def test_select_multiple(self):
'''
Test that extracted components can accept multiple selectors
'''
from mobilize.components import CssPath, XPath
selectors = [
'nav',
'section',
]
src_html = '''<div>
<nav>
<a href="/A">A</a>
<a href="/B">B</a>
</nav>
<table><tr><td> </td><td>I'm using tables for layout!!! DUR</td></tr></table>
<section>
<p>Hello.</p>
</section>
</div>
'''
expected_html = '''<div class="mwu-elem" id="foo">
<nav>
<a href="/A">A</a>
<a href="/B">B</a>
</nav>
<section>
<p>Hello.</p>
</section>
</div>'''
# test for CssPath
css_component = CssPath(selectors, idname='foo')
css_component.extract(html.fromstring(src_html))
extracted = css_component.process()
extracted_str = html.tostring(extracted)
self.assertSequenceEqual(normxml(expected_html), normxml(extracted_str))
# test for XPath
x_component = XPath(selectors, idname='foo')
x_component.extract(html.fromstring(src_html))
extracted = x_component.process()
extracted_str = html.tostring(extracted)
self.assertSequenceEqual(normxml(expected_html), normxml(extracted_str))
def test_collapse(self):
'''
Test for collapsing filter application mode
'''
from mobilize.components import (
XPath,
FILT_EACHELEM,
FILT_COLLAPSED,
)
def testfilter(elem):
if elem.tag == 'a':
elem.attrib['class'] = 'foo'
for ii, child in enumerate(elem):
if 'a' == child.tag:
child.attrib['id'] = 'child-%d' % ii
htmlstr1 = '''<a href="/">a</a>
<a href="/">b</a>
<a href="/">c</a>
'''
nocollapse = XPath('//a', postfilters=[testfilter], filtermode=FILT_EACHELEM)
nocollapse.extract(html.fromstring(htmlstr1))
actual = nocollapse.process('idname')
actual_str = html.tostring(actual)
expected_str = '''<div class="mwu-elem" id="idname">
<a href="/" class="foo">a</a>
<a href="/" class="foo">b</a>
<a href="/" class="foo">c</a>
</div>
'''
self.assertSequenceEqual(normxml(expected_str), normxml(actual_str))
expected_str = '''<div id="idname">
<a href="/">a</a>
<a href="/">b</a>
<a href="/">c</a>
</div>
'''
collapse = XPath('//a', postfilters=[testfilter], filtermode=FILT_COLLAPSED)
collapse.extract(html.fromstring(htmlstr1))
actual = collapse.process('idname')
actual_str = html.tostring(actual)
expected_str = '''<div class="mwu-elem" id="idname">
<a href="/" id="child-0">a</a>
<a href="/" id="child-1">b</a>
<a href="/" id="child-2">c</a>
</div>
'''
self.assertSequenceEqual(normxml(expected_str), normxml(actual_str))
def test_innerhtml(self):
from mobilize.components import XPath
html_str = '''<table><tr><td>Hello</td></tr></table>'''
# test for innerhtml=False
component_f = XPath('//td', idname='foo', innerhtml=False)
component_f.extract(html.fromstring(html_str))
extracted = component_f.process()
extracted_str = html.tostring(extracted)
expected = '<div class="mwu-elem" id="foo"><td>Hello</td></div>'
e = normxml(expected)
a = normxml(extracted_str)
self.assertSequenceEqual(e, a)
# test for innerhtml=True
component_t = XPath('//td', idname='foo', innerhtml=True)
component_t.extract(html.fromstring(html_str))
extracted = component_t.process()
extracted_str = html.tostring(extracted)
expected = '<div class="mwu-elem" id="foo">Hello</div>'
self.assertSequenceEqual(normxml(expected), normxml(extracted_str))
# test for ineffectiveness of innerhtml=True with multiple matching elements
component_t = XPath('//td', idname='foo', innerhtml=True)
component_t.extract(html.fromstring('''
<table><tr>
<td>Hello</td>
<td>Goodbye</td>
</tr></table>
'''))
extracted = component_t.process()
extracted_str = html.tostring(extracted)
expected = '<div class="mwu-elem" id="foo"><td>Hello</td><td>Goodbye</td></div>'
self.assertSequenceEqual(normxml(expected), normxml(extracted_str))