def parse_product(self, response):
#Check the products description section on the page to make sure it is FSC Certified
check_for_fsc_cert = response.xpath(
'//p[text()[contains(.,"FSC")]]').extract()
if check_for_fsc_cert == []:
return
product_name = response.xpath(
'//div[@class="ml-product-name"]/div/text()').extract_first()
product_url = response.xpath(
'//link[@rel="alternate"]/@href').extract_first()
image = response.xpath(
'//div[@class="ml-product-alt-detail-image"]//img/@src'
).extract_first()
#Some product pages render the product images dynamically, after scrapy has rendered page
#This following if-statement is used to move on to next product if image was not rendered in page
if image == None:
return
description = response.xpath(
'//meta[@name="description"]/@content').extract_first()
original_price = response.xpath(
'//span[@class="ml-item-price"]/text()').extract_first()
#The prices will be returned as a string, and they may also have commas and '$' in them,
#This function is intended to remove any commas and '$' then turn the strings into integers
def modifyPriceList(thePrice):
price_container = []
#Takes dollar sign and commas out of price
price_without_commas = thePrice.replace(',', '').replace('$', '')
#Turns price_without_commas into floating integer
price_as_integer = float(price_without_commas)
price_container.append(price_as_integer)
return price_container
final_price = modifyPriceList(original_price)
#Most of the eco-products on France and Son are FSC Certified
#Currently no Greenguard Products have been noted for this store
certifications = [{
"certification":
"Forest Stewardship (FSC) Certified",
"title":
"FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests.",
"url":
"https://us.fsc.org/en-us/what-we-do/mission-and-vision"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'One Kings Lane'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = final_price[0]
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Check the product page to see if it includes the sold out tag
sold_out = response.xpath(
'//span[@class="product--badge badge--soldout"]/text()').extract()
#If the page does contain sold out tag end the parse_product function
if sold_out == []:
return
product_name = response.xpath(
'//meta[@property="og:title"]/@content').extract_first()
product_url = response.xpath(
'//meta[@property="og:url"]/@content').extract_first()
image = response.xpath(
'//meta[@property="og:image"]/@content').extract_first()
description = response.xpath(
'//meta[@property="og:description"]/@content').extract_first()
original_price = response.xpath(
'//meta[@property="og:price:amount"]/@content').extract_first()
#The prices will be returned as a string, and they may also have commas in them,
#This function is intended to remove any commas and turn the strings into integers
def modifyPriceList(thePrice):
price_container = []
#Takes commas out of price
price_without_commas = thePrice.replace(',', '')
#Turns price_without_commas into floating integer
price_as_integer = float(price_without_commas)
price_container.append(price_as_integer)
return price_container
final_price = modifyPriceList(original_price)
#Most of the eco-products on France and Son are FSC Certified
#Currently no Greenguard Products have been noted for this store
certifications = [{
"certification":
"Forest Stewardship (FSC) Certified",
"title":
"FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests.",
"url":
"https://us.fsc.org/en-us/what-we-do/mission-and-vision"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'France and Son'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = final_price[0]
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Check the products description section on the page to make sure it is FSC Certified
check_for_fsc_cert = response.xpath(
'//div[@class="row multi-column-row"]/div[contains(.,"FSC")]'
).extract()
if check_for_fsc_cert == []:
return
product_name = response.xpath(
'//meta[@property="og:title"]/@content').extract_first()
product_url = response.xpath(
'//meta[@property="og:url"]/@content').extract_first()
image = response.xpath(
'//meta[@property="og:image"]/@content').extract_first()
description = response.xpath(
'//meta[@property="og:description"]/@content').extract_first()
string_of_price = response.xpath(
'//meta[@property="og:price:amount"]/@content').extract_first()
def modifyPrice(thePrice):
price_container = []
price_without_commas = thePrice.replace(',', '')
price_as_number = float(price_without_commas)
price_container.append(price_as_number)
return price_container
final_price = modifyPrice(string_of_price)
#Most of the eco-products on WestElm are FSC Certified
#Currently no Greenguard Products have been noted for this store
certifications = [{
"certification":
"Forest Stewardship (FSC) Certified",
"title":
"FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests.",
"url":
"https://us.fsc.org/en-us/what-we-do/mission-and-vision"
}]
#Currently no price span for any products on Stem Goods
lowest_price = final_price[0]
load_item = productSpiderItem()
load_item['sitename'] = 'Stem'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
product_name = response.xpath(
'//meta[@property="og:title"]/@content').extract_first()
product_url = response.xpath(
'//meta[@property="og:url"]/@content').extract_first()
image = 'https:' + response.xpath(
'//meta[@property="og:image"]/@content').extract_first().replace(
'medium', 'large')
description = response.xpath(
'//meta[@property="og:description"]/@content').extract_first()
#The following line will return the price(s) as a string inside of a list, and it may also have commas.
original_price_span = response.xpath(
'//meta[@property="og:price:amount"]/@content').extract()
def modifyPriceList(thePriceList):
price_container = []
#Takes commas out of price
for price in thePriceList:
price_without_commas = price.replace(',', '')
price_container.append(price_without_commas)
#Convert string in list to floating number
price_container = list(map(float, price_container))
return price_container
final_price_span = modifyPriceList(original_price_span)
#Most of the eco-products on 2modern are FSC Certified
#Currently no Greenguard Products have been noted for this store
certifications = [{
"certification":
"Forest Stewardship (FSC) Certified",
"title":
"FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests.",
"url":
"https://us.fsc.org/en-us/what-we-do/mission-and-vision"
}]
#In order for elasticsearch to sort the products by price amount it will need the first
#one in the array if there is a price range for the product
lowest_price = final_price_span[0]
load_item = productSpiderItem()
load_item['sitename'] = '2Modern'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price_span
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Checking product description for Greenguard Gold, if no Greenguard Gold is
#detected the function should be cancelled since the product may not be certified
check_description = response.xpath('//div[@class="std"]//ul/li').extract()
def check_for_certification(description):
if any("GREENGUARD Gold" in string for string in description):
pass
else:
return
productname = response.xpath('//h1[@itemprop="name"]/text()').extract_first()
product_url = response.xpath('//meta[@itemprop="url"]/@content').extract_first()
image = response.xpath('//ul[@id="imageGallery"]/li//img/@src').extract_first()
#.replace() Removes excess unicode characters
description = response.xpath('//div[@class="std"]/p/text()').extract_first().replace(u'\xa0', u' ')
#The price for the product changes dynamically at the last minute, this price may be off
original_price = response.xpath('//span[@class="amount"]/text()').extract_first()
#The prices will be returned as a string, and they may also have commas in them,
#This function is intended to remove any commas and turn the strings into integers
def modifyPriceList (thePrice):
price_container = []
#Takes commas and dollar signs out of price
price_without_commas = thePrice.replace(',','').replace('$','')
price_container.append(price_without_commas)
#Changes each number in price container to a floating number
price_container = list(map(float, price_container))
return price_container
final_price = modifyPriceList(original_price)
certifications = [{
"certification": "GREENGUARD Certified",
"title": "GREENGUARD Certified products contain materials and finishes that have been verified to have low chemical emissions. \
As a result, this product improves overall indoor air quality by reducing the presence of harmful \
pollutants and airborne chemicals.", "url": "http://greenguard.org/en/CertificationPrograms/CertificationPrograms_indoorAirQuality.aspx"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'Romina Furniture'
load_item['productname'] = productname
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = final_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Checking for Greenguard Gold, if no Greenguard Cert is
#detected close method
greenguard_verified = re.search(r'<a\s*href="[^"]*?"\s*title="[^"]*?GREENGUARD[^"]*?"', response.text, flags=re.I |re.S)
if not greenguard_verified:
print("No Greenguard Products Detected")
return
productname = re.search(r'itemprop="name"\s*content="([^"]*?)">', response.text, flags=re.I | re.S).group(1)
product_url = response.xpath('//meta[@itemprop="url"]/@content').extract_first()
image_url_stub = re.search(r'data-src="([^"]*?)"[^>]*?id="ProductPhotoImg">', response.text, flags=re.I |re.S).group(1)
image = 'https://rominafurniture.com' + image_url_stub
#.replace() Removes unicode characters
# description = response.xpath('//div[@class="std"]/p/text()').extract_first().replace(u'\xa0', u' ')
#The price for the product changes dynamically at the last minute, this price may be off
original_price = re.search(r'<meta property="og:price:amount"\s*content="([^"]*?)">', response.text, flags=re.I | re.S)
#The prices will be returned as a string, and they may also have commas in them,
#This function is intended to remove any commas and turn the strings into integers
def modifyPriceList (thePrice):
price_container = []
#Takes commas and dollar signs out of price
price_without_commas = thePrice.replace(',','').replace('$','')
price_container.append(price_without_commas)
#Changes each number in price container to a floating number
price_container = list(map(float, price_container))
return price_container
final_price = modifyPriceList(original_price.group(1))
certifications = [{
"certification": "GREENGUARD Certified",
"title": "GREENGUARD Certified products contain materials and finishes that have been verified to have low chemical emissions. \
As a result, this product improves overall indoor air quality by reducing the presence of harmful \
pollutants and airborne chemicals.", "url": "http://greenguard.org/en/CertificationPrograms/CertificationPrograms_indoorAirQuality.aspx"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'Romina Furniture'
load_item['productname'] = productname
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
# load_item['description'] = description
load_item['lowestprice'] = final_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
productname = response.xpath('//title/text()').extract_first()
product_url = 'https://smartfurniture.com' + response.xpath(
'//body/div/@data-url').extract_first()
#Returns a list, image will be 8th in the list(On zero-based index)
image = re.search(
r'<a\s*href="//([^"]*?)">\s*<div\s*class="square-image',
response.text,
flags=re.I | re.S)
description = response.xpath(
'//meta[@name="description"]/@content').extract_first()
pricing = re.search(
r'<div class="product-price-details\s*"[^>]*?data-sale-price="([^"]*?)"\s*data-original-price="([^"]*?)"',
response.text,
flags=re.I | re.S)
lowest_price = pricing.group(1)
price = pricing.group(2)
check_greenguard = response.xpath(
'//*[text()[contains(.,"GREENGUARD")]]')
check_fsc = response.xpath('//*[text()[contains(.,"FSC")]]')
#Both FSC and Greenguard products
def find_certifications():
cert_container = []
if check_greenguard and check_fsc:
cert_container.extend(
("GREENGUARD Certified",
"Forest Stewardship Council (FSC) Certified"))
elif check_greenguard:
cert_container.append('GREENGUARD Certified')
elif check_fsc:
cert_container.append(
'Forest Stewardship Council (FSC) Certified')
return cert_container
certifications = find_certifications()
load_item = productSpiderItem()
load_item['sitename'] = 'Smart Furniture'
load_item['productname'] = productname
load_item['producturl'] = product_url
load_item['image'] = image.group(1)
load_item['price'] = price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
productname = response.xpath('//title/text()').extract_first()
product_url = 'https://smartfurniture.com' + response.xpath(
'//body/div/@data-url').extract_first()
#Returns a list, image will be 8th in the list(On zero-based index)
image = 'https://smartfurniture.com' + response.xpath(
'//div[@class="mainContent"]//a/@href')
description = response.xpath(
'//meta[@name="description"]/@content').extract_first()
price = response.xpath(
'//meta[@itemprop="price"]/@content').extract_first()
lowest_price = response.xpath(
'//meta[@itemprop="price"]/@content').extract_first()
check_greenguard = response.xpath(
'//*[text()[contains(.,"GREENGUARD")]]')
check_fsc = response.xpath('//*[text()[contains(.,"FSC")]]')
#Both FSC and Greenguard products
def find_certifications():
cert_container = []
if check_greenguard[0] and check_fsc[0]:
cert_container.extend(
("GREENGUARD Certified",
"Forest Stewardship Council (FSC) Certified"))
elif check_greenguard[0]:
cert_container.append('GREENGUARD Certified')
elif check_fsc[0]:
cert_container.append(
'Forest Stewardship Council (FSC) Certified')
return cert_container
ceritifications = find_certifications()
load_item = productSpiderItem()
load_item['sitename'] = 'Smart Furniture'
load_item['productname'] = productname
load_item['producturl'] = product_url
load_item['image'] = image[8]
load_item['price'] = price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Check the products description section on the page to make sure it is Greenguard Certified
check_for_gg_cert = response.xpath('//div[@itemprop="description"]//ul').extract_first()
if 'GREENGUARD' not in check_for_gg_cert:
return
product_name = response.xpath('//meta[@property="og:title"]/@content').extract_first()
product_url = response.xpath('//meta[@property="og:url"]/@content').extract_first()
image = response.xpath('//meta[@property="og:image"]/@content').extract_first()
description = response.xpath('//meta[@property="og:description"]/@content').extract_first()
original_price = response.xpath('//meta[@property="og:price:amount"]/@content').extract_first()
#The prices will be returned as a string
#This function is intended to turn the original_price string into an integer
def modifyPriceList (thePrice):
price_container = []
#Turns price_without_commas into floating integer
price_as_integer = float(thePrice)
price_container.append(price_as_integer)
return price_container
final_price = modifyPriceList(original_price)
#Most of the eco-products on davincibaby are GREENGUARD Gold Certified
certifications = [{
"certification": "GREENGUARD Certified",
"title": "GREENGUARD Certified products contain materials and finishes that have been verified to have low chemical emissions. \
As a result, this product improves overall indoor air quality by reducing the presence of harmful \
pollutants and airborne chemicals.", "url": "http://greenguard.org/en/CertificationPrograms/CertificationPrograms_indoorAirQuality.aspx"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'Davinci Baby'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = final_price[0]
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
productname = response.xpath(
'//div[@class="pip-summary"]/h1/text()').extract_first()
product_url = response.xpath(
'//head/meta[@property="og:url"]/@content').extract_first()
image = response.xpath(
'//head/meta[@property="og:image"]/@content').extract_first()
#Description response will have unicode characters in scrapy shell but they are parsed into utf-8
#when it is sent via ElasticSearch pipeline
description = response.xpath(
'//head/meta[@property="twitter:description"]/@content'
).extract_first()
#The following line will return the price(s) as a string in a list, and it may also have commas.
original_price_span = response.xpath(
'//section[@class="simple-subset"]//span[@class="price-amount"]/text()'
).extract()
#Some Pottery Barn Kids products list a price range for different sizes
#Products with a price range must be grabbed from a different section on product page
#This function is intended to remove any commas and turn the strings into integers
#The function also grabs the low and high price if original_price_span is empty
def modifyPriceList(thePriceSpan):
if thePriceSpan == []:
price_container = []
#Grabs the object as a string from script element on page
#Object contains both high price and low price
load_string_with_pricing = response.xpath(
'//script[@type="application/ld+json"]/text()'
).extract_first()
#Converts string element to dictionary
convert_string_to_dictionary = ast.literal_eval(
load_string_with_pricing)
#Grab highest and lowest price
low_price = convert_string_to_dictionary['offers']['lowPrice']
high_price = convert_string_to_dictionary['offers'][
'highPrice']
#Add low price and high price to price_conteinr list
price_container.extend([low_price, high_price])
#Convert low price and high price to floating numbers
price_container = list(map(float, price_container))
return price_container
#Removes original price range, and extracts the new marked down price range
if len(thePriceSpan) == 4:
del thePriceSpan[:2]
price_container = []
for price in thePriceSpan:
#Takes commas out of price
price_without_commas = price.replace(',', '')
price_container.append(price_without_commas)
#Changes each number in price container to a floating number
price_container = list(map(float, price_container))
return price_container
final_price_span = modifyPriceList(original_price_span)
#Most of the eco-products on Pottery Barn Kids products are Greenguard Gold Certified
#Currently no FSC Products have been noted for this store
certifications = [{
"certification":
"GREENGUARD Certified",
"title":
"GREENGUARD Certified products contain materials and finishes that have been verified to have low chemical emissions. \
As a result, this product improves overall indoor air quality by reducing the presence of harmful \
pollutants and airborne chemicals.",
"url":
"http://greenguard.org/en/CertificationPrograms/CertificationPrograms_indoorAirQuality.aspx"
}]
#In order for elasticsearch to sort the products by price amount it will need the first
#one in the array if there is a price range for the product
lowest_price = final_price_span[0]
load_item = productSpiderItem()
load_item['sitename'] = 'Pottery Barn Kids'
load_item['productname'] = productname
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price_span
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
product_name = "Outdoor: " + response.xpath('//head/meta[@property="og:title"]/@content').extract_first()
#Remove registered trade mark from string since it arrives as numeric
#representation of the non-ascii character
if "®" in product_name:
product_name_without_symbols = product_name.replace("®", "")
product_name = product_name_without_symbols
product_url = response.xpath('//head/meta[@property="og:url"]/@content').extract_first()
image = response.xpath('//head/meta[@property="og:image"]/@content').extract_first()
#Description response will have unicode characters in scrapy shell but they are parsed into utf-8
#when it is sent via ElasticSearch pipeline
description = response.xpath('//head/meta[@property="twitter:description"]/@content').extract_first()
#The following line will return the price(s) as a string in a list, and it may also have commas.
original_price_span = response.xpath('//section[@class="simple-subset"]//span[@class="price-amount"]/text()').extract()
#Some Pottery Barn products list a price range for different sizes
#Products with a price range must be grabbed from a different section on product page
#This function is intended to remove any commas and turn the strings into integers
#The function also grabs the low and high price if original_price_span is empty
def modifyPriceList (thePriceSpan):
#If the following condition is true
#It indicates that a price range is in place for the product
if thePriceSpan == []:
price_container = []
#Grabs the object as a string from script element on page
#Object contains both high price and low price
load_string_with_pricing = response.xpath('//script[@type="application/ld+json"]/text()').extract_first()
#Converts string element to dictionary
convert_string_to_dictionary = ast.literal_eval(load_string_with_pricing)
#Grab highest and lowest price
low_price = convert_string_to_dictionary['offers']['lowPrice']
high_price = convert_string_to_dictionary['offers']['highPrice']
#Add low price and high price to price_conteinr list
price_container.extend([low_price, high_price])
#Convert low price and high price to floating numbers
price_container = list(map(float, price_container))
return price_container
#Whenever there are two numbers in the list
#The first one has to be deleted because it is not
#the current marked down price
if len(thePriceSpan) == 2:
del thePriceSpan[:1]
#Removes original price range, and extracts the new marked down price range
if len(thePriceSpan) == 4:
del thePriceSpan[:2]
price_container = []
for price in thePriceSpan:
#Takes commas out of price
price_without_commas = price.replace(',','')
price_container.append(price_without_commas)
#Changes each number in price container to a floating number
price_container = list(map(float, price_container))
return price_container
final_price_span = modifyPriceList(original_price_span)
#Most of the eco-products on 2modern are FSC Certified
#Currently no Greenguard Products have been noted for this store
certifications = [{"certification": "Forest Stewardship (FSC) Certified",
"title": "FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests.",
"url": "https://us.fsc.org/en-us/what-we-do/mission-and-vision"}]
#In order for elasticsearch to sort the products by price amount it will need the first
#one in the array if there is a price range for the product
lowest_price = final_price_span[0]
load_item = productSpiderItem()
load_item['sitename'] = 'Pottery Barn'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price_span
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = lowest_price
#Returns object with each load_item included
yield load_item
def parse_product(self, response):
#Check the products description section on the page to make sure it is FSC Certified
check_for_fsc_cert = response.xpath(
'//div[@class="accordion-tab-copy"]//ul/li[text()[contains(.,"FSC")]]'
).extract()
if check_for_fsc_cert == []:
return
product_name = response.xpath(
'//meta[@property="og:title"]/@content').extract_first()
product_url = response.xpath(
'//meta[@property="og:url"]/@content').extract_first()
image = response.xpath(
'//meta[@property="og:image"]/@content').extract_first()
description = response.xpath(
'//meta[@name="description"]/@content').extract_first()
original_price = response.xpath(
'//div[@class="pip-summary"]//span[@class="price-amount"]/text()'
).extract()
def modifyPriceList(thePriceSpan):
#If the following condition is true
#It indicates that a price range is in place for the product
if thePriceSpan == []:
price_container = []
#Grabs the object as a string from script element on page
#Object contains both high price and low price
load_string_with_pricing = response.xpath(
'//script[@type="application/ld+json"]/text()'
).extract_first()
#Converts string element to dictionary
convert_string_to_dictionary = ast.literal_eval(
load_string_with_pricing)
#Grab highest and lowest price
low_price = convert_string_to_dictionary['offers']['lowPrice']
high_price = convert_string_to_dictionary['offers'][
'highPrice']
#Add low price and high price to price_conteinr list
price_container.extend([low_price, high_price])
#Convert low price and high price to floating numbers
price_container = list(map(float, price_container))
return price_container
#Whenever there are two numbers in the list
#The first one has to be deleted because it is not
#the current marked down price
if len(thePriceSpan) == 2:
del thePriceSpan[:1]
#Removes original price range, and extracts the new marked down price range
if len(thePriceSpan) == 4:
del thePriceSpan[:2]
price_container = []
for price in thePriceSpan:
#Takes commas out of price
price_without_commas = price.replace(',', '')
price_container.append(price_without_commas)
#Changes each number in price container to a floating number
price_container = list(map(float, price_container))
return price_container
final_price = modifyPriceList(original_price)
#Most of the eco-products on davincibaby are GREENGUARD Gold Certified
certifications = [{
"certification":
"Forest Stewardship (FSC) Certified",
"title":
"FSC Certified products help reduce deforestation by ensuring products have been manufactured with recycled wood materials or have originated from sustainably managed forests. For more information click here",
"url":
"https://us.fsc.org/en-us/what-we-do/mission-and-vision"
}]
load_item = productSpiderItem()
load_item['sitename'] = 'Williams Sonoma'
load_item['productname'] = product_name
load_item['producturl'] = product_url
load_item['image'] = image
load_item['price'] = final_price
load_item['certifications'] = certifications
load_item['description'] = description
load_item['lowestprice'] = final_price[0]
#Returns object with each load_item included
yield load_item