AliExpressをスクレイピングする方法：究極の2025年データ抽出ガイド

from playwright.sync_api import sync_playwright

def scrape_aliexpress(search_term):
    with sync_playwright() as p:
        # Launching with stealth-like configurations
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = context.new_page()
        
        url = f'https://www.aliexpress.com/wholesale?SearchText={search_term}'
        page.goto(url, wait_until='networkidle')
        
        # Wait for product grid to appear
        page.wait_for_selector('[class*="multi--container"]', timeout=10000)
        
        products = page.query_selector_all('[class*="multi--container"]')
        for product in products:
            title = product.query_selector('[class*="multi--title"]').inner_text()
            price = product.query_selector('[class*="multi--price-sale"]').inner_text()
            print(f'Product: {title} | Price: {price}')
            
        browser.close()

scrape_aliexpress('mechanical keyboard')

import scrapy

class AliExpressSpider(scrapy.Spider):
    name = 'aliexpress'
    start_urls = ['https://www.aliexpress.com/w/wholesale-drone.html']

    def parse(self, response):
        # AliExpress often hides data in window.runParams script tags
        for product in response.css('.search-item'):
            yield {
                'title': product.css('h3::text').get(),
                'price': product.css('.price--current::text').get(),
                'rating': product.css('.rating-value::text').get(),
                'sold': product.css('.sale-value::text').get()
            }

        # Basic pagination handling
        next_page = response.css('a.next-pagination-item::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: "new" });
  const page = await browser.newPage();
  
  // Set a realistic User-Agent
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  
  await page.goto('https://www.aliexpress.com/w/wholesale-camera.html', { waitUntil: 'networkidle2' });
  
  // Evaluate the page to extract titles
  const results = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('h3'));
    return items.map(h => h.innerText.trim());
  });

  console.log('Scraped Titles:', results);
  await browser.close();
})();