def test_null_bytes(self):
hxs = HtmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(hxs.extract(),
u'<html><body><root>lala</root></body></html>')
xxs = XmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(xxs.extract(), u'<root>lala</root>')
def test_null_bytes(self):
hxs = HtmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(hxs.extract(),
u'<html><body><root>lala</root></body></html>')
xxs = XmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(xxs.extract(),
u'<root>lala</root>')
def test_unquote(self):
xmldoc = "\n".join(
(
"<root>",
" lala",
" <node>",
" blabla&more<!--comment-->a<b>test</b>oh",
" <![CDATA[lalalal&ppppp<b>PPPP</b>ppp&la]]>",
" </node>",
" pff",
"</root>",
)
)
xxs = XmlXPathSelector(text=xmldoc)
self.assertEqual(xxs.extract_unquoted(), u"")
self.assertEqual(xxs.select("/root").extract_unquoted(), [u""])
self.assertEqual(xxs.select("/root/text()").extract_unquoted(), [u"\n lala\n ", u"\n pff\n"])
self.assertEqual(xxs.select("//*").extract_unquoted(), [u"", u"", u""])
self.assertEqual(
xxs.select("//text()").extract_unquoted(),
[
u"\n lala\n ",
u"\n blabla&more",
u"a",
u"test",
u"oh\n ",
u"lalalal&ppppp<b>PPPP</b>ppp&la",
u"\n ",
u"\n pff\n",
],
)
def test_unquote(self):
xmldoc = '\n'.join((
'<root>',
' lala',
' <node>',
' blabla&more<!--comment-->a<b>test</b>oh',
' <![CDATA[lalalal&ppppp<b>PPPP</b>ppp&la]]>',
' </node>',
' pff',
'</root>'))
xxs = XmlXPathSelector(text=xmldoc)
self.assertEqual(xxs.extract_unquoted(), u'')
self.assertEqual(xxs.select('/root').extract_unquoted(), [u''])
self.assertEqual(xxs.select('/root/text()').extract_unquoted(), [
u'\n lala\n ',
u'\n pff\n'])
self.assertEqual(xxs.select('//*').extract_unquoted(), [u'', u'', u''])
self.assertEqual(xxs.select('//text()').extract_unquoted(), [
u'\n lala\n ',
u'\n blabla&more',
u'a',
u'test',
u'oh\n ',
u'lalalal&ppppp<b>PPPP</b>ppp&la',
u'\n ',
u'\n pff\n'])
def test_unquote(self):
xmldoc = '\n'.join(
('<root>', ' lala', ' <node>',
' blabla&more<!--comment-->a<b>test</b>oh',
' <![CDATA[lalalal&ppppp<b>PPPP</b>ppp&la]]>', ' </node>',
' pff', '</root>'))
xxs = XmlXPathSelector(text=xmldoc)
self.assertEqual(xxs.extract_unquoted(), u'')
self.assertEqual(xxs.select('/root').extract_unquoted(), [u''])
self.assertEqual(
xxs.select('/root/text()').extract_unquoted(),
[u'\n lala\n ', u'\n pff\n'])
self.assertEqual(xxs.select('//*').extract_unquoted(), [u'', u'', u''])
self.assertEqual(
xxs.select('//text()').extract_unquoted(), [
u'\n lala\n ', u'\n blabla&more', u'a', u'test',
u'oh\n ', u'lalalal&ppppp<b>PPPP</b>ppp&la', u'\n ',
u'\n pff\n'
])