Last active
April 21, 2020 14:16
-
-
Save scrapehero-code/63bd64202090ecfa226e7881a1e748d6 to your computer and use it in GitHub Desktop.
Sitemap to extract product details from H&M such as product name, price, reviews, description and details using Web Scraper Chrome Extension and Google Chrome
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"_id": "h_and_m", | |
"startUrl": [ | |
"https://www2.hm.com/en_us/women/products/shoes.html?product-type=ladies_shoes&sort=stock&productTypes=shoes&sizes=15_6_6_footwear&colorWithNames=black_000000&image-size=small&image=model&offset=0&page-size=36" | |
], | |
"selectors": [ | |
{ | |
"id": "listing", | |
"type": "SelectorElementClick", | |
"parentSelectors": [ | |
"_root" | |
], | |
"selector": "div.item-details", | |
"multiple": true, | |
"delay": "2000", | |
"clickElementSelector": "button.js-load-more", | |
"clickType": "clickMore", | |
"discardInitialElements": "do-not-discard", | |
"clickElementUniquenessType": "uniqueHTMLText" | |
}, | |
{ | |
"id": "link", | |
"type": "SelectorLink", | |
"parentSelectors": [ | |
"listing" | |
], | |
"selector": "a.link", | |
"multiple": false, | |
"delay": 0 | |
}, | |
{ | |
"id": "name", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"link" | |
], | |
"selector": "h1.primary", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "price", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"link" | |
], | |
"selector": "span.price-value", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "description", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"link" | |
], | |
"selector": "div.pdp-text", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
}, | |
{ | |
"id": "review_count", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"link" | |
], | |
"selector": "span.reviews-number", | |
"multiple": false, | |
"regex": "\\(.*?\\)", | |
"delay": 0 | |
}, | |
{ | |
"id": "details", | |
"type": "SelectorText", | |
"parentSelectors": [ | |
"link" | |
], | |
"selector": "div.product-details-details", | |
"multiple": false, | |
"regex": "", | |
"delay": 0 | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment