如何抓取美国自然历史博物馆 (AMNH) 数据

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://data.amnh.org/anthropology/collections')
        
        # 等待动态结果加载
        page.wait_for_selector('.specimen-result-item')
        
        # 提取数据
        items = page.eval_on_selector_all('.specimen-result-item', 'elements => elements.map(e => e.innerText)')
        for item in items:
            print(item)
        
        browser.close()
run()

import scrapy

class AmnhSpider(scrapy.Spider):
    name = 'amnh'
    start_urls = ['https://www.amnh.org/exhibitions']

    def parse(self, response):
        # 抓取展览标题和链接
        for exhibit in response.css('.exhibit-card'):
            yield {
                'title': exhibit.css('.title::text').get(),
                'link': exhibit.css('a::attr(href)').get()
            }

        # 如果有分页，则跟随分页链接
        next_page = response.css('a.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.goto('https://www.amnh.org/calendar');

  // 等待日历活动加载
  await page.waitForSelector('.event-item');

  const events = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.event-item')).map(event => ({
      title: event.querySelector('.event-title').innerText,
      date: event.querySelector('.event-date').innerText
    }));
  });

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