Yahoo Financeをスクレイピングする方法：株価データの抽出

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # 本物のブラウザプロファイルで起動することで、基本的な検知を回避できます
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://finance.yahoo.com/quote/TSLA')
        
        # JSによって価格要素が更新されるのを待ちます
        page.wait_for_selector('fin-streamer[data-field="regularMarketPrice"]')
        
        price = page.inner_text('fin-streamer[data-field="regularMarketPrice"]')
        name = page.inner_text('h1')
        
        print(f'{name}: {price}')
        browser.close()

run()

import scrapy

class YahooFinanceSpider(scrapy.Spider):
    name = 'yahoo_finance'
    start_urls = ['https://finance.yahoo.com/quote/NVDA']

    def parse(self, response):
        yield {
            'ticker': 'NVDA',
            'current_price': response.css('fin-streamer[data-field="regularMarketPrice"]::attr(value)').get(),
            'market_cap': response.xpath('//td[@data-test="MARKET_CAP-value"]/text()').get(),
            'pe_ratio': response.xpath('//td[@data-test="PE_RATIO-value"]/text()').get()
        }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  // Puppeteerでは、現実的なUser-Agentの設定が極めて重要です
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  
  await page.goto('https://finance.yahoo.com/quote/MSFT');
  
  const data = await page.evaluate(() => {
    return {
      price: document.querySelector('fin-streamer[data-field="regularMarketPrice"]').innerText,
      prevClose: document.querySelector('td[data-test="PREV_CLOSE-value"]').innerText
    };
  });

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