def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'vitamina'
item['breadcrumb'] = []
item['title'] = sel.xpath('.//h1[@id="nombreProducto"]/text()').extract()[0]
description = html_text_normalize(sel.xpath('.//p[@itemprop="description"]/text()').extract())
item['description'] = description
item['code'] = ''
price = sel.xpath('.//section[@id="datos"]//p[@class="special-price"]/span[@itemprop="price" and @class="price"]/@content').extract()
if len(price) > 0:
price = price[0]
else:
price = sel.xpath('.//span[@itemprop="price"]/@content').extract()[0]
item['price'] = price_normalize(price)
sizes = sel.xpath('.//li[@class="swatchContainer"]/div[@class="swatch"]/text()').extract()
item['sizes'] = sizes
item['image_urls'] = sel.xpath('.//div[@class="fotozoom"]/img[@class="zoomImg"]/@src').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'ladystork'
title = html_text_normalize(sel.xpath('.//div[@class="p-title-group"]/h2/text()').extract()[0])
item['title'] = title
item['breadcrumb'] = sel.xpath('.//ol/li/a/text()').extract()[2:]
item['description'] = html_text_normalize(sel.xpath('.//div[@id="ctl00_HTMLContent_pnlDesc"]/div/p/text()').extract())
item['code'] = None
price = price_normalize(sel.xpath('.//strong[@class="p-price"]/text()').extract()[0])
item['price'] = price
sizes = sel.xpath('.//ul[@class="p-size-list"]/li[@class!="disabled"]/a/text()').extract()
item['sizes'] = sizes
item['other'] = None
img_urls = sel.xpath('.//div[@class="slick p-thumbs-photo"]/div/img/@src').extract()
item['image_urls'] = img_urls
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
# wait for sizes and color data to load
sizes_path = './/div[@role="option"]/text()'
self.is_visible(sizes_path, timeout=2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'prune'
item['breadcrumb'] = sel.xpath('.//title/text()').extract()[0].split(' ', 1)[0]
item['title'] = sel.xpath('.//div[@class="page-title-wrapper product"]/h1/span/text()').extract()[0]
sizes = sel.xpath(sizes_path).extract()
item['sizes'] = sizes
item['color'] = sel.xpath('.//div[@class="swatch-option color selected"]/@aria-label').extract()
description = sel.xpath('.//div[@class="product attribute description"]/div/ul').extract()
item['description'] = html_text_normalize(description)
item['code'] = sel.xpath('.//div[@itemprop="sku"]/text()').extract()[0]
price_str = sel.xpath('.//span[@class="price"]/text()').extract()[0]
item['price'] = price_normalize(price_str)
item['other'] = None
item['image_urls'] = sel.xpath('.//img[@class="img-responsive"]/@src').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'justaosadia'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//span[@class="name"]/text()').extract()[0]
description = html_text_normalize(
sel.xpath('.//span[@class="desc"]//text()').extract())
description += ' ' + html_text_normalize(
sel.xpath('.//ul[@class="detail-list"]/li//text()').extract())
item['description'] = description
item['code'] = sel.xpath(
'.//span[@class="code"]/text()').extract()[0]
item['price'] = price_normalize(
sel.xpath(
'.//span[@class="price"]/span[@itemprop="price"]/@content'
).extract()[0])
sizes = sel.xpath('.//ul[@class="sizes-list"]/li/@title').extract()
item['sizes'] = sizes
item['image_urls'] = sel.xpath(
'.//ul[@class="thumbs"]/li/a/@href').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'dos61'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//h1[@itemprop="name"]/text()').extract()[0]
description = html_text_normalize(
sel.xpath('.//div[@class="content"]//text()').extract())
item['description'] = description
item['code'] = ''
price = sel.xpath(
'.//p[@class="price"]//span[@class="woocommerce-Price-amount amount"]/text()'
).extract()
if len(price) > 1:
price = price[len(price) - 1]
else:
price = price[0]
item['price'] = price_normalize(price)
item['sizes'] = sel.xpath(
'.//div[@data-attribute="pa_talle"]/span[contains(@class, "ivpa_instock")]/@data-term'
).extract()
item['image_urls'] = sel.xpath(
'.//a[@data-slide-index]/img/@src').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(1)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'batistella'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//h1[@itemprop="name"]/text()').extract()[0]
description = html_text_normalize(
sel.xpath('.//div[@class="column push-1-16 col-10-12"]/p/text()').extract() + \
sel.xpath('.//table[@class="table-right"]//text()').extract()
)
item['description'] = description
item['code'] = sel.xpath(
'.//span[@itemprop="sku"]/text()').extract()[0]
item['price'] = price_normalize(
sel.xpath('.//span[@itemprop="price"]/text()').extract()[0])
sizes = sel.xpath(
'.//select[@class="form-control attribute_select"]/option[@value!=0]/text()'
).extract()
item['sizes'] = sizes_normalize(sizes)
item['image_urls'] = sel.xpath(
'.//img[@data-src]/@data-src').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'margiefranzini'
item['breadcrumb'] = []
title = sel.xpath('.//h1[@class="title border"]/text()').extract()[0]
item['title'] = title.replace(' Margie Franzini Shoes ',
' ').replace(' Margie Franzini ', ' ')
item['description'] = html_text_normalize(
sel.xpath('.//article[@id="tabDescription"]/p/text()').extract())
item['code'] = ''
price = sel.xpath(
'.//dl[@class="priceInfo clearfix promotionPrice"]//span[@class="ch-price price"]/text()'
).extract()
if len(price) == 0:
price = sel.xpath(
'.//span[@class="ch-price price"]/text()').extract()[0]
else:
price = price[0]
item['price'] = price_normalize(price)
sizes = sel.xpath(
'.//menu/li/span[not(contains(text(),"Talle"))]/text()').extract()
if len(sizes) == 0:
sizes = sel.xpath(
'.//span[@data-idx="1" and contains(text(),"Talle")]/text()'
).extract()
item['sizes'] = sizes_normalize(sizes)
img_urls = sel.xpath('.//li[@role="listitem"]/img/@src').extract()
item['image_urls'] = [url[2:] for url in img_urls]
yield item
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'lazaro'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//div[@class="product-main-info text-center"]//h1/text()'
).extract()[0]
item['description'] = html_text_normalize(
sel.xpath('.//div[@id="collapseOne"]/div/text()').extract())
item['code'] = sel.xpath(
'.//div[@class="sku"]/text()').extract()[0].replace(
'SKU# ', '')
item['price'] = price_normalize(
sel.xpath('.//span[@class="price"]/text()').extract()[0])
sizes = sel.xpath(
'.//div[@class="amconf-images-container switcher-field"]//label[not(contains(@class,"no-stock"))]/text()'
).extract()
item['sizes'] = sizes
item['image_urls'] = sel.xpath(
'.//div[@id="gallery_01"]//li/a/@data-image').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'johnlcook'
item['breadcrumb'] = None
item['title'] = sel.xpath('.//h2[@class="name"]/text()').extract()[0]
item['description'] = sel.xpath(
'.//div[@id="descripcion"]/child::text()').extract()[-1]
item['code'] = sel.xpath(
'.//h2[@class="name"]/following-sibling::p/text()').extract(
)[0][8:]
item['price'] = sel.xpath(
'.//span[@class="price"]/text()').extract()[0]
sizes = sel.xpath(
'.//ul[@id="ul-attribute257"]//li//div/@title').extract()
availability = sel.xpath(
'.//ul[@id="ul-attribute257"]//li//div/@class').extract()
available_sizes = list()
for i in range(len(sizes)):
if not str(availability[i]) == 'swatch disabledSwatch':
available_sizes.append(str(sizes[i]))
item['sizes'] = available_sizes
item['other'] = None
item['image_urls'] = sel.xpath(
'.//li[contains(@class,"moreview")]/child::node()/child::node()/@src'
).extract()
yield item
def parse_item(self, response):
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(5)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'mishka'
item['breadcrumb'] = []
title = sel.xpath('.//span[@itemprop="name"]/text()').extract()
item['title'] = html_text_normalize(title)
item['description'] = html_text_normalize(sel.xpath('.//div[@class="product attribute description"]/div/text()') \
.extract())
item['code'] = sel.xpath('.//div[@itemprop="sku"]/text()').extract()[0]
price = sel.xpath(
'.//span[contains(@id,"product-price")]/span/text()').extract()[0]
item['price'] = price_normalize(price)
sizes = sel.xpath('.//div[@class="swatch-attribute size"]/div[@class="swatch-attribute-options clearfix"]/div/text()') \
.extract()
item['sizes'] = sizes_normalize(sizes)
img_urls_prefix = sel.xpath('.//img[contains(@src, "https://www.mishka.com.ar/media/catalog/product/cache/") and not(contains(@src, "thumb"))]/@src') \
.extract()[0][:-5]
thumbnails = len(
sel.xpath('.//img[contains(@src, "thumb")]/@src').extract())
img_urls = list()
for thumb in range(thumbnails):
img_url = img_urls_prefix + str(thumb) + '.jpg'
img_urls.append(img_url)
item['image_urls'] = img_urls
yield item
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.get_with_short_wait(10, response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'sofimartire'
title = sel.xpath(
'.//div[@class="product-main-info"]//h1/text()').extract()[0]
item['breadcrumb'] = [title.split(' ', 1)[0]]
item['title'] = title
item['description'] = html_text_normalize(
sel.xpath('.//div[@id="collapseOne"]/div/text()').extract())
item['code'] = sel.xpath(
'.//div[@class="sku"]/text()').extract()[0]
item['price'] = price_normalize(
sel.xpath(
'.//div[@class="product-main-info"]//span[@class="price"]/text()'
).extract()[0])
sizes = sel.xpath(
'.//label[@class="amconf-color-container amconf-noimage-div"]/text()'
).extract()
item['sizes'] = sizes
item['other'] = None
item['image_urls'] = sel.xpath(
'.//a[contains(@data-image,"product/cache")]/@data-zoom-image'
).extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'cestfini'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//h1[@itemprop="name"]/text()').extract()[0]
description = sel.xpath(
'.//div[@class="descripcion_cestfini"]//text()').extract()
description = html_text_normalize(description)
item['description'] = description
item['code'] = ''
price = sel.xpath(
'.//div[@class="span4 force100ipad"]//span[@id="price_display"]/text()'
).extract()[0]
item['price'] = price_normalize(price)
item['sizes'] = list(
set(
sel.xpath(
'.//div[@data-variant="Talle"]//span[@class="custom-variants" and not(@style)]/text()'
).extract()))
item['image_urls'] = [
url[2:] for url in sel.xpath(
'.//a[@class="cloud-zoom-gallery"]/@href').extract()
]
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'converse'
item['breadcrumb'] = ['calzado', 'zapatilla', 'zapatilla urbana']
item['title'] = sel.xpath(
'.//h1[@class="entry-title"]/text()').extract()[0]
item['description'] = None
item['code'] = sel.xpath(
'.//p[contains(text(),"SKU")]/text()').extract()[0]
price = None
item['sizes'] = None
item['other'] = None
item['image_urls'] = sel.xpath(
'.//div[@class="producto-image"]/img/@src').extract()
yield item
self.links.insert({"_id": response.url})
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'blaque'
item['breadcrumb'] = ''
item['title'] = sel.xpath('.//h2[@class="tituloproducto"]/text()').extract()[0]
description = sel.xpath('.//p[@class="descri"]/text()').extract()
if len(description) > 0:
item['description'] = html_text_normalize(description)
item['code'] = sel.xpath('.//span[@class="numart"]/text()').extract()[0]
item['price'] = price_normalize(sel.xpath('.//div[@class="descprod"]//div[@class="price-box"]//span[@itemprop="price"]/@content').extract()[0])
sizes = sel.xpath('.//div[@class="swatchesContainer"]//li/div[not(contains(@class, "disabledSwatch"))]/text()').extract()
item['sizes'] = sizes
img_urls = sel.xpath('.//ul[@id="ul-moreviews"]//a[@class="cloud-zoom-gallery"]/@href').extract()
item['image_urls'] = img_urls
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'febo'
item['breadcrumb'] = sel.xpath(
'.//a[contains(@href,"javascript:Form")]/text()').extract()
item['title'] = sel.xpath('.//articulo_det/text()').extract()[0]
description = sel.xpath('.//descripcion_det/p/text()').extract()
item['description'] = html_text_normalize(description)
item['code'] = sel.xpath('.//articulo_det/text()').extract()[0]
item['price'] = price_normalize(
sel.xpath('.//precio_det[@id="preciohtml"]/text()').extract()
[0])
sizes = sel.xpath(
'.//div[@class="talles" and img/@src="img/btn_S.jpg"]/span/text()'
).extract()
item['sizes'] = sizes
item['other'] = None
item['image_urls'] = ['https://zapateriafebo.com/' + url for url in \
sel.xpath('.//foto_principal/img/@src').extract()]
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'viamo'
item['breadcrumb'] = sel.xpath(
'.//ul[@class="breadcrumb"]/li//a/text()').extract()
item['title'] = sel.xpath(
'.//div[contains(@class,"prodname")]/text()').extract()[0]
item['description'] = html_text_normalize(
sel.xpath(
'.//div[@class="productDescription"]/text()').extract())
item['code'] = None
item['price'] = price_normalize(
sel.xpath('.//strong[@class="skuBestPrice"]/text()').extract()
[0])
sizes = sel.xpath(
'.//label[contains(@class,"dimension-Talle") and not(contains(@class,"unavailable"))]/text()'
).extract()
item['sizes'] = sizes
item['other'] = None
item['image_urls'] = sel.xpath(
'.//a[contains(@title,"Zoom")]/@zoom').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'lucerna'
title = sel.xpath('.//h1[@itemprop="name"]/text()').extract()[0]
item['title'] = title
item['breadcrumb'] = [title.split(' ', 1)[0]]
item['description'] = html_text_normalize(
sel.xpath(
'.//div[@class="description user-content clear"]/p/text()'
).extract())
item['code'] = None
price = price_normalize(
sel.xpath('.//span[@id="price_display"]/text()').extract()[0])
item['price'] = price
sizes = sel.xpath(
'.//a[contains(@class,"insta-variations Talle") and span/@class="custom-variants"]/@data-option'
).extract()[0:5]
item['sizes'] = sizes
item['other'] = None
img_urls = sel.xpath(
'.//a[contains(@class,"cloud-zoom") and not(contains(@rel,"position"))]/@href'
).extract()
img_urls = list(map((lambda x: x[2:]), img_urls))
item['image_urls'] = img_urls
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'benditopie'
item['breadcrumb'] = []
item['title'] = sel.xpath(
'.//h1[@itemprop="name"]/text()').extract()[0]
item['description'] = html_text_normalize(
sel.xpath(
'.//div[@itemprop="description"]//span/text()').extract())
item['code'] = ''
item['price'] = price_normalize(
sel.xpath('.//span[@itemprop="price"]/text()').extract()[0])
size_labels = sel.xpath(
'.//select[@id="ProductSelect-product-template"]/option[not(contains(text(),"gotado"))]/text()'
).extract()
item['sizes'] = [label.strip()[:2] for label in size_labels]
image_urls = sel.xpath(
'.//ul[@id="ProductThumbs-product-template"]/li/a/@href'
).extract()
item['image_urls'] = [url[2:] for url in image_urls]
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'lucianomarra'
item['breadcrumb'] = []
title = sel.xpath('.//h1[@itemprop="name"]/span/text()').extract()
item['title'] = html_text_normalize(title)
item['description'] = html_text_normalize(sel.xpath('.//div[@id="tab-description"]//text()').extract())
item['code'] = ''
price = sel.xpath('.//div[@class="product-price"]/p/ins/span/text()').extract()
if len(price) == 0:
price = sel.xpath('.//div[@class="product-price"]/p/span/text()').extract()[0]
else:
price = price[0]
item['price'] = price_normalize(price)
sizes = sel.xpath('.//div[@class="select_option_label select_option"]/span/text()').extract()
item['sizes'] = sizes_normalize(sizes)
img_urls = sel.xpath('.//div[@class="images"]//a[@itemprop="image"]/@href').extract()
if len(img_urls) ==0:
img_urls = sel.xpath('.//div[@class="caroufredsel_wrapper"]//li/a/@href').extract()
item['image_urls'] = img_urls
yield item
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = sel.xpath(
'.//div[@class="prd-details"]//h2[@itemprop="brand"]/text()'
).extract()[0]
item['breadcrumb'] = [] # TODO
item['title'] = sel.xpath(
'.//div[@class="prd-details"]//h1[@class="prd-title"]/text()'
).extract()[0]
item['description'] = html_text_normalize(
sel.xpath(
'.//div[@id="productDetails"]//div[contains(@class,"prd-information")]/text()'
).extract())
item['code'] = sel.xpath(
'.//div[@id="detailSku"]/@data-sku').extract()[0]
item['price'] = price_normalize(
sel.xpath('.//span[@id="price_box"]/text()').extract()[0])
jsonSizes = sel.xpath(
'.//div[@class="prd-details"]//ul[contains(@class,"shoe_size")]/li/@data-simple'
).extract()
item['sizes'] = self.parseSize(jsonSizes)
item['image_urls'] = sel.xpath(
'.//ul[@id="productMoreImagesList"]//li/@data-image-product'
).extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'honkytonk'
item['breadcrumb'] = sel.xpath(
'.//a[@class="breadcrumb-crumb"]/text()').extract()
item['title'] = sel.xpath(
'.//span[contains(@class,"product-name")]/text()').extract()[0]
item['description'] = ''
item['code'] = ''
item['price'] = price_normalize(
sel.xpath(
'.//span[@class="price product-price js-price-display"]/@content'
).extract()[0])
sizes = sel.xpath(
'.//div[contains(./label/text(),"talle")]/select/option/text()'
).extract()
if len(sizes) == 0:
sizes = sel.xpath(
'.//a[contains(@class,"custom Size")]/span/@data-name'
).extract()
item['sizes'] = list(set(sizes))
img_urls = [
url[2:] for url in sel.xpath(
'.//div[@class="jTscroller scroller-thumbs"]/a/@href').
extract()
]
if len(img_urls) == 0:
img_urls = [
url[2:]
for url in sel.xpath('.//a[@id="zoom"]/@href').extract()
]
item['image_urls'] = img_urls
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'xl'
item['breadcrumb'] = sel.xpath(
'.//li[@class="last" and @typeof="v:Breadcrumb"]/a/text()'
).extract()
item['title'] = sel.xpath(
'.//div[contains(@class, "fn productName")]/text()').extract(
)[0]
description = sel.xpath(
'.//div[contains(@class, "productDescription")]/text()'
).extract()
code = ''
if len(description) > 0:
for i, s in enumerate(description):
if 'Código:' in s:
start_of_code = s.index('Código:') + 8
code = s[start_of_code:]
del description[i]
item['description'] = html_text_normalize(description)
item['code'] = code
item['price'] = price_normalize(response.meta['price'])
sizes = sel.xpath(
'.//div[@class="talles isTalle"]/span[@class="stock"]/text()'
).extract()
item['sizes'] = sizes
img_urls = sel.xpath('.//div[@class="thumbs"]/img/@src').extract()
item['image_urls'] = [
'https://www.xlshop.com.ar/' + url for url in img_urls
]
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'sarkany'
js_dict_variable = sel.xpath(
'//script[contains(.,"categoryName")]/text()').extract()[0]
# String like --> vtxctx = {skus:"23",.....,categoryName:"Fiesta",....}
js_dict_variable = js_dict_variable[js_dict_variable.
find('categoryName') + 14:]
category = js_dict_variable[:js_dict_variable.find('"')]
item['breadcrumb'] = [category]
item['title'] = sel.xpath(
'.//div[contains(@class,"prodname")]/text()').extract()[0]
item['description'] = html_text_normalize(
sel.xpath(
'.//div[@class="productDescription"]/text()').extract()[0])
item['code'] = None
price = sel.xpath(
'.//strong[@class="skuBestPrice"]/text()').extract()
if len(price) > 0:
price = price_normalize(price[0])
else:
price = 0
item['price'] = price
sizes = sel.xpath(
'.//label[contains(@class,"Talle") and not(contains(@class,"unavailable"))]/text()'
).extract()
item['sizes'] = sizes
item['other'] = None
item['image_urls'] = sel.xpath(
'.//a[@id="botaoZoom"]/@rel').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'ancayco'
item['breadcrumb'] = []
item['title'] = sel.xpath('.//div[@class="name uppercase bold"]/text()').extract()[0]
description = [(text if ('PRODUCTO' not in text and 'MERCADO' not in text) else '') for text in sel.xpath('.//div[@class="lfill top-1"]//text()').extract()]
description = html_text_normalize(description)
item['description'] = description
item['code'] = sel.xpath('.//div[@class="lfill"]/text()').extract()[0].replace('Código ','')
price = sel.xpath('.//span[@class="_totalContainer left-1"]//text()').extract()
if len(price) > 0:
price = price[0]
item['price'] = price_normalize(price)
else:
item['price'] = 0
sizes = []
for size_div in self.browser.find_elements_by_xpath(self.size_div_path):
for color_div in self.browser.find_elements_by_xpath(self.color_div_path):
self.click_element(size_div)
self.click_element(color_div)
time.sleep(1)
actual_size = size_div.text
source = self.browser.page_source
sel = Selector(text=source)
buy_button_style = sel.xpath(self.buy_button_path).extract()[0]
if not 'display: none;' in buy_button_style:
sizes.append(actual_size)
item['sizes'] = list(set(sizes))
item['image_urls'] = sel.xpath('.//div[@class="thumbnail"]/a/@href').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'sibylvane'
item['breadcrumb'] = []
item['title'] = html_text_normalize(sel.xpath('.//h3[@class="light-blue"]/text()').extract())
item['description'] = html_text_normalize(sel.xpath('.//div[@id="ctl00_HTMLContent_pnlDesc"]/p/text()').extract())
item['code'] = sel.xpath('.//div[@class="ref"]/text()').extract()[0].replace('ref:', '').replace('\n','')
item['price'] = price_normalize(sel.xpath('.//div[@id="ctl00_HTMLContent_pnlPrice"]/text()').extract()[1])
sizes = sel.xpath('.//select[@id="ddlSizesPicker"]/option[not(@value="-1") and not(@disabled)]/text()').extract()
item['sizes'] = sizes
item['image_urls'] = sel.xpath('.//img[@id="imgProductGallery"]/@data-zoom-image').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = '47street'
item['breadcrumb'] = []
item['title'] = sel.xpath('.//span[@class="base"]/text()').extract()[0]
item['description'] = html_text_normalize(sel.xpath('.//div[@itemprop="description"]/text()').extract())
item['code'] = sel.xpath('.//div[@itemprop="sku"]/text()').extract()[0].replace('SKU# ', '')
item['price'] = price_normalize(sel.xpath('.//span[@class="price"]/text()').extract()[0])
sizes = sel.xpath('.//div[@class="swatch-option text"]/text()').extract()
item['sizes'] = sizes
item['image_urls'] = sel.xpath('.//div[@class="imagen"]/img/@src').extract()
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'natacha'
breadcrumb = sel.xpath('.//nav/ol/li/a/text()').extract()
if len(breadcrumb) > 2:
breadcrumb = breadcrumb[1:-1]
else:
breadcrumb = []
item['breadcrumb'] = breadcrumb
item['title'] = sel.xpath('.//h1[@class="title border"]/text()').extract()[0].replace('Natacha Zapato Mujer', '')
description = sel.xpath('.//article[@id="tabDescription"]//text()').extract()
description = html_text_normalize(description)
generic_text_start = ' Productos confeccionados'
if generic_text_start in description:
description = description[:description.index(generic_text_start)]
item['description'] = description
item['code'] = ''
price = sel.xpath('.//span[@class="ch-price price"]/text()').extract()[0]
item['price'] = price_normalize(price)
sizes = sel.xpath('.//div[@id="my-variation-1-container"]//menu[contains(@class,"ch-select-content")]/li/span[not(text()="Talle")]/text()').extract()
if len(sizes) == 0:
sizes = [sel.xpath('.//span[contains(text(),"Talle")]/text()').extract()[0].replace('Talle: ','')]
item['sizes'] = [s for s in sizes if "Sin Stock" not in s] # Cuando no hay un talle queda asi [ "37 - Sin Stock", "39 - Sin Stock", "40 - Sin Stock", "41 - Sin Stock" ]
img_urls = sel.xpath('.//ul[@class="ch-carousel-list"]/li/img/@src').extract()
if len(img_urls) > 1:
img_urls = img_urls[:-1] # Eliminate size table image
item['image_urls'] = img_urls
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(1)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
brand = sel.xpath(
'.//h6[@class="fb-product-cta__brand fb-stylised-caps"]/text()'
).extract()[0]
item['brand'] = slugify(brand)
item['breadcrumb'] = html_text_normalize(
sel.xpath(
'.//b[@class="fb-masthead__breadcrumb__links"]//span[@itemprop="title"]/text()'
).extract())
item['title'] = sel.xpath(
'.//h1[@class="fb-product-cta__title"]/text()').extract()[0]
description = html_text_normalize(
sel.xpath(
'.//table[@class="fb-product-information__specification__table"]//tr[contains(@class,"row-data")]//text()'
).extract())
item['description'] = description
item['code'] = sel.xpath(
'.//p[@class="fb-product-sets__product-code"]/text()').extract(
)[0].replace('Código del producto:', '')
item['price'] = price_normalize(
sel.xpath(
'.//p[@class="fb-price" and contains(text(), "Contado")]/text()'
).extract()[0].replace('Contado', ''))
sizes = sel.xpath(
'.//select[@class="fb-inline-dropdown__native-dropdown fsrVisible"]/option[@value!=""]/@value'
).extract()
item['sizes'] = sizes_normalize(sizes)
item['image_urls'] = [url[2:] for url in \
sel.xpath('.//span[@class="fb-pp-gallery-list__link js-pp-zoom-link" and not(span/i[@class="icon-productGalleryMore"])]/@data-image-zoom').extract()]
yield item
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(10)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'grimoldi'
# Get first word of title i.e Abotinadas Berry
item['breadcrumb'] = sel.xpath(
'.//title/text()').extract()[0].split(' ', 1)[0]
item['title'] = sel.xpath(
'.//span[@id="Nombre"]/text()').extract()[0]
description = html_text_normalize(
sel.xpath('.//div[@class="description"]/p/text()').extract())
# remove generic text
description = description.split('. Compr', 1)[0]
item['description'] = description
item['code'] = None
item['price'] = price_normalize(
sel.xpath(
'.//label[@id="PrecioSeleccionado"]/text()').extract()[0])
sizes = sel.xpath(
'.//select[@id="IdMedidaSeleccionada"]/option/text()').extract(
)
item['sizes'] = sizes
item['other'] = None
urls = sel.xpath(
'.//div[@class="productImages"]//li/img/@data-image-url'
).extract()
item['image_urls'] = [url[2:] for url in urls]
yield item
else:
print("-------------- OLD -------------")
def parse_item(self, response):
if self.links.find_one({"_id": response.url}) is None:
print("------------- New Item ----------------")
self.browser.get(response.url)
time.sleep(2)
source = self.browser.page_source
sel = Selector(text=source)
item = Item()
item['created_at'] = datetime.now()
item['url'] = response.url
item['brand'] = 'brunomanetti'
item['breadcrumb'] = []
item['title'] = sel.xpath('.//span[@itemprop="name"]/text()').extract()[0]
description = [sel.xpath('.//h3/strong/font/i/text()').extract()[0]]
description += sel.xpath('.//p[contains(@style,"color: rgb(51, 51, 51); font-family: sans-serif, Arial, Verdana, ")]//text()').extract()
if len(description) > 3:
description = html_text_normalize(description[:len(description)-2])
item['description'] = description
item['code'] = ''
price = sel.xpath('.//span[@id="price_display"]/text()').extract()[0]
item['price'] = price_normalize(price)
sizes = []
for size_a in self.browser.find_elements_by_xpath(self.size_a_path):
try:
tmp = size_a.click()
except:
pass
time.sleep(0.2)
actual_size = size_a.text
buy_button = self.browser.find_elements_by_xpath(self.buy_button_path)[0]
if buy_button.is_enabled():
sizes.append(actual_size)
item['sizes'] = sizes
item['image_urls'] = sel.xpath('.//a[@class="cloud-zoom"]/@href').extract()[0][2:]
yield item
else:
print("-------------- OLD -------------")