Web スクレイピングが簡単に: Puppeteer であらゆる HTML ページを解析

npm i puppeteer # Downloads compatible Chrome during installation.
npm i puppeteer-core # Alternatively, install as a library, without downloading Chrome.

yarn add puppeteer // Downloads compatible Chrome during installation.
yarn add puppeteer-core // Alternatively, install as a library, without downloading Chrome.

pnpm add puppeteer # Downloads compatible Chrome during installation.
pnpm add puppeteer-core # Alternatively, install as a library, without downloading Chrome.

const puppeteer = require("puppeteer");
const CategorySchema = require("./models/Category");

// Define the scrape function as a named async function
const scrape = async () => {
    // Launch a new browser instance
    const browser = await puppeteer.launch({ headless: false });

    // Open a new page
    const page = await browser.newPage();

    // Navigate to the target URL and wait until the DOM is fully loaded
    await page.goto('https://www.myntra.com/mens-sport-wear?rawQuery=mens%20sport%20wear', { waitUntil: 'domcontentloaded' });

    // Wait for additional time to ensure all content is loaded
    await new Promise((resolve) => setTimeout(resolve, 25000));

    // Extract product details from the page
    const items = await page.evaluate(() => {
        // Select all product elements
        const elements = document.querySelectorAll('.product-base');
        const elementsArray = Array.from(elements);

        // Map each element to an object with the desired properties
        const results = elementsArray.map((element) => {
            const image = element.querySelector(".product-imageSliderContainer img")?.getAttribute("src");
            return {
                image: image ?? null,
                brand: element.querySelector(".product-brand")?.textContent,
                title: element.querySelector(".product-product")?.textContent,
                discountPrice: element.querySelector(".product-price .product-discountedPrice")?.textContent,
                actualPrice: element.querySelector(".product-price .product-strike")?.textContent,
                discountPercentage: element.querySelector(".product-price .product-discountPercentage")?.textContent?.split(' ')[0]?.slice(1, -1),
                total: 20, // Placeholder value, adjust as needed
                available: 10, // Placeholder value, adjust as needed
                ratings: Math.round((Math.random() * 5) * 10) / 10 // Random rating for demonstration
            };
        });

        return results; // Return the list of product details
    });

    // Close the browser
    await browser.close();

    // Prepare the data for saving
    const data = {
        category: "mens-sport-wear",
        subcategory: "Mens",
        list: items
    };

    // Create a new Category document and save it to the database
    // Since we want to store product information in our e-commerce store, we use a schema and save it to the database.
    // If you don't need to save the data, you can omit this step.
    const category = new CategorySchema(data);
    console.log(category);
    await category.save();

    // Return the scraped items
    return items;
};

// Export the scrape function as the default export
module.exports = scrape;