def parsing_html(page, page_title=None):
'''
Parse the HTML to put it in an envelope. Optional arguments are for
unittests only.
'''
try:
with open(page, 'r') as contents:
soupit = BeautifulSoup(contents, 'html.parser')
with open(page, 'r') as contents2:
that_page = tocbuilder.parse_it(contents2)
except OSError:
soupit = BeautifulSoup(page, 'html.parser')
that_page = tocbuilder.parse_it(page)
toc_html = tocbuilder.htmlify(that_page)
if page_title == None:
the_title = soupit.title.string
else:
the_title = page_title
set_up_class = Envelope_RAML(page,
soupit.body,
originalFile=page,
title=the_title,
toc=toc_html)
whole_envelope = set_up_class.make_an_envelope()
return whole_envelope
def test_parse_it_full_pass(self):
'''
Does parse_it work for a full sample?
'''
self.maxDiff = None
html_sample = (
'<body><h2>Heading 1 h4</h2><p>Random text</p>'
'<h3>Heading 1.1 h4</h3><p>Random text</p><p>Random text</p>'
'<h4>Heading 1.1.1 h4</h4><p>Random text</p><p>Random text</p>'
'<h4>Heading 1.1.2 h4</h4><p>Random text</p>'
'<h3>Heading 1.2 h4</h3><p>Random text</p><p>Random text</p>'
'<h4>Heading 1.2.1 h4</h4><p>Random text</p>'
'<h2>Heading 2 h4</h2><p>Random text</p><p>Random text</p>'
'<h3>Heading 2.1 h4</h3><p>Random text</p>'
'<h3>Heading 2.2 h4</h3><p>Random text</p><p>Random text</p>'
'<p>Random text</p></body>')
the_result = [
'<li><a href="#Heading1h4">Heading 1 h4</a></li>',
[
'<li><a href="#Heading1.1h4">Heading 1.1 h4</a></li>',
[
'<li><a href="#Heading1.1.1h4">Heading 1.1.1 h4</a></li>',
'<li><a href="#Heading1.1.2h4">Heading 1.1.2 h4</a></li>'
], '<li><a href="#Heading1.2h4">Heading 1.2 h4</a></li>',
['<li><a href="#Heading1.2.1h4">Heading 1.2.1 h4</a></li>']
], '<li><a href="#Heading2h4">Heading 2 h4</a></li>',
[
'<li><a href="#Heading2.1h4">Heading 2.1 h4</a></li>',
'<li><a href="#Heading2.2h4">Heading 2.2 h4</a></li>'
]
]
the_method = parse_it(html_sample)
self.assertEqual(the_method, the_result)
def test_parse_it_h2_only(self):
'''
Does parse_it work for h2 tags only?
'''
self.maxDiff = None
html_sample = '<body><h2>Heading 1 h2</h2><h2>Heading 2 h2</h2></body>'
the_result = [
'<li><a href="#Heading1h2">Heading 1 h2</a></li>',
'<li><a href="#Heading2h2">Heading 2 h2</a></li>'
]
the_method = parse_it(html_sample)
self.assertEqual(the_method, the_result)
def test_parse_it_h2_and_h3(self):
'''
Does parse_it work for h2 and h3 tags?
'''
self.maxDiff = None
html_sample = ('<body><h2>Heading 1 h3</h2><h3>Heading 1.1 h3</h3>'
'<h3>Heading 1.2 h3</h3><h2>Heading 2 h3</h2>'
'<h3>Heading 2.1 h3</h3><h3>Heading 2.2 h3</h3></body>')
# BUG: Need to figure out why the double square bracket appears on the
# first 2nd level here.
the_result = [
'<li><a href="#Heading1h3">Heading 1 h3</a></li>',
[[
'<li><a href="#Heading1.1h3">Heading 1.1 h3</a></li>',
'<li><a href="#Heading1.2h3">Heading 1.2 h3</a></li>'
]], '<li><a href="#Heading2h3">Heading 2 h3</a></li>',
[
'<li><a href="#Heading2.1h3">Heading 2.1 h3</a></li>',
'<li><a href="#Heading2.2h3">Heading 2.2 h3</a></li>'
]
]
the_method = parse_it(html_sample)
self.assertEqual(the_method, the_result)