'tags': ['foo', 'bar', 'foobar'],
}
for key, value in expected.items():
self.assertEqual(value, metadata[key], key)
def test_article_with_metadata(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(_path('article_with_metadata.html'))
expected = {
'category': 'yeah',
'author': 'Alexis Métaireau',
'title': 'This is a super article !',
'summary': 'Summary and stuff',
'date': datetime.datetime(2010, 12, 2, 10, 14),
'tags': ['foo', 'bar', 'foobar'],
'custom_field': 'http://notmyidea.org',
}
for key, value in expected.items():
self.assertEqual(value, metadata[key], key)
