Statistaをスクレイピングする方法：市場データ抽出の究極ガイド

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # パフォーマンス向上のためheadless=Trueでブラウザを起動
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://www.statista.com/statistics/popular/')
        # 動的なチャート要素がロードされるのを待機
        page.wait_for_selector('.contentList__item')
        
        stats = page.query_selector_all('.contentList__item h3')
        for stat in stats:
            print(f'抽出済み: {stat.inner_text()}')
        
        browser.close()

run()

import scrapy

class StatistaSpider(scrapy.Spider):
    name = 'statista_spider'
    allowed_domains = ['statista.com']
    start_urls = ['https://www.statista.com/topics/']

    def parse(self, response):
        # トピックのタイトルとリンクを抽出
        for topic in response.css('.topicCard__title'):
            yield {
                'topic': topic.css('::text').get().strip(),
                'link': response.urljoin(topic.css('a::attr(href)').get())
            }
        
        # 次のページボタンを追ってパージネーションを処理
        next_page = response.css('a.pagination__next::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  
  await page.goto('https://www.statista.com/search/?q=finance');
  await page.waitForSelector('.searchItem');

  // 評価ロジックを使用してタイトルのリストを抽出
  const data = await page.$$eval('.searchItem__title', elements => 
    elements.map(el => el.innerText.trim())
  );

  console.log(data);
  await browser.close();
})();