Notes

singleRecord: true
regionsSelector: null
recordSelector: null
recordXPath: null
screenCapture: true
fields:
- name: image
singleValue: true
xpath: //img[@id="productImage"]/@src
regExp: .+(?=&recipe(Id|Name)=d+)
description: URL of the main product image
- name: imageAlt
singleValue: true
xpath: //img[contains(@id,"initialImage")]/@alt
description: Alt text of the main product image
- name: alternateImages
singleValue: false
xpath: //div[@id="theViews"]//div[@class="slick-track"]//a[not(contains(@class,"selectedSlide"))]//img/@src
regExp: .+(?=&recipe(Id|Name)=d+)
description: Other product images (not in manufacturer description)
- name: metaKeywords
singleValue: true
xpath: //meta[contains(@name, "keywords")]/@content
description: The <meta> keywords content
- name: category
singleValue: false
xpath: //ul[@itemprop="breadcrumb" and @id="crumbs_ul"]//li[position()>1]//a/span[span]/text()
description: The categories (e.g. from breadcrumbs)
- name: nameExtended
singleValue: true
xpath: //h1[@itemprop="name"]
description: The product name, prefixing "${brand} - " if not included in "name"
and appending " - ${variantType}" if necessary (fixed per feed)
- name: listPrice
singleValue: true
xpath: //div[contains(@class,"online-price")]/span[@class="op-value"]
description: The stated undiscounted price for the product
- name: price
singleValue: true
xpath: //div[@id="pull-right-price"]
description: The offered price for the selected product variant - if a user
clicks add to basket this is the price they would be charged
- name: availabilityText
singleValue: true
xpath: //meta[@property="og:availability"]/@content
description: Availability as described on page for the selected variant. If
there is no availability but the product can be added to cart, this field
should be "In Stock"
- name: description
singleValue: false
xpath: //div[contains(@class,"features-container form-group")]//ul[contains(@class,"pdp-features")]//child::li
description: Product description supplied by website - may be concatenanted from
multiple places; specifically not the manufacturer description
- name: descriptionBullets
singleValue: true
xpath: //div[@id="bulletsCount"]
description: Number of ul > li tags in the description
type: NUMBER
- name: brandText
singleValue: true
xpath: //div[@itemprop="brand"]
description: Product brand shown - this may actually NOT be just a brand name,
e.g. "Visit the Gillette Store"
- name: manufacturer
singleValue: true
description: Product manufacturer
- name: quantity
singleValue: false
xpath: //li[contains(text(), "Dimension")] | //li[contains(text(), "Dimension")]/following-sibling::li[1]
regExp: (?![DimenonsLWH×()s:])(.*)s(x|×)s(.*)(x|×)s(.*)
description: Quantity as described on the page
- name: weightNet
xpath: //li[contains(text(), "Weight")]
regExp: (?![Weights])d.*
description: Net weight as described on the page
- name: weightGross
singleValue: true
description: Gross weight as described on the page
- name: gtin
singleValue: true
description: GTIN code (includes UPC/EAN)
- name: variantId
singleValue: true
xpath: //p[@id="product-body-item-number"]/span
description: Identifier for a variant from a store where variants share the same sku
- name: mpc
xpath: (//span/@data-model-number | //p[@id="product-body-model-number"])[1]
description: The manufacturer model code (unique) of the product
- name: packSize
singleValue: true
description: The number of packs in the product offer (if stated separately on
the site to quantity)
- name: legalDisclaimer
singleValue: true
description: Content under "legal disclaimer" header
- name: directions
singleValue: true
description: Content under "directions" header
- name: warnings
singleValue: true
description: Content under "warnings" header
- name: ratingCount
singleValue: true
xpath: //span[@itemprop="reviewCount"] | //div[@id="ratingcount"]
description: The number of ratings
type: NUMBER
- name: aggregateRatingText
singleValue: true
xpath: //span[@itemprop="ratingValue"] | | //div[@id="rating"]
description: The stated aggregate rating normalized to be out of 5
- name: aggregateRating
singleValue: true
xpath: //span[@itemprop="ratingValue"] | //div[@id="rating"]
description: The stated aggregate rating
- name: shippingInfo
singleValue: true
description: Shipping information for the product
- name: shippingDimensions
singleValue: true
description: Stated shipping dimensions
- name: shippingWeight
singleValue: true
description: Stated shipping weight
- name: variantCount
singleValue: true
xpath: count(//div[contains(@class,"swatches-v2")]//span[contains(@class,"variant-")])
description: Number of variants listed
type: NUMBER
- name: color
xpath: //div[contains(@class,"product-info-specs")]//div[contains(text(),"Color") or contains(text(), "Colour")]/following-sibling::div
description: A textual description of the colour
- name: colorCode
singleValue: true
description: A code description of the color (e.g. RGB hex)
- name: manufacturerDescription
singleValue: false
xpath: //div[@id="wc-power-page"] | //div[@class="product-info-description"]
description: The extended description of the product supplied by the lister
- name: manufacturerImages
singleValue: true
xpath: //body/@import-enhanced-content
description: Images within the third party description
- name: videos
singleValue: false
xpath: //div[@itemprop="video"]//meta[@itemprop="contentUrl"]/@content | //head//@video | //body//@videospan
description: URLs of videos on page
- name: name
singleValue: true
xpath: //h1[@itemprop="name"]
description: The product name
- name: inStorePrice
singleValue: true
xpath: //span[contains(text(), "Your Price")]/following-sibling::div
description: Price in the selected store
- name: asin
singleValue: true
description: null
- name: coupon
xpath: (//div[@id="unclippedCouponSns"]//span[@class="a-color-success"])[1]
singleValue: true
description: Text of any coupon offer
- name: amazonChoice
singleValue: true
description: YES or Blank
- name: amazonChoiceCategory
singleValue: true
description: Text of link next to Amazon choice graphic
- name: brandLink
singleValue: true
description: null
- name: internationalShipping
singleValue: true
description: Text next to bullet point
- name: salesRankCategory
singleValue: false
description: Amazon best selling rank from product details (linked back) - needs
to be collapsed
- name: subscriptionPrice
singleValue: true
description: Subscribe and save price
- name: subscribeAndSave
singleValue: true
description: YES/NO
- name: heroQuickPromoHeadline
singleValue: true
description: See image - top section hero area
- name: heroQuickPromoImageUrl
singleValue: true
description: null
- name: heroQuickPromoUrl
singleValue: true
description: null
- name: pasin
singleValue: true
description: Parent asin
- name: videoLength
singleValue: false
description: null
- name: ingredientImagePresent
singleValue: true
description: null
- name: factImagePresent
singleValue: true
description: null
- name: largeImageCount
singleValue: true
description: null
type: NUMBER
- name: variantAsins
singleValue: true
description: null
- name: primeFlag
singleValue: true
description: null
- name: lbb
singleValue: true
description: Check Lost by Box Requirements (just for Amazon and a couple of
other stores) - LBB occurs when a product is bought from someone other
than Amazon (on Amazon Website) - even though Amazon has the product "in
Stock"
- name: lbbPrice
singleValue: true
description: null
- name: featureBullets
singleValue: false
xpath: //ul[@class='pdp-features']/li
description: null
- name: otherSellersName
singleValue: false
description: null
defaultValue: Costco Wholesale Corporation
- name: otherSellersPrice
singleValue: false
description: null
- name: otherSellersShipping
singleValue: false
description: null
- name: secondaryImageTotal
singleValue: true
description: null
type: NUMBER
- name: news
singleValue: true
description: null
- name: addonItem
singleValue: true
description: null
- name: fastTrack
singleValue: true
description: null
- name: ingredientsList
singleValue: true
description: List of Ingredients from site - can be string of data if no
discernible start/end point
- name: servingSize
singleValue: true
description: The size of serving Nutritional information is based on.
- name: servingSizeUom
singleValue: true
description: Unit of measure of serving
- name: numberOfServingsInPackage
singleValue: true
description: Suggested number of servings of the product.
type: NUMBER
- name: caloriesPerServing
singleValue: true
description: Nutritional Information for Calories Per Serving content - Usually
based on per 100g serving
- name: caloriesFromFatPerServing
singleValue: true
description: Nutritional Information for Calories From Fat content - Usually
based on per 100g serving
type: NUMBER
- name: totalFatPerServing
singleValue: true
description: Nutritional Information for Total Fat content - Usually based on
per 100g serving
type: NUMBER
- name: totalFatPerServingUom
singleValue: true
description: Unit of Measure Data for Total Fat content
- name: saturatedFatPerServing
singleValue: true
description: Nutritional Information for Saturated Fat content - Usually based
on per 100g serving
type: NUMBER
- name: saturatedFatPerServingUom
singleValue: true
description: Unit of Measure Data for Saturated Fat content
- name: transFatPerServing
singleValue: true
description: Nutritional Information for Trans Fat content - Usually based on
per 100g serving
type: NUMBER
- name: transFatPerServingUom
singleValue: true
description: Unit of Measure Data for Trans Fat content
- name: cholesterolPerServing
singleValue: true
description: Nutritional Information for Cholesterol content - Usually based on
per 100g serving
type: NUMBER
- name: cholesterolPerServingUom
singleValue: true
description: Unit of Measure Data for Cholesterol content
- name: sodiumPerServing
singleValue: true
description: Nutritional Information for Sodium content - Usually based on per
100g serving
type: NUMBER
- name: sodiumPerServingUom
singleValue: true
description: Unit of Measure Data for Sodium content
- name: totalCarbPerServing
singleValue: true
description: Nutritional Information for Total Carbohydrate content - Usually
based on per 100g serving
type: NUMBER
- name: totalCarbPerServingUom
singleValue: true
description: Unit of Measure Data for Total Carbohydrate content
- name: dietaryFibrePerServing
singleValue: true
description: Nutritional Information for Dietary Fibre content - Usually based
on per 100g serving
type: NUMBER
- name: dietaryFibrePerServingUom
singleValue: true
description: Unit of Measure Data for Dietary Fibre content
- name: totalSugarsPerServing
singleValue: true
description: Nutritional Information for Total Sugar content - Usually based on
per 100g serving
type: NUMBER
- name: totalSugarsPerServingUom
singleValue: true
description: Unit of Measure Data for Total Sugar content
- name: proteinPerServing
singleValue: true
description: Nutritional Information for Protein content - Usually based on per
100g serving
type: NUMBER
- name: proteinPerServingUom
singleValue: true
description: Unit of Measure Data for Protein
- name: vitaminAPerServing
singleValue: true
description: Nutritional Information for Vitamin A content - Usually based on
per 100g serving
type: NUMBER
- name: vitaminAPerServingUom
singleValue: true
description: Unit of Measure Data for Vitamin A
- name: vitaminCPerServing
singleValue: true
description: Nutritional Information for Vitamin C content - Usually based on
per 100g serving
type: NUMBER
- name: vitaminCPerServingUom
singleValue: true
description: Unit of Measure Data for Vitamin C
- name: calciumPerServing
singleValue: true
description: Nutritional Information for Calcium content - Usually based on per
100g serving
type: NUMBER
- name: calciumPerServingUom
singleValue: true
description: Unit of Measure Data for Calcium
- name: ironPerServing
singleValue: true
description: Nutritional Information for Iron content - Usually based on per
100g serving
type: NUMBER
- name: ironPerServingUom
singleValue: true
description: Unit of Measure Data for Iron
- name: dietarySymbols
singleValue: true
description: Information related to the dietary symbols of a specific product
- name: magnesiumPerServing
singleValue: true
description: Nutritional Information for Magnesium content - Usually based on
per 100g serving
type: NUMBER
- name: magnesiumPerServingUom
singleValue: true
description: Unit of Measure Data for Magnesium
- name: saltPerServing
singleValue: true
description: Nutritional Information for Salt content - Usually based on per
100g serving
type: NUMBER
- name: saltPerServingUom
singleValue: true
description: Unit of Measure Data for Salt
- name: dietaryInformation
singleValue: true
description: null
- name: warranty
xpath: //span[contains(text(), "Warranty")]/following-sibling::ul | //p[contains(text(), "Warranty")]
description: Guarantee associated with the product
- name: storage
singleValue: true
description: Suggested storage location for product
- name: countryOfOrigin
singleValue: true
description: The country from which the product originates
- name: allergyAdvice
singleValue: true
description: Allergy information associated with the product
- name: recyclingInformation
singleValue: true
description: Recycling information associated with the product
- name: productOtherInformation
singleValue: false
description: Any other product information
- name: packaging
singleValue: true
description: Packaging information
- name: additives
singleValue: true
description: List of additives in the product
- name: pricePerUnit
singleValue: true
description: Price of the product split into certain units
- name: pricePerUnitUom
singleValue: true
description: The unit of measurement used in price_per_unit
- name: promotion
singleValue: true
xpath: //div[contains(@class,"marketing-container")]/p/text()
description: promotion text on product page
- name: alcoholContent
singleValue: true
description: Alcohol content information
- name: newVersion
singleValue: true
description: In product page, information about a new version of the product
(https://www.amazon.es/DODOT-Sensitive-Pa%C3%B1ales-Talla-240/dp/B01ELA8U0Q/ref=sr_1_4?__mk_es_ES=%C3%85M%C3%85%C5%BD%C3%95%C3%91&dchild=1&keywords=dodot%2B-%2Bpa%C3%B1ales%2Bpara%2Bni&qid=1589984387&sr=8-4&th=1)
- name: newAsin
singleValue: true
description: In product page, information about a new version of the product -
new asin info
- name: newDescription
singleValue: true
description: In product page, information about a new version of the product -
new desription info
- name: variantInformation
singleValue: true
xpath: //div[@id="product-details"]//label[contains(@for, "productOption")]
description: colour / scent / flavour / other
- name: firstVariant
singleValue: true
description: Unique identifier for a collection of variants. For a subset of
core feeds (43) we have a column "first_variant" that is populated with a
common code to link all variants for a product. method 1 (Preferred) = use
common tag (Could be parent sku) that is same value for all variants of a
product. method 2 = first_variant method technique, Identify the first
varient in the sequence and use this rpc to populate "first_variant" for
all variants of a product, this rpc becomes the common link between other
variants. method 3 = apply some logic to determine link between variants,
this will need analysis
- name: variants
singleValue: false
xpath: //import-variant-sku/@data
- name: additionalDescBulletInfo
singleValue: false
xpath: //ul[@class="pdp-features"]/li | //h3[contains(text(), "Product Details")]/following-sibling::div[@class="product-info-description" and not(div[@id="wc-power-page"])]//li
- name: prop65Warning
singleValue: true
description: null
- name: ageSuitability
singleValue: true
description: Recommended age displayed on the product page.
https://www.amazon.com/LEGO-Classic-Medium-Creative-Brick/dp/B00NHQFA1I
example: 4 - 99 years
- name: energyEfficiency
singleValue: true
description: Energy rating of a product.
https://www.amazon.de/Siemens-WM16W541-Waschmaschine-Schnellwaschprogramm-Nachlegefunktion/dp/B015FJFK14
example: A+, A+++, B
- name: technicalInformationPdfPresent
singleValue: true
description: If there is for example a manual in pdf format on the website. ['Yes','No']
example: https://www.amazon.de/Hasbro-Spiele-44220100-Mastermind-Kinderspiel/dp/B0007OHUG6
defaultValue: No
- name: termsAndConditions
singleValue: true
description: Terms and conditions information text ['Yes','No']
defaultValue: No
- name: privacyPolicy
singleValue: true
description: Privacy Policy information text ['Yes','No']
defaultValue: No
- name: customerServiceAvailability
singleValue: true
description: Information related to customer service availability (text), ['Yes','No']
defaultValue: No
- name: materials
singleValue: true
description: Materials used to make the product
example: https://www.jdsports.co.uk/product/blue-adidas-linear-20-reversible-wind-breaker-jacket/15988125/
- name: Image360Present
singleValue: true
xpath: //div[@id="threeSixtyImage"]
description: If 360 image is present in the carousel ['Yes','No']
example: https://www.amazon.com/Trinsic-Single-Handle-Magnetic-Champagne-9159-CZ-DST/dp/B0050EN8E6
defaultValue: No
- name: imageZoomFeaturePresent
singleValue: true
description: If Zoom feature is available for Main image or images in the
carousel,['Yes','No']
example: https://www.zalando.de/adidas-neo-sneaker-low-blackwhite-a4315i002-q11.html
defaultValue: No
- name: shownImages
singleValue: false
xpath: //div[@id='thumbnails']/div[@id='theViews'][count(*)>0]//div[@class='slick-track']/a/img/@src | //div[@id='thumbnails']/div[@id='theViews'][count(*)=0]/../../div[@id='productImageContainer']/div[@id='realHeroContainer']/div/img[1]/@src | //img[@id="productImage"]/@src
regExp: .+(?=&recipe(Id|Name)=d+)
- name: highQualityImages
singleValue: false
xpath: //div[@id='thumbnails']/div[@id='theViews'][count(*)>0]//div[@class='slick-track']/a/img/@src | //div[@id='thumbnails']/div[@id='theViews'][count(*)=0]/../../div[@id='productImageContainer']/div[@id='realHeroContainer']/div/img[1]/@src
regExp: .+(?=&recipe(Id|Name)=d+)
- name: sponsoredProductUrls
singleValue: false
xpath: //h2[contains(text(),'Sponsored Products')]/following::div[@id="hl-prodgroup-viewItem-Carousel"]//a[1]//@href
regExp: (.+)
regExpReplace: https:$1
- name: specifications
xpath: //h3[contains(., 'Specifications')]/..//div[contains(@class, 'product-info-specs')]
description: The physical dimensions of the product including packaging.
- name: sku
xpath: //p[@id='product-body-item-number']
regExp: (d+)
regExpReplace: $1
- name: shortDescription
xpath: //div[contains(@class,"features-container form-group")]//ul[contains(@class,"pdp-features")]//child::li