cops

## refs: https://www.blog.datahut.co/post/scraping-amazon-product-category

async def get_technical_details(page):
    try:
        # Get table containing technical details and its rows
        table_element = await page.query_selector("#productDetails_techSpec_section_1")
        rows = await table_element.query_selector_all("tr")

        # Initialize dictionary to store technical details
        technical_details = {}

        # Iterate over rows and extract key-value pairs
        for row in rows:
            # Get key and value elements for each row
            key_element = await row.query_selector("th")
            value_element = await row.query_selector("td")

            # Extract text content of key and value elements
            key = await page.evaluate('(element) => element.textContent', key_element)
            value = await page.evaluate('(element) => element.textContent', value_element)

            # Strip whitespace and unwanted characters from value and add key-value pair to dictionary
            value = value.strip().replace('\u200e', '')
            technical_details[key.strip()] = value

        # Extract required technical details (colour, capacity, wattage, country of origin)
        colour = technical_details.get('Colour', 'Not Available')
        if colour == 'Not Available':
            # Get the colour element from the page and extract its inner text
            colour_element = await page.query_selector('.po-color .a-span9')
            if colour_element:
                colour = await colour_element.inner_text()
                colour = colour.strip()

        capacity = technical_details.get('Capacity', 'Not Available')
        if capacity == 'Not Available' or capacity == 'default':
            # Get the capacity element from the page and extract its inner text
            capacity_element = await page.query_selector('.po-capacity .a-span9')
            if capacity_element:
                capacity = await capacity_element.inner_text()
                capacity = capacity.strip()

        wattage = technical_details.get('Wattage', 'Not Available')
        if wattage == 'Not Available' or wattage == 'default':
            # Get the wattage element from the page and extract its inner text
            wattage_elem = await page.query_selector('.po-wattage .a-span9')
            if wattage_elem:
                wattage = await wattage_elem.inner_text()
                wattage = wattage.strip()

        country_of_origin = technical_details.get('Country of Origin', 'Not Available')

        # Return technical details and required fields
        return technical_details, colour, capacity, wattage, country_of_origin

    except:
        # Set technical details to default values if table element or any required element is not found or text content cannot be extracted
        return {}, 'Not Available', 'Not Available', 'Not Available', 'Not Available'



# 2
async def get_bullet_points(page):
    bullet_points = []
    try:
        # Try to get the unordered list element containing the bullet points
        ul_element = await page.query_selector('#feature-bullets ul.a-vertical')

        # Get all the list item elements under the unordered list element
        li_elements = await ul_element.query_selector_all('li')

        # Loop through each list item element and append the inner text to the bullet points list
        for li in li_elements:
            bullet_points.append(await li.inner_text())
    except:
        # If the unordered list element or list item elements are not found, assign an empty list to bullet points
        bullet_points = []

    # Return the list of bullet points
    return bullet_points