def parse_product(self, response):
product = Product()
product['url'] = response.url
# NAME
name = xtract(response, "//h1/text()")
add_field(product, 'name', name)
# ITEM NUM
item_num = xtract(response, xcontains('span', 'style-number'))
add_field(product, 'item_num', item_num, lambda x: x.split('#')[-1].strip())
# PRICE
price = xtract(response, xcontains('span', 'price-current'))
if len(price) == 0:
price = xtract(response, xcontains('span', 'regular-price'))
add_field(product, 'price', price, to_float)
data_script = response.xpath("//script[contains(., 'initialData')]/text()").extract()
if len(data_script) > 0:
product['initial_data'] = transform_initial_data(data_script[0])
yield product
def test_xcontains(self):
val = xcontains('span', 'a-class')
assert val == "//span[contains(@class, 'a-class')]/text()"
val = xcontains('a', 'ddd', 'href()')
assert val == "//a[contains(@class, 'ddd')]/href()"
def test_xcontains(self):
val = xcontains('span', 'a-class')
assert val == "//span[contains(@class, 'a-class')]/text()"
val = xcontains('a', 'ddd', 'href()')
assert val == "//a[contains(@class, 'ddd')]/href()"
