github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

new HTMLReader

Browse source
This commit is contained in:
dave mankoff 2012-06-14 23:08:34 -04:00
commit cc1988fbda
5 changed files with 146 additions and 97 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/content/article_with_keywords.html Normal file
View file

@ -0,0 +1,6 @@
<html>
<head>
<title>This is a super article !</title>
<meta name="keywords" contents="foo, bar, foobar" />
</head>
</html>

15
tests/content/article_with_metadata.html Normal file
View file

@ -0,0 +1,15 @@
<html>
<head>
<title>This is a super article !</title>
<meta name="tags" contents="foo, bar, foobar" />
<meta name="date" contents="2010-12-02 10:14" />
<meta name="category" contents="yeah" />
<meta name="author" contents="Alexis Métaireau" />
<meta name="custom_field" contents="http://notmyidea.org" />
</head>
<body>
Multi-line metadata should be supported
as well as <strong>inline markup</strong>.
<!-- PELICAN_END_SUMMARY -->
</body>
</html>

6
tests/content/article_with_uppercase_metadata.html Normal file
View file

@ -0,0 +1,6 @@
<html>
<head>
<title>This is a super article !</title>
<meta name="Category" contents="Yeah" />
</head>
</html>

38
tests/test_readers.py
View file

@ -86,3 +86,41 @@ class MdReaderTest(unittest.TestCase):
"<p>This is another markdown test file. Uses the mkd extension.</p>"
self.assertEqual(content, expected)
class HTMLReaderTest(unittest.TestCase):
def test_article_with_metadata(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_metadata.html'))
expected = {
'category': 'yeah',
'author': u'Alexis Métaireau',
'title': 'This is a super article !',
'summary': u'''
Multi-line metadata should be supported
as well as <strong>inline markup</strong>.
''',
'date': datetime.datetime(2010, 12, 2, 10, 14),
'tags': ['foo', 'bar', 'foobar'],
'custom_field': 'http://notmyidea.org',
}
for key, value in expected.items():
self.assertEquals(value, metadata[key], key)
def test_article_with_keywords(self):
reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_keywords.html'))
expected = {
'tags': ['foo', 'bar', 'foobar'],
}
for key, value in expected.items():
self.assertEquals(value, metadata[key], key)
def test_article_metadata_key_lowercase(self):
"""Keys of metadata should be lowercase."""
reader = readers.HTMLReader({})
content, metadata = reader.read(_filename('article_with_uppercase_metadata.html'))
self.assertIn('category', metadata, "Key should be lowercase.")
self.assertEquals('Yeah', metadata.get('category'), "Value keeps cases.")