def parse(self, response):
reader = csv.DictReader(StringIO(response.body))
for row in reader:
product_price = extract_price(row['SalePrice'])
if not product_price:
product_price = extract_price(row['Price'])
product_name = ' - '.join([
row['PaperType'], row['LaminationType'], row['PrintType'],
row['PaperSize'], row['FoldingType']])
product_identifier = row['ProductID']
if row['ProdRange'] != 'NULL':
product_category = row['ProductType'] + ' - ' + row['ProdRange']
else:
product_category = row['ProductType']
loader = ProductLoader(item=Product(), response=response)
loader.add_value('name', product_name)
loader.add_value('identifier', product_identifier)
loader.add_value('sku', product_identifier)
loader.add_value('price', product_price)
loader.add_value('category', product_category)
item = loader.load_item()
item['metadata'] = row.copy()
yield item
def parse_product(self, response):
base_url = get_base_url(response)
hxs = HtmlXPathSelector(response)
meta = response.meta
loader = ProductLoader(response=response, item=Product())
loader.add_xpath('identifier', '//input[@name="product"]/@value')
loader.add_xpath('sku', '//h3[@class="sku-number"]/text()')
loader.add_xpath('name', '//h1[@itemprop="name"]/text()')
price = hxs.select(
'//p[@class="special-price"]/span[@class="price"]/text()').extract(
)
if price:
price = extract_price(price[0])
else:
price = hxs.select('//span[@class="price"]/text()').extract()
if price:
price = extract_price(price[0])
else:
price = 0
loader.add_value('price', price)
loader.add_value('url', response.url)
loader.add_xpath('image_url', '//img[@id="main-image-image"]/@src')
loader.add_xpath('brand', '//a[@itemprop="brand"]/text()')
category = hxs.select(
'//div[@class="breadcrumbs"]/ul/li/a/span/text()').extract()[1]
loader.add_value('category', meta['category'])
loader.add_value('shipping_cost', 25)
sold_out = hxs.select('//button[@class="btn-cart soldout"]')
if sold_out:
loader.add_value('stock', 0)
yield loader.load_item()
def parse_dealers(self, response):
item = response.meta['item']
try:
hxs = HtmlXPathSelector(response)
dealers = hxs.select('//div[@class="product-list" and @data-condition="new"]')
except Exception:
dealers = []
if not dealers and response.meta['one_seller']:
log.msg('ERROR >>> ONE SELLER: ' + item['url'])
return
for dealer in dealers:
dealer_name = ''.join(dealer.select('.//div[@class="seller-name"]/span/text()').extract()).strip()
if dealer_name.upper() == 'BEST BUY':
log.msg('INFO >>> COLLECT BEST BUY ITEM: ' + item['url'])
out_of_stock = dealer.select('.//div[@class="cart-button" and @data-button-state-id="SOLD_OUT_ONLINE"]')
if out_of_stock:
item['stock'] = 0
price = dealer.select('.//div[@class="medium-item-price"]//text()').extract()
if not price:
log.msg('ADD TO CART PRICE >>> ' + item['url'])
price = dealer.select('@data-price').extract()
item['price'] = extract_price(price[-1])
shipping_cost = dealer.select('.//div[@class="shipping-cost-puck"]//text()').extract()
if shipping_cost:
item['shipping_cost'] = extract_price(shipping_cost[0])
break
if item['identifier']:
self.new_ids.append(item['identifier'])
yield item
def parse_product(self, response):
# inspect_response(response, self)
# return
hxs = HtmlXPathSelector(response)
loader = ProductLoader(item=Product(), response=response)
tmp = hxs.select(
'//div[@class="breadcrumbs"]/ul/li[contains(@class,"category")]/a/text()'
).extract()
if tmp:
for s in tmp:
loader.add_value('category', s)
p = loader.load_item()
product = response.meta['item']
product['category'] = p['category']
identifier = product['identifier']
tmp = hxs.select(
'//div[@class="breadcrumbs"]/ul/li[@class="product"]/strong/text()'
).extract()
if tmp:
product['name'] = tmp[0]
name = product['name']
price = hxs.select('//div[@class="price"]/span/text()').extract()
if not product['price'] and price:
product['price'] = extract_price(price[0])
options = hxs.select(
'//select[@id="simple-selection"]/option[not(@value="null")]')
if not options:
tmp = hxs.select(
'//div[@id="product-options"]//input[@id="sku-code"]/@value'
).extract()
if tmp:
product['sku'] = tmp[0]
tmp = hxs.select(
'//form[@id="product_addtocart_form"]/@action').extract()
if tmp and '/product/' in tmp[0]:
product['identifier'] = tmp[0].split('/product/',
1)[1].split('/', 1)[0]
yield product
return
for sel in options: # ##
item = copy.deepcopy(product)
tmp = sel.select('text()').extract()
if tmp:
item['name'] = name + ' - ' + tmp[0]
tmp = sel.select('@data-sku').extract()
if tmp:
item['identifier'] = identifier + '-' + tmp[0]
item['sku'] = tmp[0]
tmp = sel.select('@value').extract()
if tmp:
item['identifier'] = tmp[0]
tmp = sel.select('@data-simple-price').extract()
if tmp:
price = round(extract_price(tmp[0]), 2)
item['price'] = price
yield item
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
brand = response.meta.get('brand', '')
category = response.meta.get('category', '')
sku = hxs.select('//input[@name="product_sku"]/@value').extract().pop()
identifier = sku
name = hxs.select('//h1[@class="gf_1"]/text()').extract()
price = hxs.select('//span[@itemprop="price"]/text()').extract().pop()
price = extract_price(price)
# VAT
price_vat = extract_price(str(float(price)*1.2))
#image_url
image_url = hxs.select('//img[@id="main_image"]/@src').extract()
loader = ProductLoader(item=Product(), response=response)
loader.add_value('url', response.url)
if image_url:
loader.add_value('image_url', urljoin(response.url, image_url.pop()))
if brand:
loader.add_value('brand', brand)
if category or brand:
loader.add_value('category', category or brand)
loader.add_value('name', name)
loader.add_value('price', price_vat)
if price < 50.00:
loader.add_value('shipping_cost', '5.00')
loader.add_value('sku', sku)
loader.add_value('identifier', identifier)
#Stock
#loader.add_value('stock', stock[0].strip())
if sku not in self.ids_seen:
self.ids_seen.add(sku)
yield loader.load_item()
def parse_shipping(self, response):
shipping_cost, free_shipping_over = response.xpath(u'//span[contains(text(),"FREE ECONOMY SHIPPING FOR ORDERS OVER $65.00")]/text()')\
.re(u'\((.*?) for orders less than (.*)\)')
self.shipping_cost = extract_price(shipping_cost)
self.free_shipping_over = extract_price(free_shipping_over)
for url in self.start_urls:
yield scrapy.Request(url)
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
meta = response.meta
sku = hxs.select('//p[@class="alignright"]/text()').extract()[0].replace('[', '').replace(']', '')
category = hxs.select('//div[@class="breadcrumbs"]/ul/li/a/text()').extract()[-1]
name = response.meta.get('name')
price_box = hxs.select("//div[@itemprop='offers']//*[contains(text(),'HT')]/text()").extract()
if price_box:
price_box = ''.join(price_box[0].split())
price = re.findall(re.compile("[^0-9]*([0-9 .,]+).*"), price_box)[0].strip()
price = extract_price(price)
tax = hxs.select('//span[@class="weee"]/small/text()').extract()
tax = extract_price(tax[0]) if tax else 0
if not name:
name = hxs.select('//div[@class="product-name"]/h1[@itemprop="name"]/text()').extract()
l = ProductLoader(item=Product(), response=response)
l.add_xpath('identifier', '//form[@id="product_addtocart_form"]//input[@name="product"]/@value')
l.add_value('name', name)
l.add_value('category', category)
l.add_xpath('brand', '//div[@class="product-manufacturer"]/a/@title')
l.add_value('sku', sku)
l.add_value('url', response.url)
l.add_value('price', price + tax)
l.add_value('stock', 1)
l.add_xpath('image_url', '//p[@class="product-image"]/a/img/@src')
yield l.load_item()
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
options = hxs.select('//*[@id="buyingOptions"]/dl/dd/ul/li')
log.msg('PARSE PRODUCT')
base_product = response.meta['product']
used_items = hxs.select('.//li[contains(@id,"usedItem")]')
if options:
for option in options:
log.msg('PARSE PRODUCT OPTIONS')
product_option = Product(base_product)
full_name = ' '.join(
(base_product['name'],
''.join(option.select('div/strong/a/text()').extract())))
option_values = json.loads(
option.select(".//var/text()").extract()[0])
sku = option_values['sku']
product_option['name'] = full_name
product_option['sku'] = sku
product_option['identifier'] = sku
price = ''.join(
option.select(
'div/p/span[@class="priceVal"]/text()').extract())
if not price:
try:
price = json.loads(
option.select(
'var[contains(@class, "styleInfo")]/text()').
extract().pop())['price']
except KeyError:
return
product_option['price'] = extract_price(str(price))
if product_option['price'] > 0:
yield product_option
else:
if base_product['price'] > 0:
yield base_product
if used_items:
for used_item in used_items:
product_option = Product(base_product)
full_name = ' '.join((base_product['name'], '(Used,', ''.join(
used_item.select(
'.//p[contains(@class,"usedCondition")]/text()').
extract()), ')')).replace('\n', ' ')
sku = used_item.select('.//fieldset/a/@href').re(
'url_catalog_ref_id=(.*?)&')[0]
product_option['name'] = full_name
product_option['sku'] = sku
product_option['identifier'] = sku
price = used_item.select(
'.//p[contains(@class,"usedPrice")]/text()').extract()
price = ''.join(price).replace('\n', '')
decimal_price = used_item.select(
'.//p[contains(@class,"usedPrice")]/sup[@class="decimalPrice"]/text()'
)[0].extract()
price = '.'.join([price, decimal_price])
product_option['price'] = extract_price(str(price))
if product_option['price'] > 0:
yield product_option
def parse_product(self, response):
sku = response.meta['sku']
brands = response.meta['brands']
loader = ProductLoader(Product(), response=response)
identifier = response.xpath('//input[@name="pid"]/@value').extract()
if identifier:
product_brand = response.meta.get('product_brand', None)
if not product_brand:
product_brand = re.findall('BRAND:</b> (.*)<br><b>W',
response.body)
if product_brand:
product_brand = product_brand[0].strip()
else:
self.log('>>> ERROR: No brand found: ' + response.url)
return
product_code = response.xpath('//span[@itemprop="name"]/text()'
).re('(.*) : ')[0].strip()
if product_brand.upper(
) not in brands or product_code.upper() != sku.upper():
return
identifier = identifier[0]
name = response.xpath(
'//span[@itemprop="name"]/text()').extract()[0].strip()
price = response.xpath(
'//font[@class="selling_price"]/b/text()').extract()[0]
loader.add_value('identifier', identifier)
loader.add_value('url', response.url)
loader.add_value('name', name)
loader.add_value('price', price)
loader.add_value('url', response.url)
loader.add_value('sku', sku)
image_url = response.xpath(
'//img[@itemprop="image"]/@src').extract()
if image_url:
loader.add_value('image_url', response.urljoin(image_url[0]))
loader.add_value('brand', product_brand)
weight = response.xpath(
'//p[b[contains(text(), "Weight or Volume")]]/span/text()'
).extract()
if weight:
weight = weight[0].upper()
# convert price to grams if it is in KG
if 'KG' in weight:
weight = extract_price(weight) * 1000
else:
weight = extract_price(weight)
if weight > 1000:
loader.add_value('shipping_cost', 4.99)
else:
loader.add_value('shipping_cost', 3.50)
item = loader.load_item()
yield item
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
product_loader = ProductLoader(item=Product(), selector=hxs)
product_loader.add_value('url', response.url)
product_loader.add_xpath('name', u'//h1/text()')
product_loader.add_value('category', response.meta.get('category'))
img = hxs.select(u'//img[@id="gallery-image"]/@src').extract()
if img:
product_loader.add_value(
'image_url', urljoin_rfc(get_base_url(response), img[0]))
product_loader.add_xpath(
'brand', u'//div[@class="manufacturer-logo"]/a/img/@alt')
product = product_loader.load_item()
for opt in hxs.select(
u'//div[contains(@class,"purchase-options")]/div/form'):
prod = Product(product)
prod['name'] = prod['name'] + ' ' + opt.select(
u'.//span[@class="option"]/text()').extract()[0].strip()
prod['price'] = extract_price(
opt.select(
u'.//input[contains(@id, "-base-sale-price")]/@value').
extract()[0])
prod['sku'] = opt.select(
u'.//input[@name="product-id"]/@value').extract()[0]
prod['identifier'] = opt.select(
u'.//input[@name="product-id"]/@value').extract()[0]
opt_groups = []
for select in opt.select(
u'.//select/../../label[not(contains(text(),"Delivery"))]/../div/select'
):
opts = []
import logging
for o in select.select(
u'./option[not(contains(text(), "None"))]'):
option = ''.join(o.select('.//text()').extract())
id = o.select('./@value').extract()[0]
try:
logging.error(option)
name, price = option.split('(')
price = extract_price(price)
except:
name, price = option, 0
opts.append((price, name, id))
opt_groups.append(opts)
for opt_price, opt_name, opt_id in multiply(opt_groups):
p = Product(prod)
p['name'] = p['name'] + ' ' + opt_name
p['price'] = p['price'] + Decimal(opt_price).quantize(
Decimal('1.00'))
p['identifier'] = p[
'identifier'] + ':' + opt_id if opt_id else p[
'identifier'] + '-'
yield p
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
product_loader = ProductLoader(item=Product(), selector=hxs)
product_loader.add_value('url', response.url)
product_loader.add_xpath(
'name',
'//h1/span[@class="name-name" or @class="name-range" or @class="name-size"]/text()'
)
product_loader.add_xpath('brand',
u'//h1/a[@class="name-brand"]/text()')
product_loader.add_xpath('sku', '//meta[@name="esc-sku"]/@content')
product_loader.add_xpath(
'category',
'//div[@class="breadcrumbs"]/ul/li[position() > 1 and position() < last()-1]//a/text()'
)
img = hxs.select(
u'//div[@class="product-image-wrapper"]//img/@src').extract()
if img:
product_loader.add_value(
'image_url', urljoin_rfc(get_base_url(response), img[0]))
item = product_loader.load_item()
metadata = FragranceDirectMeta()
metadata['promotion'] = normalize_space(' '.join(
hxs.select(
'//div[@class="bubble-msg-container"]//text()').extract()))
if item.get('price'):
metadata['price_exc_vat'] = Decimal(
product['price']) / Decimal('1.2')
item['metadata'] = metadata
for opt in hxs.select(
'//table[@id="super-product-table"]//tbody/tr[not(contains(@class,"gwp"))]'
):
p = Product(item)
name = normalize_space(''.join(
opt.select('./td[2]/text()').extract()))
self.log("NAE %s" % name)
if name not in p['name']:
p['name'] = normalize_space(p['name'] + ' ' + name)
p['identifier'] = opt.select(
'normalize-space(substring-after(.//div[@class="product-code"]/text(), "#"))'
).extract()[0]
p['price'] = extract_price(''.join(
opt.select('.//span[starts-with(@id,"product-price-")]//text()'
).extract()))
if p['price'] < 30:
p['shipping_cost'] = extract_price('1.95')
p['price'] = p['price'] + p['shipping_cost']
if p['price']:
p['metadata']['price_exc_vat'] = Decimal(
p['price']) / Decimal('1.2')
p['stock'] = 'in stock' in ''.join(
opt.select('.//span[@class="stock-status-main"]/text()').
extract()) and 1 or 0
yield p
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
options = None
js_line = ''
for l in response.body.split('\n'):
if 'variants:' in l:
js_line = l
break
if js_line:
options = demjson.decode(re.search(r'variants:(.*};)?', js_line).groups()[0][:-2].strip())
product_loader = ProductLoader(item=Product(), selector=hxs)
row = response.meta['row']
sku = row['PRODUCT_NUMBER']
product_loader.add_value('sku', sku)
product_loader.add_value('identifier', sku)
product_loader.add_value('url', response.url)
name = hxs.select('//span[@itemprop="name"]/text()').extract()[0]
product_loader.add_value('name', name)
category = hxs.select('//*[@id="breadcrumb"]//a/text()').extract()[1:-1]
product_loader.add_value('category', category)
img = hxs.select('//meta[@property="og:image"]/@content').extract()
if img:
product_loader.add_value('image_url', urljoin_rfc(get_base_url(response), img.pop()))
price = hxs.select('//p[@class="productOfferPrice"]/text()').extract()[0]
price = extract_price(price)
product_loader.add_value('price', price)
brand = hxs.select('//*[@id="brandHeader"]/a/@href').extract()
if brand:
brand = brand[0].replace('/en/', '')[:-1]
product_loader.add_value('brand', brand)
stock = ''.join(hxs.select('//div[@class="cvos-availbility-panel"]/p/text()').extract())
if 'Item is currently out of stock online' in stock:
product_loader.add_value('stock', 0)
product = product_loader.load_item()
metadata = BootsMeta()
prom = ''.join(hxs.select('//div[@class="productSavings"]//text()').extract())
metadata['promotion'] = prom + ' ' + ''.join(hxs.select('//div[@class="primaryItemDeal"]//p/text()').extract())
if product['price']:
metadata['price_exc_vat'] = Decimal(product['price']) / Decimal('1.2')
product['metadata'] = metadata
yield product
if options:
for k, val in options.items():
option_name = k.replace('_', ' ')
option_product = Product(product)
option_product['name'] = product['name'] + ' ' + option_name
option_product['sku'] = val['productCode']
option_product['identifier'] = val['variantId']
option_product['price'] = extract_price(val['nowPrice'])
if option_product.get('price'):
option_product['metadata']['price_exc_vat'] = Decimal(option_product['price']) / Decimal('1.2')
yield option_product
def parse_node(self, response, node):
identifier = node.select('./*[local-name()="id"]/text()')[0].extract()
if identifier not in self.id_code_map:
return
product_code = self.id_code_map[identifier]
loader = ProductLoader(item=Product(), selector=node)
size = node.xpath('./*[local-name()="size"]/text()').extract()
color = node.xpath('./*[local-name()="color"]/text()').extract()
material = node.xpath('./*[local-name()="material"]/text()').extract()
name = node.xpath('./*[local-name()="parent_title"]/text()').extract()
if not name:
name = node.xpath('./title/text()').extract()
name = name[0]
if material:
name += u' {}'.format(material[0])
if color:
name += u' {}'.format(color[0])
if size:
name += u' {}'.format(size[0])
price = node.xpath('./*[local-name()="price"]/text()').extract_first()
pack_size = node.xpath('./description/text()').re(
'Pack Size m: *([\d.]+)')
if pack_size:
price = extract_price(price) * extract_price(pack_size[0])
loader.add_value('name', name)
loader.add_xpath('url', './link/text()')
loader.add_xpath('image_url', './*[local-name()="image_link"]/text()')
loader.add_value('identifier', identifier)
loader.add_value('price', price)
loader.add_xpath(
'shipping_cost',
'./*[local-name()="shipping"]/*[local-name()="price"]/text()')
loader.add_xpath('brand', './*[local-name()="brand"]/text()')
loader.add_xpath('category',
'./*[local-name()="google_product_category"]/text()')
loader.add_xpath('sku', './*[local-name()="mpn"]/text()')
stock = node.xpath('./*[local-name()="availability"]/text()').extract()
if stock and stock[0] == 'out of stock':
loader.add_value('stock', 0)
item = loader.load_item()
if product_code in self.cost_prices:
try:
cost_price = Decimal(self.cost_prices[product_code])
except:
self.log('ERROR: unable to set cost price for item %r' % item)
else:
item['metadata'] = {'cost_price': str(cost_price)}
if pack_size:
yield Request(loader.get_output_value('url'),
self.parse_pack_price,
meta={'item': item})
else:
yield item
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
product_loader = ProductLoader(item=Product(), selector=hxs)
product_loader.add_value('url', response.url)
product_loader.add_xpath('name', u'//h1//text()')
product_loader.add_xpath(
'category',
u'normalize-space(//a[@class="Link21" and position()=2]/text())')
product_loader.add_xpath(
'brand',
u'//a[@id="ModelsDisplayStyle4_HlkSeeAllBrandProducts"]/@title')
img = hxs.select(u'//div[@id="DivModelImage"]/a/@href').extract()
if not img:
img = hxs.select(
u'//div[@id="DivModelImage"]/a/img/@src').extract()
if img:
product_loader.add_value(
'image_url', urljoin_rfc(get_base_url(response), img[0]))
product_loader.add_xpath('brand',
u'//span[@itemprop="manufacturer"]/text()')
# product_loader.add_xpath('shipping_cost', '')
product = product_loader.load_item()
for option in hxs.select(
u'//div[@id="TabContentAddToBasketTab"]//tr[@class="BackGround15"]'
):
prod = Product(product)
prod['identifier'] = option.select(
u'normalize-space(./td[1]/text())').extract()[0]
prod['sku'] = option.select(
u'normalize-space(./td[1]/text())').extract()[0]
if option.select(u'./td[position()=1 and @colspan="4"]'):
continue
elif option.select(u'./td[4]//td[1]/text()').extract():
prod['name'] = prod['name'].strip() + ' ' + option.select(
u'normalize-space(./td[3]/a/text())').extract()[0]
prod['price'] = extract_price(
option.select(u'./td[4]//td[1]/text()').extract()[0])
elif option.select(u'./td[6]//td[1]/text()').extract():
prod['name'] = prod['name'].strip() + ' ' + option.select(
u'normalize-space(./td[4]/a/text())').extract()[0]
prod['price'] = extract_price(
option.select(u'./td[6]//td[1]/text()').extract()[0])
prod['identifier'] = option.select(
u'normalize-space(./td[2]/text())').extract()[0]
prod['sku'] = option.select(
u'normalize-space(./td[2]/text())').extract()[0]
elif option.select(u'./td[3]//td[1]/text()').extract():
prod['price'] = extract_price(
option.select(u'./td[3]//td[1]/text()').extract()[0])
else:
continue
if prod['identifier'].strip():
yield prod
def parse_product(self, response):
base_url = get_base_url(response)
hxs = HtmlXPathSelector(response)
meta = response.meta
l = ProductLoader(item=Product(), response=response)
sku = meta.get('sku') if meta.get('sku', None) else hxs.select(
'//div[@class="buy"]//select[@id="ProductItemId"]/@data-wpc'
).extract()[0]
l.add_value('sku', sku)
identifier = hxs.select(
'//input[@id="AddToBasketMain"]/@data-event-label').extract()
identifier = identifier[0] if identifier else sku
l.add_value('identifier', identifier)
brand = hxs.select(
'//div[@class="info"]/h2[@class="designer"]/a/text()').extract()[0]
name = hxs.select(
'//div[@class="info"]/h3[@class="description"]/text()').extract(
)[0].strip()
l.add_value('name', brand + ' ' + name)
brand = meta.get('brand') if meta.get('brand', None) else brand
l.add_value('brand', brand)
url = meta.get('url') if meta.get('url', None) else response.url
l.add_value('url', url)
image_url = hxs.select(
'//a[@class="zoom"]/img[@class="product-image" and contains(@src, "_1_")]/@src'
).extract()
if image_url:
l.add_value('image_url', image_url[0])
l.add_value('category', meta.get('category'))
price = hxs.select(
'//div[@class="details"]//div[@class="pricing"]/div[@class="price"]/span[@class="sale"]/text()'
).extract()
if price:
price = extract_price(price[0])
else:
price = hxs.select(
'//div[@class="details"]//div[@class="pricing"]/div[@class="price"]/text()'
).extract()
if price:
price = extract_price(price[0])
else:
price = 0
l.add_value('price', price)
l.add_value('shipping_cost', 20)
out_of_stock = hxs.select(
'//div[@class="detail-allsizesoutofstock visible"]')
if out_of_stock:
l.add_value('stock', 0)
yield l.load_item()
def parse_product(self, response):
name = ' '.join(response.xpath('//h1/text()').extract()[0].split())
identifier = response.xpath(
'//input[@id="itemsArray"]/@value').extract()[0]
sku = response.xpath('//span[@itemprop="mpn"]/text()').extract()
sku = sku[0].strip() if sku else ''
price = response.xpath('//span[@itemprop="price"]/text()').extract()
price = extract_price(price[0]) if price else '0'
brand = response.xpath(
'//dd[contains(@itemtype, "Organization")]//a/text()').extract()
brand = brand[0].strip() if brand else ''
categories = response.xpath(
'//div[@id="breadcrumb"]//a/text()').extract()[1:-1]
product_image = response.xpath(
'//img[@id="productMainImage"]/@src').extract()
loader = ProductLoader(item=Product(), response=response)
loader.add_value('identifier', identifier)
loader.add_value('sku', sku)
loader.add_value('name', name)
loader.add_value('url', response.url)
loader.add_value('price', price)
if product_image:
loader.add_value('image_url', response.urljoin(product_image[0]))
loader.add_value('brand', brand)
loader.add_value('category', categories)
stock = response.xpath(
'//span[contains(@class, "availability")]//text()').re('\d+')
if not stock:
loader.add_value('stock', 0)
else:
stock = extract_price(stock[0])
loader.add_value('stock', stock)
product = loader.load_item()
metadata = TranscatMeta()
metadata['reviews'] = []
product['metadata'] = metadata
reviews_url = "http://api.bazaarvoice.com/data/batch.json?passkey=tkfeqezs3t1ybjthb77uxbvqd&apiversion=5.5&displaycode=1015-en_us&resource.q0=reviews&filter.q0=isratingsonly%3Aeq%3Afalse&filter.q0=productid%3Aeq%3A" + identifier + "&filter.q0=contentlocale%3Aeq%3Aen_CA%2Cen_US&sort.q0=submissiontime%3Adesc&stats.q0=reviews&filteredstats.q0=reviews&include.q0=authors%2Cproducts%2Ccomments&filter_reviews.q0=contentlocale%3Aeq%3Aen_CA%2Cen_US&filter_reviewcomments.q0=contentlocale%3Aeq%3Aen_CA%2Cen_US&filter_comments.q0=contentlocale%3Aeq%3Aen_CA%2Cen_US&limit.q0=100&offset.q0=0&limit_comments.q0=3&callback=bv_1111_4827"
request = Request(reviews_url,
meta={
'product': product,
'offset': 0,
'identifier': identifier
},
callback=self.parse_reviews)
yield request
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
base_url = get_base_url(response)
for url in hxs.select(
'//div[@class="product-tile"]//a/@href').extract():
pid = url.split('_')[-1]
if pid not in self.parsed_products:
self.parsed_products.append(pid)
yield Request(urljoin_rfc(base_url, url),
callback=self.parse_product)
product_loader = ProductLoader(item=Product(), selector=hxs)
product_loader.add_value('url', response.url)
name = hxs.select('//h1/text()').extract()
if not name:
request = self.retry(response,
"No name for product: " + response.url)
if request:
yield request
return
product_loader.add_value('name', name)
category = hxs.select(
'//ol[@class="breadcrumbs"]//a/text()').extract()[1:]
product_loader.add_value('category', category)
img = hxs.select('//div[@class="item"]//img/@src').extract()
if img:
product_loader.add_value(
'image_url', urljoin_rfc(get_base_url(response), img.pop(0)))
product = product_loader.load_item()
options = hxs.select(u'//div[contains(@class, "MainProds")]/ol/li')
if not options:
options = hxs.select(
u'//div[@class="SingColl"]/div[contains(@class, "Prod")]')
if True:
if not options or len(options) == 1:
prod = Product(product)
prod['sku'] = hxs.select('//div[@class="product-sku"]/text()'
).re('Product code: (\w+)').pop()
prod['identifier'] = prod['sku']
prod['price'] = extract_price(
hxs.select('//div[@class="price-current"]/text()').extract(
).pop())
if prod['identifier']:
yield prod
else:
for opt in options:
prod = Product(product)
prod['name'] = opt.select(
u'normalize-space(.//h2/text())').extract()[0]
prod['sku'] = \
opt.select(u'normalize-space(substring-after(.//div[@class="code"]/text(), ":"))').extract()[0]
prod['identifier'] = prod['sku']
prod['price'] = extract_price(
opt.select(
u'.//span[@class="Price"]/text()').extract()[0])
yield prod
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
base_url = get_base_url(response)
product_name = hxs.select('//h1[@itemprop="name itemreviewed"]/text()').extract()
if not product_name:
return
product_name = product_name[0].strip()
image_url = hxs.select('//div[@class="product_main"]//img[@itemprop="image photo"]/@src').extract()
if not image_url:
image_url = hxs.select('//img[@itemprop="image photo"]/@src').extract()
brand = hxs.select('//a[@class="brand-link"]/img/@title').extract()
sku = hxs.select('//p[@itemprop="identifier"]/@content').extract()[0]
sku = sku.replace('sku:', '')
options_config = re.search(r'var spConfig = new Product.Config\((.*)\)', response.body)
if options_config:
product_data = json.loads(options_config.groups()[0])
products = {}
for attr in product_data['attributes'].itervalues():
for option in attr['options']:
for product in option['products']:
products[product] = ' - '.join((products.get(product, ''), option['label']))
for identifier, option_name in products.iteritems():
loader = ProductLoader(item=Product(), selector=hxs)
loader.add_value('identifier', identifier)
loader.add_value('name', product_data['childProducts'][identifier]['productName'])
if image_url:
loader.add_value('image_url', urljoin_rfc(base_url, image_url[0]))
price = extract_price(product_data['childProducts'][identifier]['price'])
price = price * self.exchange_rate * Decimal(1.2) + 100
loader.add_value('price', price)
loader.add_value('url', response.url)
loader.add_value('category', response.meta.get('category', ''))
if brand:
loader.add_value('brand', brand[0])
loader.add_value('sku', sku)
yield loader.load_item()
else:
loader = ProductLoader(item=Product(), selector=hxs)
loader.add_value('url', response.url)
loader.add_value('name', product_name)
if brand:
loader.add_value('brand', brand[0])
if image_url:
loader.add_value('image_url', urljoin_rfc(base_url, image_url[0]))
price = hxs.select('//div[@class="price-box"]//span[@class="price"]/text()').extract()
if price:
price = extract_price(price[0].replace(',', ''))
price = price * self.exchange_rate * Decimal(1.2) + 100
else:
price = 0
loader.add_value('price', price)
loader.add_value('category', response.meta.get('category', ''))
loader.add_value('sku', sku)
identifier = hxs.select('//div[@class="no-display"]//input[@name="product"]/@value').extract()[0]
loader.add_value('identifier', identifier)
yield loader.load_item()
def parse(self, response):
transport = paramiko.Transport((CLIENTS_SFTP_HOST, CLIENTS_SFTP_PORT))
password = "******"
username = "******"
transport.connect(username = username, password = password)
sftp = paramiko.SFTPClient.from_transport(transport)
files = sftp.listdir_attr()
last = get_last_file(self.file_start_with, files)
sftp.get(last.filename, self.xls_file_path)
# Convert XLXS file to CSV
excel_to_csv(self.xls_file_path, self.csv_file_path)
with open(self.csv_file_path) as f:
reader = csv.DictReader(f, delimiter=',')
for row in reader:
if row['BI ProductID'].lower() in self.identifiers:
continue
self.identifiers.append(row['BI ProductID'].lower())
loader = ProductLoader(response=response, item=Product())
loader.add_value('identifier', row['BI ProductID'])
loader.add_value('sku', row['BI ProductID'])
loader.add_value('category', unicode(row['BI Product Grp'], errors='ignore'))
loader.add_value('category', unicode(row['BI CategoryGroup'], errors='ignore'))
loader.add_value('name', unicode(row['BI ProductName'], errors='ignore'))
loader.add_value('price', extract_price(row['BI ListPrice']))
loader.add_value('shipping_cost', extract_price(row['BI Shipping']))
loader.add_value('brand', unicode(row['BI Brand'], errors='ignore'))
loader.add_value('url', '')
if self.image_url_key:
image_url = row.get(self.image_url_key)
if image_url.lower() != 'na':
loader.add_value('image_url', image_url)
else:
loader.add_value('image_url', '')
product = loader.load_item()
metadata = BIWordlwideMeta()
metadata['dropship_fee'] = unicode(row['BI Dropship Fee'], errors='ignore')
metadata['est_tax'] = unicode(row['BI Est Tax'], errors='ignore')
metadata['ship_weight'] = unicode(row['BI ship Wt'], errors='ignore')
metadata['product_group'] = unicode(row['BI Product Grp'], errors='ignore')
metadata['upc'] = unicode(row['BI UPC #'], errors='ignore')
metadata['mpn'] = unicode(row['BI Model'], errors='ignore')
metadata['item_group'] = unicode(row.get('BI ItemGroup', ''), errors='ignore')
for meta_key, feed_key in self.tag_keys.items():
tag = unicode(row.get(feed_key, ''), errors='ignore')
tag = tag if tag != u'NA' else u'N/A'
metadata[meta_key] = tag
product['metadata'] = metadata
yield product
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
product_loader = ProductLoader(item=Product(), selector=hxs)
product_loader.add_value('url', response.url)
product_loader.add_xpath('name', u'//h1[1]/text()')
price = ''.join(
hxs.select(
u'//div/span[position()=2 and contains(text(),"VAT") and contains(text(),"ex.")]/../span[1]//text()'
).extract())
product_loader.add_value('price', extract_price(price))
product_loader.add_xpath(
'sku',
u'substring-after(//div[contains(text(),"Product Code:")]/text(), ":")'
)
product_loader.add_xpath(
'category',
u'//span[@class="breadcrumblink" and position()=3]/a/text()')
img = hxs.select(
u'//a[starts-with(@id,"img") and contains(@class,"mainImageParent")]/@href'
).extract()
if not img:
img = hxs.select(
u'//div[contains(@class,"proPicHolder")]/a/img/@src').extract(
)
product_loader.add_value('image_url',
urljoin_rfc(get_base_url(response), img[0]))
js = ''.join(hxs.select(u'//script/text()').extract())
brand = re.search(u's.prop3=Trim\("(.+)"\);', js)
if brand:
product_loader.add_value('brand', brand.group(1))
# product_loader.add_xpath('shipping_cost', '')
product = product_loader.load_item()
if not product['price'] and not product['sku']:
rows = hxs.select(
u'//table/tbody/tr[@id="rangeHeader"]/../tr[position()!=1 and position()!=last()]'
)
for i, row in enumerate(rows):
if row.select(u'./td[2]/a/@href'):
# Comparison table with links to products
break
p = Product(product)
p['name'] = p['name'] + ' ' + row.select(
u'../tr[1]//table//tr[%d]/td/div/text()' %
(i + 2)).extract()[0]
p['sku'] = row.select(u'./td[2]/text()').extract()[0]
#p['price'] = extract_price(row.select(u'./td/div[@id="priceExcVAT1"]/text()').extract()[0])
p['price'] = extract_price(
row.select(u'./td/div/div[2]/text()').extract()[0])
yield p
else:
yield product
def parse_size(self, response):
item = response.meta['item']
data = json.loads(response.body)
item['price'] = extract_price(data['discount_price_promotion_display'])
yield item
if data['with_lens_price']:
item['price'] = extract_price(data['with_lens_price'])
item['identifier'] += '-with_lens'
item['name'] += ' with lenses'
yield item
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
base_url = get_base_url(response)
name = hxs.select('//h1//span[@itemprop="name"]/text()').extract()[0]
brand = hxs.select('//h1//span[@itemprop="brand"]/text()').extract()
brand = brand[0].strip() if brand else ''
if brand.upper() in self.ignore_brands:
return
image_url = hxs.select(
'//div[@class="productimg_container"]/a/img/@src').extract()
identifier = hxs.select(
'//*[@id="basketform"]//input[@name="product_id"]/@value').extract(
)
if not identifier:
identifier = hxs.select('//span[@itemprop="sku"]/text()').extract()
identifier = identifier[0]
price = response.css('.product_price #exvatprice ::text').extract()
if not price:
price = response.xpath(
'//span[@itemprop="price"]/text()').extract()
if not price:
self.log('Warning: no price found! %s' % response.url)
return
price = extract_price(price[0])
loader = ProductLoader(item=Product(), response=response)
loader.add_value('price', price)
stock = hxs.select(
'//span[@class="stockstatus"]/span[@class="stock" and contains(text(), "In Stock")]'
)
if not stock:
loader.add_value('stock', 0)
loader.add_value('identifier', identifier)
loader.add_value('name', name)
categories = hxs.select(
'//div[@itemprop="breadcrumb"]//a/text()').extract()
loader.add_value('category', categories)
loader.add_value('brand', brand)
loader.add_xpath('sku', '//td[@itemprop="mpn"]/text()')
loader.add_value('url', response.url)
if image_url:
loader.add_value('image_url', urljoin_rfc(base_url, image_url[0]))
shipping = hxs.select(
'//div[@class="delivery_text"]/strong/text()').extract()
if shipping:
if shipping[0] == 'FREE':
loader.add_value('shipping_cost', 0)
else:
loader.add_value('shipping_cost', extract_price(shipping[0]))
yield loader.load_item()
def parse_shipping_price2(response):
hxs = HtmlXPathSelector(response)
product = response.meta['product']
shipping = hxs.select('//tr[@class="ordershipping"]/td[2]/span/text()').extract()
if shipping:
shipping = extract_price(shipping[0])
shipping_discount = hxs.select('//tr[@class="ordershippingdiscount discount"]/td[2]/span/text()').extract()
if shipping_discount:
shipping -= extract_price(shipping_discount[0])
product['shipping_cost'] = shipping
yield product
def parse_product(self, response):
base_url = get_base_url(response)
hxs = HtmlXPathSelector(response)
name = hxs.select('//*[@id="Pbox"]/nav[1]/a[3]/text()').extract()[0]
brand = ''
for b in self.brands:
if name.upper().startswith(b.upper()):
brand = b
break
identifier = re.findall('roduct.ia\/(\d+)\/', response.url)[0]
image_url = hxs.select('//*[@id="thumbnail"]//li/a/@href').extract()
image_url = urljoin_rfc(base_url, image_url[0]) if image_url else ''
category = response.meta.get('categories')
products = hxs.select(
'//*[@id="priceBox"]/form/table/tr[position()>1]')
for product in products:
item = Product()
list_price = extract_price(
product.select(
'./td[2]/span[@class="tGrey"]/text()').extract()[0])
metadata = CRCMeta()
metadata['rrp'] = list_price
item['metadata'] = metadata
loader = ProductLoader(item=item, selector=product)
option_name = product.select(
'./td/b[@class="name"]/text()').extract()[0]
loader.add_value('name', name + ', ' + option_name)
loader.add_value('brand', brand)
loader.add_value('url', response.url)
loader.add_value('category', category)
loader.add_value('image_url', image_url)
option_id = product.select('./td/div/button/@onclick').extract()[0]
if 'proEmailMe' in option_id:
option_id = option_id.split('proEmailMe(')[1].split(
')')[0].replace("'", '').split(',')
else:
option_id = option_id.split('shopCartAdd(')[1].split(
')')[0].replace("'", '').split(',')
option_id = option_id[0].strip() + '_' + option_id[1].strip()
loader.add_value('identifier', identifier + '_' + option_id)
price = product.select('./td[2]/b/text()').extract()
price = extract_price(price[0])
loader.add_value('price', price)
sku = product.select('./td[1]/div/text()').extract()
sku = sku[0] if sku else ''
loader.add_value('sku', sku)
stock = product.select(
'./td[1]/span[@class="tGrey"]/text()').extract()[0]
if stock != 'In Stock':
loader.add_value('stock', 0)
yield loader.load_item()
def parse(self, response):
transport = paramiko.Transport((CLIENTS_SFTP_HOST, CLIENTS_SFTP_PORT))
password = "******"
username = "******"
transport.connect(username=username, password=password)
sftp = paramiko.SFTPClient.from_transport(transport)
file_path = HERE + '/Lakeland_products.csv'
sftp.get('Lakeland.csv', file_path)
with open(file_path) as f:
reader = csv.DictReader((line.replace('\x00', '') for line in f),
delimiter="|")
for row in reader:
loader = ProductLoader(item=Product(), response=response)
loader.add_value('sku', row['Unique Product Code'])
loader.add_value('identifier', row['Unique Product Code'])
loader.add_value('name', row['Product Name'])
loader.add_value('category', row['Category'])
loader.add_value('image_url', row['Image URL'])
loader.add_value('brand', row['Brand'].decode('latin-1'))
loader.add_value('url', row['Product Page URL'])
list_price = str(round(extract_price(row['List Price']), 2))
cost_price = str(round(extract_price(row['Cost Price']), 2))
rrp = str(round(extract_price(row['RRP']), 2))
selling_price = round(extract_price(row['Price']), 2)
if selling_price > 0:
margin = (
(Decimal(rrp) / Decimal('1.2') - Decimal(cost_price)) /
Decimal(selling_price)) * Decimal('1.2')
else:
margin = Decimal('0.00')
margin *= Decimal('100')
margin = '{}%'.format(str(round(extract_price(str(margin)),
2)))
loader.add_value('price', selling_price)
loader.add_value('stock', row['Stock Availability'])
loader.add_value('shipping_cost', row['Shipping Cost'])
item = loader.load_item()
metadata = LakelandMeta()
metadata['margin'] = margin
metadata['promotional_message'] = row['Promotional Message']
metadata['buyer_name'] = row['Buyer Name']
metadata['list_price'] = list_price
metadata['cost_price'] = cost_price
metadata['asin'] = row['ASIN']
metadata['dd'] = 'Yes' if row['DD'] == '1' else ''
metadata['rrp'] = rrp
item['metadata'] = metadata
yield item
def parse_product(self, response):
loader = ProductLoader(item=Product(), response=response)
name = response.xpath('//h1[@itemprop="name"]/text()').extract()
if name:
name = name[0].strip()
else:
retry_count = response.meta.get('retry_count', 0)
if retry_count < 3:
yield Request(response.url,
dont_filter=True,
callback=self.parse_product,
meta={'retry_count': retry_count + 1})
else:
self.log('Product without name: ' + response.url)
return
loader.add_value('url', response.url)
loader.add_value('name', name)
loader.add_value('brand', response.meta.get('brand'))
image_url = response.xpath('//img[@itemprop="image"]/@src').extract()
if image_url:
image_url = response.urljoin(image_url[0])
loader.add_value('image_url', image_url)
available = ''.join(response.xpath('//div[@itemprop="offers"]//div[contains(@class,"tr-prod-availability")]//text()')
.extract())\
.strip().upper()
if available:
if 'AVAILABLE IMMEDIATELY' not in available.upper():
loader.add_value('stock', 0)
price = response.xpath(
'//*[@itemprop="price"]/following-sibling::span/text()').extract()
euro_price = response.xpath(
'//*[@itemprop="price"]/text()').extract_first()
price = extract_price(price[0]) if price else 0
euro_price = extract_price(euro_price) if euro_price else 0
loader.add_value('price', price)
category = response.xpath(
'//ul[@class="tr-sidebar-categories-main"]/li/a/text()').extract()
if category:
loader.add_value('category', category[0])
sku = response.xpath('//input[@name="ar"]/@value').extract()
sku = sku[0] if sku else ''
loader.add_value('sku', sku)
loader.add_value('identifier', sku)
if int(price) <= 165:
loader.add_value('shipping_cost', 8.3)
item = loader.load_item()
item['metadata'] = {'Euro Price': euro_price}
yield item
def parse(self, response):
transport = paramiko.Transport((CLIENTS_SFTP_HOST, CLIENTS_SFTP_PORT))
password = "******"
username = "******"
transport.connect(username=username, password=password)
sftp = paramiko.SFTPClient.from_transport(transport)
files = sftp.listdir_attr()
last = get_last_file("BI UK File", files)
file_path = HERE + '/biwuk_products.csv'
sftp.get(last.filename, file_path)
with open(file_path) as f:
reader = csv.DictReader(f, delimiter=',')
for row in reader:
loader = ProductLoader(response=response, item=Product())
loader.add_value('identifier', row['BI UK ProductID'])
loader.add_value('sku', row['BI UK ProductID'])
categories = unicode(row.get('BI UK CategoryGroup'),
errors='ignore').replace(
'>>', '>').replace("'", "").split('>')
for category in categories:
loader.add_value('category', category.strip())
loader.add_value(
'name', unicode(row['BI UK ProductName'], errors='ignore'))
loader.add_value('price',
extract_price(row['BI UK Delivered Price']))
loader.add_value('shipping_cost',
extract_price(row['BI UK Shipping']))
loader.add_value('brand', row['BI UK Brand'])
loader.add_value('url', '')
loader.add_value('image_url', row['BI UK ImgURL'])
product = loader.load_item()
metadata = BIWordlwideMeta()
metadata['dropship_fee'] = unicode(row['BI UK Dropship Fee'],
errors='ignore')
metadata['est_tax'] = unicode(row['BI UK Est Tax'],
errors='ignore')
metadata['ship_weight'] = unicode(row['BI UK ship Wt'],
errors='ignore')
metadata['product_group'] = unicode(row['BI UK Product Grp'],
errors='ignore')
metadata['upc'] = unicode(row['BI UK UPC #'], errors='ignore')
metadata['mpn'] = unicode(row['BI UK Model'], errors='ignore')
product['metadata'] = metadata
yield product
def parse_product(self, response):
base_url = get_base_url(response)
hxs = HtmlXPathSelector(response)
loader = ProductLoader(item=Product(), selector=hxs)
name = hxs.select('//span[@itemprop="name"]/text()').extract()[0].strip()
loader.add_value('name', name)
identifier = hxs.select('//div[@id="article_cont"]//div[@class="itemcostinfo"]/@itemid').extract()[0]
loader.add_value('identifier', identifier)
sku = response.meta.get('sku', '')
if sku:
loader.add_value('sku', sku)
loader.add_value('brand', response.meta.get('brand', ''))
else:
sku = hxs.select('//span[@id="hbNrDataSheet"]/text()').extract()
if sku:
loader.add_value('sku', sku[0])
loader.add_value('brand', 'Logitech')
loader.add_value('url', response.url)
image_url = hxs.select('//ul[@id="gliderSmall"]/li/a/@onclick').extract()
if image_url:
match = re.search(r"imgSrc: '(.*?)',", image_url[0])
if match:
image_url = match.group(1)
loader.add_value('image_url', urljoin_rfc(base_url, image_url))
else:
image_url = hxs.select('//img[@id="itemDetail{}"]/@src'.format(identifier)).extract()
if image_url:
loader.add_value('image_url', urljoin_rfc(base_url, image_url[0]))
price = hxs.select('//meta[@itemprop="price"]/@content').extract()
price = extract_price(price[0])
loader.add_value('price', price)
in_stock = hxs.select('//meta[@itemprop="availability"]/@content').extract()[0].strip()
if in_stock == 'out_of_stock':
loader.add_value('stock', 0)
category = hxs.select('//*[@id="main-centercontainer"]/div[1]/a[3]/text()').extract()
if category:
loader.add_value('category', category[0])
shipping = '0.0'
shipping_base = hxs.select('//div[@class="clear fl b8"]/span[@class="basis fl"]/text()').extract()
if shipping_base:
shipping = shipping_base[0].replace(',', '')
shipping_decimal = hxs.select('//div[@class="clear fl b8"]/span[@class="decimal fl"]/text()').extract()
if shipping_decimal:
shipping += '.' + shipping_decimal[0]
loader.add_value('shipping_cost', extract_price(shipping))
yield loader.load_item()
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
base_url = get_base_url(response)
product = response.meta['product']
forms = hxs.select('//form[contains(@action, "BuyPrintNGo")]')
image_url = hxs.select(
'//div[@id="imagegallerymain"]/div//img/@src').extract()
if image_url:
product['image_url'] = urljoin_rfc(base_url, image_url[0])
summary = ' '.join(
map(unicode.strip,
hxs.select('//*[@id="summary"]//text()').extract())).strip()
if not summary:
summary = ''.join(
map(
unicode.strip,
hxs.select(
'//div[@id="accordion"]//div[contains(@class, "panel-heading") and contains(h4/a/text(), "Summary")]/following-sibling::div//div[contains(@class, "panel-body")]/p/text()'
).extract())).strip()
if not summary:
summary = ''.join(
map(
unicode.strip,
hxs.select(
'//div[@id="accordion"]//div[contains(@class, "panel-heading") and contains(h4/a/text(), "Summary")]/following-sibling::div//div[contains(@class, "panel-body")]//text()'
).extract())).strip()
if not summary:
summary = ''.join(
hxs.select(
'//*[@id="fine_print"]//*[@class="info_section"]//text()').
extract()).strip()
if 'metadata' in product:
product['metadata']['summary'] = summary
else:
metadata = {}
metadata['summary'] = summary
product['metadata'] = metadata
if not forms:
yield product
else:
for form in forms:
identifier = form.select(
'.//input[@name="productCode"]/@value').extract().pop()
if product['identifier'] != identifier:
continue
for line in form.select('.//table/tr'):
item = deepcopy(product)
title = line.select('./td[@class="name"]/text()').extract()
variant_id = line.select(
'.//input[contains(@name, "hdnVariantName_")]/@value'
).extract()
price = line.select(
'.//input[contains(@name, "RP_")]/@value').extract()
if title and variant_id and price:
item = deepcopy(product)
item['name'] = "%s - %s" % (item['name'], title[0])
item['identifier'] = "%s-%s" % (identifier,
variant_id[0])
item['price'] = extract_price(price[0])
yield item
def _parse_product_el(self, product_el, base_url):
name = product_el.select(
'a/div[@class="prd_details"]/h2/text()').extract()[0].strip()
price = product_el.select(
'a/div[@class="prd_details"]/div[@class="prd_price_area"]/span/text()'
).extract()[0].strip()
price = extract_price(price)
url = product_el.select("a/@href").extract()[0]
product_code = extract_product_code_from_url(url).lower()
image_url = product_el.select(
'a/span[@class="prd_img"]/img/@data-original').extract()[0]
loader = ProductLoader(selector=product_el, item=Product())
loader.add_value('identifier', product_code)
loader.add_value('sku', product_code)
loader.add_value('name', name)
loader.add_value('price', price)
loader.add_value('url', url)
if image_url:
loader.add_value('image_url', urljoin_rfc(base_url, image_url))
category = category_codes.get(product_code[0:3])
loader.add_value('category', category)
metadata = BuyAGiftMeta()
if product_code in self.suppliers:
supplier_list = self.suppliers[product_code]['suppliers']
metadata['supplier_name'] = ', '.join(supplier_list)
product = loader.load_item()
product['metadata'] = metadata
self.collected.add(product_code)
return product
def parse_product_clearance(self, response):
URL_BASE = get_base_url(response)
hxs = HtmlXPathSelector(response)
name = hxs.select("//div[contains(@class, 'prodDetails')]/h2/text()").extract()
if not name:
logging.error("ERROR!! NO NAME PRODUCT PAGE!! %s" % (response.url, ))
return
name = " ".join([x.strip() for x in name])
url = response.url
price = hxs.select("//div[@class='pricing']/h4/text()").extract()
if not price:
logging.error("ERROR!! NO PRICE PRODUCT PAGE!! %s %s" % (response.url, name))
return
price = extract_price(price[0].strip())
if not price:
logging.error("ERROR!! NO PRICE PRODUCT PAGE!! %s %s" % (response.url, name))
return
product = Product()
loader = ProductLoader(item=product, response=response)
loader.add_value('url', url)
loader.add_value('name', name)
loader.add_value('price', price)
yield loader.load_item()
def parse_options(self, response):
loader = response.meta['loader']
seen = []
url = loader.get_output_value('url')
main_name = loader.get_output_value('name')
options_data = json.loads(response.body)
base_price = extract_price(str(options_data['startingPrice']))
if base_price:
p = ProductLoader(response=response, item=Product())
p.add_value('url', url)
p.add_value('name', main_name)
p.add_value('price', base_price)
yield p.load_item()
for option in options_data['options']:
for value in option['values']:
if value.get('cost') and not value['description'] in seen:
seen.append(value['description'])
p = ProductLoader(response=response, item=Product())
p.add_value('url', url)
p.add_value('name', main_name + ' ' + value['description'])
p.add_value('price', base_price + extract_price(str(value['cost'])))
yield p.load_item()
def parse_product(self, response):
hxs = HtmlXPathSelector(response)
main_name = hxs.select('//h1[@itemprop="name"]/text()').extract()[0].strip()
main_price = hxs.select('//span[@itemprop="price"]/text()').extract()
if not main_price:
main_price = hxs.select('//input[@name="ppi"]/@value').extract()
main_price = extract_price(main_price[0])
loader = ProductLoader(response=response, item=Product())
loader.add_value('name', main_name)
loader.add_value('price', main_price)
loader.add_value('url', response.url)
loader.add_xpath('sku', '//span[@itemprop="identifier"]/text()')
yield loader.load_item()
def _add_options(option_sets, current_name, current_price):
if not option_sets and current_price > main_price:
loader = ProductLoader(response=response, item=Product())
loader.add_value('url', response.url)
loader.add_value('name', current_name)
loader.add_value('price', current_price)
yield loader.load_item()
else:
options = option_sets[0]
option_sets = option_sets[1:]
for option in options.select('./option/text()').extract():
r = re.search('(.*)\(Add(.*)\)', option)
name = current_name
price = current_price
if r:
name += ' ' + r.groups()[0].strip()
price += extract_price(r.groups()[1])
else:
name += ' ' + option
for product in _add_options(option_sets, name, price):
yield product
option_sets = hxs.select('//div[@class="inn"]/select')
if option_sets:
for product in _add_options(option_sets, main_name, main_price):
yield product
def _add_options(option_sets, current_name, current_price):
if not option_sets and current_price > main_price:
loader = ProductLoader(response=response, item=Product())
loader.add_value('url', response.url)
loader.add_value('name', current_name)
loader.add_value('price', current_price)
yield loader.load_item()
else:
options = option_sets[0]
option_sets = option_sets[1:]
for option in options.select('./option/text()').extract():
r = re.search('(.*)\(Add(.*)\)', option)
name = current_name
price = current_price
if r:
name += ' ' + r.groups()[0].strip()
price += extract_price(r.groups()[1])
else:
name += ' ' + option
for product in _add_options(option_sets, name, price):
yield product