如何抓取加州自然资源局 (resources.ca.gov)

from playwright.sync_api import sync_playwright

def scrape_grants():
    with sync_playwright() as p:
        # 启动无头浏览器
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # 导航到补助金机会页面
        page.goto('https://resources.ca.gov/grants')
        
        # 等待内容项加载
        page.wait_for_selector('.grant-item')
        grants = page.query_selector_all('.grant-item')
        
        for grant in grants:
            # 从标题元素中提取标题
            title = grant.query_selector('h3').inner_text()
            print(f'补助金机会: {title}')
            
        browser.close()

scrape_grants()

import scrapy

class CNRASpider(scrapy.Spider):
    name = 'cnra'
    start_urls = ['https://resources.ca.gov/Newsroom']

    def parse(self, response):
        # 循环遍历每个新闻文章列表项
        for article in response.css('div.news-list-item'):
            yield {
                'title': article.css('h3::text').get().strip(),
                'link': article.css('a::attr(href)').get()
            }

        # 如果存在“下一页”按钮，处理简单的分页
        next_page = response.css('a.next::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  // 启动浏览器并打开新页面
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // 前往“关于我们”领导层页面
  await page.goto('https://resources.ca.gov/About-Us/Who-We-Are');
  
  // 提取领导层个人资料数据
  const leadership = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.staff-profile')).map(p => p.innerText.trim());
  });
  
  console.log('机构领导层:', leadership);
  await browser.close();
})();