def test_comment2(self):
html = b"""
<html>
<head><title>Foo</title></head>
<body>
Some text.
<!-- HTML comment -->
Some more text.
<p>Text</p>
More text
</body>
</html>
"""
tree = decode_body(html, "http://example.com/test.html")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(
og,
{
"og:title":
"Foo",
"og:description":
"Some text.\n\nSome more text.\n\nText\n\nMore text",
},
)
def test_windows_1252(self):
"""A body which uses cp1252, but doesn't declare that."""
html = b"""
<html>
<head><title>\xf3</title></head>
<body>
Some text.
</body>
</html>
"""
tree = decode_body(html, "http://example.com/test.html")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "ó", "og:description": "Some text."})
def test_invalid_encoding(self):
"""An invalid character encoding should be ignored and treated as UTF-8, if possible."""
html = b"""
<html>
<head><title>Foo</title></head>
<body>
Some text.
</body>
</html>
"""
tree = decode_body(html, "invalid-encoding")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "Foo", "og:description": "Some text."})
def test_missing_title(self):
html = b"""
<html>
<body>
Some text.
</body>
</html>
"""
tree = decode_body(html)
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": None, "og:description": "Some text."})
def test_invalid_encoding2(self):
"""A body which doesn't match the sent character encoding."""
# Note that this contains an invalid UTF-8 sequence in the title.
html = b"""
<html>
<head><title>\xff\xff Foo</title></head>
<body>
Some text.
</body>
</html>
"""
tree = decode_body(html)
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "ÿÿ Foo", "og:description": "Some text."})
def test_h1_as_title(self):
html = b"""
<html>
<meta property="og:description" content="Some text."/>
<body>
<h1>Title</h1>
</body>
</html>
"""
tree = decode_body(html)
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "Title", "og:description": "Some text."})
def test_simple(self):
html = b"""
<html>
<head><title>Foo</title></head>
<body>
Some text.
</body>
</html>
"""
tree = decode_body(html)
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {"og:title": "Foo", "og:description": "Some text."})
def test_xml(self):
"""Test decoding XML and ensure it works properly."""
# Note that the strip() call is important to ensure the xml tag starts
# at the initial byte.
html = b"""
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head><title>Foo</title></head><body>Some text.</body></html>
""".strip()
tree = decode_body(html, "http://example.com/test.html")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {
"og:title": "Foo",
"og:description": "Some text."
})
def test_missing_title_and_broken_h1(self):
html = b"""
<html>
<body>
<h1><a href="foo"/></h1>
Some text.
</body>
</html>
"""
tree = decode_body(html, "http://example.com/test.html")
og = _calc_og(tree, "http://example.com/test.html")
self.assertEqual(og, {
"og:title": None,
"og:description": "Some text."
})