def test_regexp(self):
html = '<div><h1 id="h1">foo</h1><h2>bar</h2></div>'
sel = XpathSelector(fromstring(html))
self.assertEqual('h2', sel.select('//*[re:test(text(), "b.r")]')\
.node().tag)
self.assertEqual('foo', sel.select('//*[re:test(@id, "^h\d+$")]'
'/text()').text())
def test_regexp(self):
html = '<div><h1 id="h1">foo</h1><h2>bar</h2></div>'
sel = XpathSelector(fromstring(html))
self.assertEqual('h2', sel.select('//*[re:test(text(), "b.r")]')\
.node().tag)
self.assertEqual(
'foo',
sel.select('//*[re:test(@id, "^h\d+$")]'
'/text()').text())
def test_incorrect_xpath(self):
# The lxml xpath function return boolean for following xpath
# This breaks selector internal logic that assumes that only
# list could be returnsed
# So it was fixed and this test was crated
sel = XpathSelector(self.tree).select('//ul/li/text()="oops"')
self.assertEquals(False, sel.exists())
# Selector list is always empty in this special case
# Even if the xpath return True on lxml level
self.assertEquals(True, self.tree.xpath('//ul[1]/li[1]/text()="one"'))
sel = XpathSelector(self.tree).select('//ul[1]/li[1]/text()="one"')
self.assertEquals(False, sel.exists())
def test_incorrect_xpath(self):
# The lxml xpath function return boolean for following xpath
# This breaks selector internal logic that assumes that only
# list could be returnsed
# So it was fixed and this test was crated
sel = XpathSelector(self.tree).select('//ul/li/text()="oops"')
self.assertEquals(False, sel.exists())
# Selector list is always empty in this special case
# Even if the xpath return True on lxml level
self.assertEquals(True, self.tree.xpath('//ul[1]/li[1]/text()="one"'))
sel = XpathSelector(self.tree).select('//ul[1]/li[1]/text()="one"')
self.assertEquals(False, sel.exists())
def test_text(self):
sel = XpathSelector(self.tree).select("//ul/li")
self.assertEquals("one", sel.text())
def test_rex_method(self):
sel = XpathSelector(self.tree)
self.assertTrue(isinstance(sel.select("//li").rex("\w*"), RexResultList))
def test_text_selector_html(self):
sel = XpathSelector(self.tree).select("//li/text()").one()
self.assertEquals(u"one", sel.html())
def test_node_default(self):
sel = XpathSelector(self.tree).select('//ul/li[10]')
self.assertRaises(DataNotFound, lambda: sel.node())
self.assertEqual('DEFAULT', sel.node(default='DEFAULT'))
def test_attr_does_not_exist(self):
root = XpathSelector(self.tree)
self.assertRaises(DataNotFound, lambda: root.select("//ul[1]").attr("id-xxx"))
def test_xpath_concat_function(self):
html = '<a href="index.html"></a>'
sel = XpathSelector(fromstring(html))
self.assertEqual('/index.html', sel.select('concat("/",//a/@href)')\
.text())
def test_rex_default(self):
sel = XpathSelector(self.tree).select("//ul/li[10]")
self.assertRaises(DataNotFound, lambda: sel.rex("zz"))
self.assertEquals("DEFAULT", sel.rex("zz", default="DEFAULT"))
def test_number_default(self):
sel = XpathSelector(self.tree).select('//ul/li[10]')
self.assertRaises(DataNotFound, sel.number)
self.assertEquals('DEFAULT', sel.number(default='DEFAULT'))
def test_exists(self):
sel = XpathSelector(self.tree).select('//ul/li[4]')
self.assertEquals(True, sel.exists())
sel = XpathSelector(self.tree).select('//ul/li[5]')
self.assertEquals(False, sel.exists())
def test_inner_html_default(self):
sel = XpathSelector(self.tree).select('//ul/li[10]')
self.assertRaises(DataNotFound, sel.inner_html)
self.assertEquals('DEFAULT', sel.inner_html(default='DEFAULT'))
def test_number(self):
sel = XpathSelector(self.tree).select('//ul/li[4]')
self.assertEquals(4, sel.number())
def test_inner_html(self):
sel = XpathSelector(self.tree).select('//ul[@id="second-list"]')
self.assertEquals(
u'<li class="li-1">yet one</li>\n <li class="li-2">yet two</li>',
sel.inner_html().strip())
def test_html(self):
sel = XpathSelector(self.tree).select('//ul/li')
self.assertEquals(u'<li>one</li>', sel.html().strip())
def test_text(self):
sel = XpathSelector(self.tree).select('//ul/li')
self.assertEquals('one', sel.text())
def test_number(self):
sel = XpathSelector(self.tree).select("//ul/li[4]")
self.assertEquals(4, sel.number())
def test_text_no_default(self):
sel = XpathSelector(self.tree).select("//ul/li/text()")
self.assertRaises(DataNotFound, lambda: sel.rex("(zz)").text())
def test_assert_exists(self):
sel = XpathSelector(self.tree).select("//ul/li")
sel.assert_exists()
sel = XpathSelector(self.tree).select("//ul/li[10]")
self.assertRaises(DataNotFound, sel.assert_exists)
def test_html(self):
sel = XpathSelector(self.tree.xpath("//h1")[0])
self.assertEquals("<h1>test</h1>", sel.html().strip())
def test_attr_default(self):
sel = XpathSelector(self.tree).select("//ul[2]/li[10]")
self.assertRaises(DataNotFound, lambda: sel.attr("class"))
self.assertEquals("DEFAULT", sel.attr("class", default="DEFAULT"))
def test_context_manager_select_text(self):
html = '<b>one</b><b>two</b>'
with XpathSelector(fromstring(html)).select('b') as elem:
self.assertEqual('one', elem.text())
def test_one(self):
sel = XpathSelector(self.tree).select("//ul/li")
self.assertEquals("SRE_Match", sel.rex("one").one().__class__.__name__)
def test_context_manager_select_iter(self):
html = '<b>one</b><b>two</b>'
with XpathSelector(fromstring(html)).select('b') as qs:
vals = [x.text() for x in qs]
self.assertEqual(set(['one', 'two']), set(vals))
def test_number(self):
sel = XpathSelector(self.tree).select("//ul/li[4]/text()")
self.assertEquals(4, sel.rex("(\d+)").number())
def test_attr(self):
sel = XpathSelector(self.tree).select('//ul[2]/li')
self.assertEquals('li-1', sel.attr('class'))
def test_selector_number_does_not_exist(self):
sel = XpathSelector(self.tree).select("//ul/li[1]").one()
self.assertEquals("DEFAULT", sel.number(default="DEFAULT"))
self.assertRaises(DataNotFound, lambda: sel.number())
def test_attr_default(self):
sel = XpathSelector(self.tree).select('//ul[2]/li[10]')
self.assertRaises(DataNotFound, lambda: sel.attr('class'))
self.assertEquals('DEFAULT', sel.attr('class', default='DEFAULT'))
def test_attr_with_default_value(self):
root = XpathSelector(self.tree)
self.assertEqual("z", root.select("//ul[2]").attr("id-xxx", default="z"))
def test_rex(self):
sel = XpathSelector(self.tree).select('//ul/li')
self.assertTrue(isinstance(sel.rex('(\w+)'), RexResultList))
def test_attr_list(self):
root = XpathSelector(self.tree)
self.assertEquals(set(["li-1", "li-2"]), set(root.select('//ul[@id="second-list"]/li').attr_list("class")))
def test_rex_default(self):
sel = XpathSelector(self.tree).select('//ul/li[10]')
self.assertRaises(DataNotFound, lambda: sel.rex('zz'))
self.assertEquals('DEFAULT', sel.rex('zz', default='DEFAULT'))
def test_text_selector_select(self):
sel = XpathSelector(self.tree).select("//li/text()").one()
self.assertRaises(SelectionRuntimeError, lambda: sel.select("foo"))
def test_node_list(self):
sel = XpathSelector(self.tree).select('//ul/li')
self.assertEquals(self.tree.xpath('//ul/li'), sel.node_list())
def test_node_default(self):
sel = XpathSelector(self.tree).select("//ul/li[10]")
self.assertRaises(DataNotFound, lambda: sel.node())
self.assertEqual("DEFAULT", sel.node(default="DEFAULT"))
def test_require(self):
XpathSelector(self.tree).select('//ul').require()
self.assertRaises(RequiredDataNotFound,
XpathSelector(self.tree).select('//foo').require)
def test_html(self):
sel = XpathSelector(self.tree).select("//ul/li")
self.assertEquals(u"<li>one</li>", sel.html().strip())
def test_one(self):
sel = XpathSelector(self.tree).select('//ul/li')
self.assertEquals('SRE_Match', sel.rex('one').one().__class__.__name__)
def test_number_default(self):
sel = XpathSelector(self.tree).select("//ul/li[10]")
self.assertRaises(DataNotFound, sel.number)
self.assertEquals("DEFAULT", sel.number(default="DEFAULT"))
def test_text(self):
sel = XpathSelector(self.tree).select('//ul/li/text()')
self.assertEquals('one', sel.rex('(\w+)').text())
def test_exists(self):
sel = XpathSelector(self.tree).select("//ul/li[4]")
self.assertEquals(True, sel.exists())
sel = XpathSelector(self.tree).select("//ul/li[5]")
self.assertEquals(False, sel.exists())
def test_text_no_default(self):
sel = XpathSelector(self.tree).select('//ul/li/text()')
self.assertRaises(DataNotFound, lambda: sel.rex('(zz)').text())
def test_attr(self):
sel = XpathSelector(self.tree).select("//ul[2]/li")
self.assertEquals("li-1", sel.attr("class"))
def test_text_default_value(self):
sel = XpathSelector(self.tree).select('//ul/li/text()')
self.assertEquals('DEFAULT', sel.rex('(zz)').text(default='DEFAULT'))
def test_rex(self):
sel = XpathSelector(self.tree).select("//ul/li")
self.assertTrue(isinstance(sel.rex("(\w+)"), RexResultList))
def test_number(self):
sel = XpathSelector(self.tree).select('//ul/li[4]/text()')
self.assertEquals(4, sel.rex('(\d+)').number())
def test_node_list(self):
sel = XpathSelector(self.tree).select("//ul/li")
self.assertEquals(self.tree.xpath("//ul/li"), sel.node_list())
def test_in_general(self):
XpathSelector(self.tree)
def test_text(self):
sel = XpathSelector(self.tree).select("//ul/li/text()")
self.assertEquals("one", sel.rex("(\w+)").text())
def test_select_node(self):
sel = XpathSelector(self.tree)
self.assertEquals('test', sel.select('//h1')[0]._node.text)
def test_text_default_value(self):
sel = XpathSelector(self.tree).select("//ul/li/text()")
self.assertEquals("DEFAULT", sel.rex("(zz)").text(default="DEFAULT"))
def test_html(self):
sel = XpathSelector(self.tree.xpath('//h1')[0])
self.assertEquals('<h1>test</h1>', sel.html().strip())
def test_select_node(self):
sel = XpathSelector(self.tree)
self.assertEquals("test", sel.select("//h1")[0]._node.text)
def test_selector_number(self):
sel = XpathSelector(self.tree)
self.assertEquals(4, sel.select('//ul/li[last()]').one().number())
self.assertEquals(6, sel.select('//ul/li[last()]/@id').one().number())
def test_selector_number(self):
sel = XpathSelector(self.tree)
self.assertEquals(4, sel.select("//ul/li[last()]").one().number())
self.assertEquals(6, sel.select("//ul/li[last()]/@id").one().number())
def test_selector_number_does_not_exist(self):
sel = XpathSelector(self.tree).select('//ul/li[1]').one()
self.assertEquals('DEFAULT', sel.number(default='DEFAULT'))
self.assertRaises(DataNotFound, lambda: sel.number())
def test_text_selector(self):
sel = XpathSelector(self.tree).select("//li/text()").one()
self.assertTrue(sel.is_text_node())
self.assertEquals("one", XpathSelector(self.tree).select("//li/text()").text())
def test_text_selector(self):
sel = XpathSelector(self.tree).select('//li/text()').one()
self.assertTrue(sel.is_text_node())
self.assertEquals(
'one',
XpathSelector(self.tree).select('//li/text()').text())
