def test_render_html(self):
html = u'<html><body><p>фыва</p></body></html>'
html_utf = html.encode('utf-8')
tree = fromstring(html)
self.assertEqual(html_utf, render_html(tree))
self.assertEqual(html, render_html(tree, make_unicode=True))
self.assertEqual(html.encode('cp1251'), render_html(tree, encoding='cp1251'))
def test_replace_node_with_text(self):
# replace span
HTML = """
<div><p><span>span</span><a href="#">link</a></p></div>
"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == '<div><p>FOO<a href="#">link</a></p></div>')
# replace span and keep its tail
HTML = """
<div><p><span>span</span>BAR<a href="#">link</a></p></div>
"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == '<div><p>FOOBAR<a href="#">link</a></p></div>')
# replace p which is only child of parent div
HTML = """
<div><p><span>span</span>BAR<a href="#">link</a></p></div>
"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/p', 'FOO')
self.assertTrue(render_html(tree) == '<div>FOO</div>')
# replace span and keep tai of its preceeding sibling element
HTML = """
<div><p><strong>str</strong>!<span>span</span>BAR<a href="#">link</a></p></div>
"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == '<div><p><strong>str</strong>!FOOBAR<a href="#">link</a></p></div>')
def test_replace_node_with_text(self):
# replace span
HTML = """
<div><p><span>span</span><a href="#">link</a></p></div>"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == b'<div><p>FOO<a href="#">link</a></p></div>')
# replace span and keep its tail
HTML = """
<div><p><span>span</span>BAR<a href="#">link</a></p></div>"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == b'<div><p>FOOBAR<a href="#">link</a></p></div>')
# replace p which is only child of parent div
HTML = """
<div><p><span>span</span>BAR<a href="#">link</a></p></div>"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/p', 'FOO')
self.assertTrue(render_html(tree) == b'<div>FOO</div>')
# replace span and keep tai of its preceeding sibling element
HTML = """
<div><p><strong>str</strong>!<span>span</span>BAR<a href="#">link</a></p></div>"""
tree = fromstring(HTML)
replace_node_with_text(tree, './/span', 'FOO')
self.assertTrue(render_html(tree) == b'<div><p><strong>str</strong>!FOOBAR<a href="#">link</a></p></div>')
def test_render_html(self):
html = u'<html><body><p>фыва</p></body></html>'
html_utf = html.encode('utf-8')
tree = fromstring(html)
self.assertEqual(html_utf, render_html(tree))
self.assertEqual(html, render_html(tree, make_unicode=True))
self.assertEqual(html.encode('cp1251'), render_html(tree, encoding='cp1251'))
def test_drop_node(self):
HTML = """
<div><p>text<span>span</span><a href="#">link</a></p>tail</div>"""
tree = fromstring(HTML)
drop_node(tree, './/p')
self.assertTrue(render_html(tree) == b'<div>tail</div>')
tree = fromstring(HTML)
drop_node(tree, './/span', keep_content=True)
self.assertTrue(render_html(tree) == b'<div><p>textspan<a href="#">link</a></p>tail</div>')
def test_drop_node(self):
HTML = """
<div><p>text<span>span</span><a href="#">link</a></p>tail</div>
"""
tree = fromstring(HTML)
drop_node(tree, './/p')
self.assertTrue(render_html(tree) == '<div>tail</div>')
tree = fromstring(HTML)
drop_node(tree, './/span', keep_content=True)
self.assertTrue(render_html(tree) == '<div><p>textspan<a href="#">link</a></p>tail</div>')
def parse_project_description(self, root):
for node in root.xpath("//br"):
node.tail = (node.tail or "") + "\n"
text = strip_tags(decode_entities(render_html(root, encoding="unicode")), normalize_space=False)
text = text.split(u"Posted On")[0].strip()
text = text.split(u"Budget :")[0].strip()
return text
def parse_project_description(self, root):
for node in root.xpath('//br'):
node.tail = (node.tail or '') + '\n'
text = strip_tags(decode_entities(render_html(root,
encoding='unicode')),
normalize_space=False)
text = text.split(u'Category:')[0].strip()
return text
def html(self, encoding='unicode'):
return render_html(self.node, encoding=encoding)
def html(self, encoding='unicode'):
return render_html(self.node, encoding=encoding)