How to Scrape Amazon Product Data: Using Code and No Code Approaches

import asyncio
import json

from playwright.async_api import async_playwright

url = "https://www.amazon.com/Imploding-Kittens-First-Expansion-Exploding/dp/B01HSIIFQ2/]?th=1"


async def extract_data(page) -> list:
    """
    Parsing details from the product page

    Args:
        page: webpage of the browser

    Returns:
        list: details of product on amazon
    """

    # Initializing selectors and xpaths
    title_xpath = "h1[id='title']"
    asin_selector = "//td/div[@id='averageCustomerReviews']"
    rating_xpath = "//div[@id='prodDetails']//i[contains(@class,'review-stars')]/span"
    ratings_count_xpath = "//div[@id='prodDetails']//span[@id='acrCustomerReviewText']"
    selling_price_xpath = "//input[@id='priceValue']"
    listing_price_xpath = "//div[@id='apex_desktop_qualifiedBuybox']//span[@class='a-price a-text-price']/span[@class='a-offscreen']"
    img_link_xpath = "//div[contains(@class,'imgTagWrapper')]//img"
    brand_xpath = (
        "//tr[contains(@class,'po-brand')]//span[@class='a-size-base po-break-word']"
    )
    status_xpath = "//div[@id='availabilityInsideBuyBox_feature_div']//div[@id='availability']/span"
    description_ul_xpath = (
        "//ul[@class='a-unordered-list a-vertical a-spacing-mini']/li"
    )
    product_description_xpath = "//div[@id='productDescription']//span"

    # Waiting for the page to finish loading
    await page.wait_for_selector(title_xpath)

    # Extracting the elements
    product_title = (
        await page.locator(title_xpath).inner_text()
        if await page.locator(title_xpath).count()
        else None
    )
    asin = (
        await page.locator(asin_selector).get_attribute("data-asin")
        if await page.locator(asin_selector).count()
        else None
    )
    rating = (
        await page.locator(rating_xpath).inner_text()
        if await page.locator(rating_xpath).count()
        else None
    )
    rating_count = (
        await page.locator(ratings_count_xpath).inner_text()
        if await page.locator(ratings_count_xpath).count()
        else None
    )
    selling_price = (
        await page.locator(selling_price_xpath).get_attribute("value")
        if await page.locator(selling_price_xpath).count()
        else None
    )
    listing_price = (
        await page.locator(listing_price_xpath).inner_text()
        if await page.locator(listing_price_xpath).count()
        else None
    )
    brand = (
        await page.locator(brand_xpath).inner_text()
        if await page.locator(brand_xpath).count()
        else None
    )
    product_description = (
        await page.locator(product_description_xpath).inner_text()
        if await page.locator(product_description_xpath).count()
        else None
    )
    image_link = (
        await page.locator(img_link_xpath).get_attribute("src")
        if await page.locator(img_link_xpath).count()
        else None
    )
    status = (
        await page.locator(status_xpath).inner_text()
        if await page.locator(status_xpath).count()
        else None
    )

    # full_description is found as list, so iterating the list elements to get the descriptions
    full_description_list = []
    desc_lists = page.locator(description_ul_xpath)
    desc_count = await desc_lists.count()
    for index in range(desc_count):
        li_element = desc_lists.nth(index=index)
        desc = (
            await li_element.locator("//span").inner_text()
            if await li_element.locator("//span").count()
            else None
        )
        full_description_list.append(desc)
    full_description = " | ".join(full_description_list)

    # cleaning data
    product_title = clean_data(product_title)
    asin = clean_data(asin)
    rating = clean_data(rating)
    rating_count = clean_data(rating_count)
    selling_price = clean_data(selling_price)
    listing_price = clean_data(listing_price)
    brand = clean_data(brand)
    image_link = clean_data(image_link)
    status = clean_data(status)
    product_description = clean_data(product_description)
    full_description = clean_data(full_description)

    data_to_save = {
        "product_title": product_title,
        "asin": asin,
        "rating": rating,
        "rating_count": rating_count,
        "selling_price": selling_price,
        "listing_price": listing_price,
        "brand": brand,
        "image_links": image_link,
        "status": status,
        "product_description": product_description,
        "full_description": full_description,
    }

    save_data(data_to_save, "Data.json")


async def run(playwright) -> None:
    # Initializing the browser and creating a new page.
    browser = await playwright.chromium.launch(headless=False)
    context = await browser.new_context()
    page = await context.new_page()

    await page.set_viewport_size({"width": 1920, "height": 1080})
    page.set_default_timeout(300000)

    # Navigating to the homepage
    await page.goto(url, wait_until="domcontentloaded")
    await extract_data(page)

    await context.close()
    await browser.close()


def clean_data(data: str) -> str:
    """
    Cleaning data by removing extra white spaces and Unicode characters

    Args:
        data (str): data to be cleaned

    Returns:
        str: cleaned string
    """
    if not data:
        return None
    cleaned_data = " ".join(data.split()).strip()
    cleaned_data = cleaned_data.encode("ascii", "ignore").decode("ascii")
    return cleaned_data


def save_data(product_page_data: dict, filename: str):
    """Converting a list of dictionaries to JSON format

    Args:
        product_page_data (list): details of each product
        filename (str): name of the JSON file
    """
    with open(filename, "w") as outfile:
        json.dump(product_page_data, outfile, indent=4)


async def main() -> None:
    async with async_playwright() as playwright:
        await run(playwright)


if __name__ == "__main__":
    asyncio.run(main())