def test_all1(self):
ext = base.Extractor(
xpath='//p/text()',
regexp=r'(\d+.+\d+)',
fn=lambda matches, r, s: math.trunc(float(matches[0][0])))
self.assertEqual(ext.extract(self.text), 3)
def test_all2(self):
ext = base.Extractor(xpath='//p[not(child::string)]/text()',
regexp=r'(\d+[^.]+).',
fn=lambda matches, r, s: matches[0])
self.assertEqual(ext.extract(self.html),
['123 Foo Road, San Jose, CA'])
def test_phone(self):
ext = base.Extractor(xpath='//strong/text()', regexp=r'\d+-\d+')
self.assertEqual(ext.extract(self.html), [['555-1234']])
def test_process(self):
ext = base.Extractor(
xpath='//li/text()',
fn=lambda matches, r, s: [self.map[m] * 3 for m in matches])
self.assertEqual(ext.extract(self.text), [3, 6, 9])
def test_address(self):
ext = base.Extractor(regexp=r'(\d+[^,]+),')
self.assertEqual(ext.extract(self.html), ['123 Foo Road'])
def test_regexp2(self):
ext = base.Extractor(regexp=r'(\d+.+\d+)')
self.assertEqual(ext.extract(self.text), ['3.14'])
def test_regexp1(self):
ext = base.Extractor(regexp=r'\'(.*)\'')
self.assertEqual(ext.extract(self.text), ['pi'])
def test_third(self):
ext = base.Extractor(xpath='//li[contains(@class,"third")]/text()')
self.assertEqual(ext.extract(self.resp), ['3'])
def test_even(self):
ext = base.Extractor(xpath='//li[contains(@class,"even")]/text()')
self.assertEqual(ext.extract(self.resp), ['2'])