def test_html_encoding(self):
reader = HTMLReader()
for name in CODEC_NAMES:
data = io.BytesIO('<img>'.encode(name))
elements = tuple(reader.read_links(data, encoding=name))
html_element = elements[0]
self.assertEqual('html', html_element.tag)
def test_html_encoding(self):
reader = HTMLReader()
for name in CODEC_NAMES:
data = io.BytesIO('<img>'.encode(name))
elements = tuple(reader.read_links(data, encoding=name))
html_element = elements[0]
self.assertEqual('html', html_element.tag)
def test_html_early_html(self):
reader = HTMLReader()
for test_string in [
b'''<!DOCTYPE HTML><html></html><img>''',
b'''<html></html><img>''',
b'''<!DOCTYPE HTML><img><html></html>''',
b'''<img><html></html>''',
b'''<!DOCTYPE HTML>
<html><body></body></html><p><img>''',
b'''
<html><body></body></html><p><img>''',
b'''
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>Download</title>
</head>
<body>
<br />
</body>
</html>
<pre><img></pre>
''',
b'''
<html>
<head>
<title>Download</title>
</head>
<body>
<br />
</body>
</html>
<pre><img></pre>
''',
b'''
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd">
<html>
<body>
<br />
</body>
<head>
<title>Download</title>
</head>
</html>
<pre><img></pre>
''',
b'''
<html>
<body>
<br />
</body>
<head>
<title>Download</title>
</head>
</html>
<pre><img></pre>
''',
]:
elements = tuple(
reader.read_links(io.BytesIO(test_string), encoding='ascii')
)
self.assertEqual('img', elements[-1].tag)
elements = tuple(
reader.read_tree(io.BytesIO(test_string), encoding='ascii')
)
self.assertEqual('img', elements[-4].tag)
def test_html_early_html(self):
reader = HTMLReader()
for test_string in [
b'''<!DOCTYPE HTML><html></html><img>''',
b'''<html></html><img>''',
b'''<!DOCTYPE HTML><img><html></html>''',
b'''<img><html></html>''',
b'''<!DOCTYPE HTML>
<html><body></body></html><p><img>''',
b'''
<html><body></body></html><p><img>''',
b'''
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>Download</title>
</head>
<body>
<br />
</body>
</html>
<pre><img></pre>
''',
b'''
<html>
<head>
<title>Download</title>
</head>
<body>
<br />
</body>
</html>
<pre><img></pre>
''',
b'''
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
"http://www.w3.org/TR/html4/loose.dtd">
<html>
<body>
<br />
</body>
<head>
<title>Download</title>
</head>
</html>
<pre><img></pre>
''',
b'''
<html>
<body>
<br />
</body>
<head>
<title>Download</title>
</head>
</html>
<pre><img></pre>
''',
]:
elements = tuple(
reader.read_links(io.BytesIO(test_string), encoding='ascii')
)
self.assertEqual('img', elements[-1].tag)
elements = tuple(
reader.read_tree(io.BytesIO(test_string), encoding='ascii')
)
self.assertEqual('img', elements[-4].tag)
