1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
|
# -*- coding: utf-8 -*-
from pyth.plugins.xhtml.reader import XHTMLReader
from pyth.plugins.xhtml.writer import XHTMLWriter
import xhtml
from cStringIO import StringIO
# A simple xhtml document with limited features.
content = StringIO(r"""
<div>
<p><strong>Simple document</strong></p>
<p><i>this document has
</i>no hypertext links yet.</p>
<p><strong>bold text.</strong> <em>italic text.</em></p>
<p class=important>bold text from css style
<em> this is bold and italic</em>
</p>
<p class=bold> this is bold too</p>
<p>unicode characters : 你好</p>
<p style="font-weight: bold">bold too</p>
<p>
example<span style="vertical-align: super"> super </span>
example<span style="vertical-align: sub"> sub </span>
</p>
a list
<ul>
<li>hello
test</li>
<li>bonjour</li>
<li>guten tag</li>
</ul>
<p>
<a href=http://www.google.com>a link
</a> single space here.
<br/>a br tag
</p>
</div>
""")
css = """
.important {font-weight: bold}
p.bold {font-weight: bold}
.other {font-weight: normal; color: blue}
"""
if __name__ == '__main__':
# Parse the document and then reconstruct it using the xhtml
# writer.
doc = XHTMLReader.read(content, css)
print XHTMLWriter.write(doc).getvalue()
|
