Hi everyone,
I’m working on scraping product data from Douglas.pl , and I need some help refining my sitemap. My goal is to extract all key product details, including:
-
Product Name, Category, Price, Images, Description
-
Variants (Color & Size) – these open in new links
-
Additional product details like bullet points, ingredients, and usage instructions
-
Variant thumbnail images (for different color/size options)
-
All images from the product image carousel
I’ve already set up pagination and product navigation, so moving between products works fine. However, I need help with:
• Scraping product variants that open in separate links
• Extracting text from tabs like “Usage” and “Ingredients,” which require clicking to reveal their content
• Capturing the thumbnail image of each variant
• Scraping all images from the product image carousel
• Ensuring all elements are captured correctly without missing data
I would really appreciate it if someone could review my sitemap and help me improve it. If you have any suggestions or fixes, please let me know!
Thanks in advance!
{"_id":"DOUGLAS","startUrl":["https://www.douglas.pl/pl/b/clinique/b0008"],"selectors":[{"id":"Links","multiple":true,"parentSelectors":["_root"],"selector":".product-tile__details-container a","type":"SelectorLink"},{"id":"Pages","multiple":true,"parentSelectors":["_root"],"selector":"a[aria-label='Następna strona']","type":"SelectorLink"},{"id":"Product Container","multiple":false,"parentSelectors":["Links"],"selector":"div.product-detail-page","type":"SelectorElement"},{"clickElementSelector":"div.qmnIqJ8ZYN7t4J90JliX","clickElementUniquenessType":"uniqueCSSSelector","clickType":"clickOnce","delay":5000,"discardInitialElements":"do-not-discard","id":"Variant Color","multiple":true,"parentSelectors":["Product Container"],"selector":".product-detail__variant-selector","type":"SelectorElementClick"},{"clickElementSelector":"label","clickElementUniquenessType":"uniqueCSSSelector","clickType":"clickOnce","delay":5000,"discardInitialElements":"do-not-discard","id":"Variant Size","multiple":true,"parentSelectors":["Product Container"],"selector":"div.product-cockpit__variant","type":"SelectorElementClick"},{"extractAttribute":"src","id":"Images stack","parentSelectors":["Product Container"],"selector":".quVF6VQW9GvLTmkZ0hDj img","type":"SelectorGroup"},{"id":"Image-one","multiple":false,"parentSelectors":["Product Container"],"selector":".main-media__main-image-container img","type":"SelectorImage"},{"id":"Variant Thumbnail","multiple":false,"parentSelectors":["Product Container"],"selector":".variant-thumbnail img","type":"SelectorImage"},{"id":"Carousel Images","multiple":true,"parentSelectors":["Product Container"],"selector":".product-carousel img","type":"SelectorGroup","extractAttribute":"src"},{"id":"Category","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":".product-cockpit__breadcrumb span:nth-of-type(4) a","type":"SelectorText"},{"id":"Name","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":".product-cockpit__breadcrumb span[data-testid]","type":"SelectorText"},{"id":"Color","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":"span[data-testid='variant-selector-dropdown-name']","type":"SelectorText"},{"id":"Price","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":".product-price__discount span.product-price__price, .product-price .product-price__base span.product-price__price","type":"SelectorText"},{"id":"Size","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":"div.product-detail__variant-name","type":"SelectorText"},{"id":"Bullet","multiple":true,"parentSelectors":["Product Container"],"regex":"","selector":".bullet-points li","type":"SelectorText"},{"id":"Detail","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":"div.hbqjtcyY4DmGUU0ezjD6","type":"SelectorText"},{"id":"Description","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":"div.truncate","type":"SelectorText"},{"id":"Kontakt producenta","multiple":false,"parentSelectors":["Product Container"],"regex":"","selector":".AMwnL9Fw8t0XAAZ4SMJ9 div:nth-of-type(2)","type":"SelectorText"},{"clickElementSelector":"li.react-tabs__tab:nth-of-type(2)","clickElementUniquenessType":"uniqueCSSSelector","clickType":"clickOnce","delay":2000,"discardInitialElements":"do-not-discard","id":"Stosowanie Click","multiple":false,"parentSelectors":["Product Container"],"selector":"div.product-detail-content","type":"SelectorElementClick"},{"id":"Stosowanie","multiple":false,"parentSelectors":["Stosowanie Click"],"regex":"","selector":"div.product-detail-other-info__html","type":"SelectorText"},{"clickElementSelector":"li.react-tabs__tab:nth-of-type(3)","clickElementUniquenessType":"uniqueCSSSelector","clickType":"clickOnce","delay":3000,"discardInitialElements":"do-not-discard","id":"Skladniki Click","multiple":false,"parentSelectors":["Product Container"],"selector":"div.product-detail-content","type":"SelectorElementClick"},{"id":"Skladniki","multiple":false,"parentSelectors":["Skladniki Click"],"regex":"","selector":"div.product-detail-other-info__html","type":"SelectorText"}]}