def test_missing_title_tag():
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<h1>Gandalf</h1>
<body>hi</body>
"""
parts = hfr.parse_html(html_frag)
assert parts['title'] == '[[NO TITLE FOUND]]'
def test_content_without_body():
""" If you don't have any content in your page at all;
you'll get this message."""
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<title>Gandalf</title>
</head>
"""
parts = hfr.parse_html(html_frag)
assert parts['content'] == '[[YOUR CONTENT SHOULD GO HERE]]'
def test_read_category_metadata():
# Category is a special case; it gets converted to "categories"
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<title>Gandalf</title>
<meta name="category" content="hobbit"/>
<body>Hi</body>
"""
parts = hfr.parse_html(html_frag)
assert parts['meta']['categories'] == 'hobbit'
def test_read_title_tag():
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<title>Gandalf</title>
<body>hi</body>
"""
parts = hfr.parse_html(html_frag)
# Ensure both ways of reading titles are available
assert parts['title'] == 'Gandalf'
assert parts['meta']['title'] == 'Gandalf'
def test_bad_meta_tag():
hfr = HtmlFileReader('no_filename')
# This meta tag doesn't have a "content" attribute.
html_frag = """
<head>
<title>Gandalf</title>
<meta name="tags" value="hobbit"/>
<body>Hi</body>
"""
parts = hfr.parse_html(html_frag)
# No category stuff, and we should NOT throw an exception
assert 'tags' not in parts['meta']
def test_custom_theme():
hfr = HtmlFileReader('no_filename')
# This meta tag doesn't have a "content" attribute.
html_frag = """
<head>
<title>Gandalf</title>
<meta name="theme" content="lotr"/>
<body>Hi</body>
"""
parts = hfr.parse_html(html_frag)
# No category stuff, and we should NOT throw an exception
assert 'theme' in parts['meta']
assert parts['meta']['theme'] == 'lotr'
def test_read_content():
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<title>Gandalf</title>
<body>
<p>Bilbo Baggins</p>
<p>Bard the Bowman</p>
<p>Thorin Oakenshield</p>
</body>
"""
parts = hfr.parse_html(html_frag)
expected = '''
<p>Bilbo Baggins</p>
<p>Bard the Bowman</p>
<p>Thorin Oakenshield</p>
'''
assert parts['content'] == expected
def test_content_no_explicit_body_tag():
""" if a <body> tag is not specified, anything that is not
a <head> is treated as the body."""
hfr = HtmlFileReader('no_filename')
html_frag = """
<head>
<title>Gandalf</title>
</head>
<div>
<p>Bilbo Baggins</p>
<p>Bard the Bowman</p>
<p>Thorin Oakenshield</p>
</div>
"""
expected = '''<div>
<p>Bilbo Baggins</p>
<p>Bard the Bowman</p>
<p>Thorin Oakenshield</p>
</div>
'''
parts = hfr.parse_html(html_frag)
assert parts['content'] == expected