WebElementsのスクレイピング方法：周期表データ取得ガイド

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        # 元素はメインの周期表からリンクされています
        page.goto('https://www.webelements.com/iron/')
        
        # プロパティテーブルが表示されるまで待機
        page.wait_for_selector('table')
        
        element_data = {
            'name': page.inner_text('h1'),
            'density': page.locator('th:has-text("Density") + td').inner_text().strip()
        }
        
        print(element_data)
        browser.close()

run()

import scrapy

class ElementsSpider(scrapy.Spider):
    name = 'elements'
    start_urls = ['https://www.webelements.com/']

    def parse(self, response):
        # 周期表内の各元素へのリンクをたどる
        for link in response.css('table a[title]::attr(href)'):
            yield response.follow(link, self.parse_element)

    def parse_element(self, response):
        yield {
            'name': response.css('h1::text').get().strip(),
            'symbol': response.xpath('//th[contains(text(), "Symbol")]/following-sibling::td/text()').get().strip(),
            'atomic_number': response.xpath('//th[contains(text(), "Atomic number")]/following-sibling::td/text()').get().strip(),
        }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.goto('https://www.webelements.com/silver/');

  const data = await page.evaluate(() => {
    const name = document.querySelector('h1').innerText;
    const meltingPoint = Array.from(document.querySelectorAll('th'))
      .find(el => el.textContent.includes('Melting point'))
      ?.nextElementSibling.innerText;
    return { name, meltingPoint };
  });

  console.log('Extracted Data:', data);
  await browser.close();
})();