def parse_html(html_string, debug=False):
""" create the document tree from html code """
assert isinstance(html_string, str), "given html_string must be unicode!"
h2c = HtmlParser(debug=debug)
document_tree = h2c.feed(html_string)
if debug:
h2c.debug()
return document_tree
</ul>
</li>
<li><p>subitem 1.2</p>
</li>
</ul>
</li>
<li><p>item 2</p>
<ul>
<li>subitem 2.1</li>
</ul>
</li>
</ul>
<p>Text under list.</p>
<p>4 <img alt="PNG pictures" src="/image.png" /> four</p>
<p>5 <img alt="Image without files ext?" src="/path1/path2/image" /> five</p>
"""
print(data)
h2c = HtmlParser(
# debug=True
)
document_tree = h2c.feed(data)
h2c.debug()
e = ReStructuredTextEmitter(document_tree, debug=True)
content = e.emit()
print("*" * 79)
print(content)
print("*" * 79)
print(content.replace(" ", ".").replace("\n", "\\n\n"))