how to create array of object inside object in puppeteer - node.js

Question

I want to create array of object of product sizes inside array of object of product info.
this is the HTML tree I am trying to scrape
<div class="product-thumbShim"></div><a target="_blank" href="tshirts/herenow/herenow-men-black-printed-round-neck-t-shirt/4318138/buy" style="display: block;"><div class="product-imageSliderContainer"><div class="product-sliderContainer" style="display: block;"><div style="background: rgb(244, 255, 249);"><div style="height: 280px; width: 100%;"><picture class="img-responsive" style="width: 100%; height: 100%; display: block;"><source srcset="
https://assets.myntassets.com/f_webp,dpr_1.0,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg ,
https://assets.myntassets.com/f_webp,dpr_1.5,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 1.5x,
https://assets.myntassets.com/f_webp,dpr_1.8,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 1.8x,
https://assets.myntassets.com/f_webp,dpr_2.0,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 2.0x,
https://assets.myntassets.com/f_webp,dpr_2.2,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 2.2x,
https://assets.myntassets.com/f_webp,dpr_2.4,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 2.4x,
https://assets.myntassets.com/f_webp,dpr_2.6,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 2.6x,
https://assets.myntassets.com/f_webp,dpr_2.8,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg 2.8x" type="image/webp"><img src="https://assets.myntassets.com/dpr_2,q_60,w_210,c_limit,fl_progressive/assets/images/4318138/2018/5/4/11525433792765-HERENOW-Men-Black-Printed-Round-Neck-T-shirt-2881525433792598-1.jpg" class="img-responsive" alt="HERE&NOW Men Black Printed Round Neck T-shirt" title="HERE&NOW Men Black Printed Round Neck T-shirt" style="width: 100%; display: block;"></picture></div></div></div></div><div class="product-productMetaInfo"><h3 class="product-brand">HERE&NOW</h3><h4 class="product-product">Men Printed Round Neck T-shirt</h4><h4 class="product-sizes"><!-- react-text: 396 -->Sizes: <!-- /react-text --><span class="product-sizeInventoryPresent">S, </span><span class="product-sizeInventoryPresent">M, </span><span class="product-sizeInventoryPresent">L, </span><span class="product-sizeInventoryPresent">XL, </span><span class="product-sizeInventoryPresent">XXL</span></h4><div class="product-price"><span><span class="product-discountedPrice"><!-- react-text: 405 -->Rs. <!-- /react-text --><!-- react-text: 406 -->374<!-- /react-text --></span><span class="product-strike"><!-- react-text: 408 -->Rs. <!-- /react-text --><!-- react-text: 409 -->749<!-- /react-text --></span></span><span class="product-discountPercentage">(50% OFF)</span></div></div></a><div class="image-grid-similarColorsCta product-similarItemCta"><span class="myntraweb-sprite image-grid-similarColorsIcon sprites-similarProductsIcon"></span><span class="image-grid-iconText">VIEW SIMILAR</span></div><div class="product-actions "><span class="product-actionsButton product-wishlist " style="width: 100%; text-align: center;"><!-- react-text: 416 -->wishlist<!-- /react-text --></span></div><div class="product-sizeDisplayDiv"><div class="product-sizeDisplayHeader"><span>Select a size</span><span class="myntraweb-sprite product-sizeDisplayRemoveMark sprites-remove"></span></div><div class="product-sizeButtonsContaier"><button class="product-sizeButton">S</button><button class="product-sizeButton">M</button><button class="product-sizeButton">L</button><button class="product-sizeButton">XL</button><button class="product-sizeButton">XXL</button></div></div>"
adn this is my current output
[
{
brandName: 'max',
productName: 'Colourblocked Round Neck T-shirt',
productSizes: 'Sizes: S, M, L, XL, XXL'
},
{
brandName: 'YOLOCLAN',
productName: 'Printed Round Neck T-shirt',
productSizes: 'Sizes: S, M, L, XL, XXL, 3XL'
},
{
brandName: 'Maniac',
productName: 'Colourblocked Hooded T-shirt',
productSizes: 'Sizes: S, M, L, XL'
}
]
and my expected output is
[
{
brandName: 'max',
productName: 'Colourblocked Round Neck T-shirt',
productSizes: [
Size: 'S',
Size: 'M',
Size: 'L',
]
}
]
current code :
const res = await page.$$eval(".product-base", (productInfo) =>
productInfo.map((product) => {
return {
brandName: product.querySelector(".product-brand").innerText,
productName: product.querySelector(".product-product").innerText,
productSizes: product.querySelector(".product-sizes").innerText,
};
}),
);
and also how often I can scrape websites in order to not get my IP blocked

Answer 1

You could do something like this:
const res = await page.$$eval(".product-base", (productInfo) =>
productInfo.map((product) => {
let productSizeText = product.querySelector(".product-sizes").innerText;
let productSizeArr = productSizeText.replace('Sizes:', '').trim().split(',');
return {
brandName: product.querySelector(".product-brand").innerText,
productName: product.querySelector(".product-product").innerText,
productSizes: productSizeArr,
};
}),
);

Answer 2

Second answer for the HTML URLs: Using Puppeteer.js you can get the source tag URLs like below:
let imageURLArr = await page.evaluate(() => {
//This will get the first sourceTag of the DOM, change the value 0 according to your DOM that you are scraping if it has more source tags and is not the first source tag element
let sourceTag = document.getElementsByTagName('source')[0];
// check selector exists
if (sourceTag) {
// This will give you all the image URLs of source tag
let imagURLs = sourceTag.getAttribute('srcset')
return imagURLs;
}
});
console.log(imageURLArr);