如何抓取 Archive.org | Internet Archive 网页抓取工具

from playwright.sync_api import sync_playwright

def scrape_archive():
    with sync_playwright() as p:
        # 启动 headless 浏览器
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # 导航到搜索结果
        page.goto('https://archive.org/search.php?query=web+scraping')
        
        # 等待动态结果加载
        page.wait_for_selector('.item-ia')
        
        # 从列表中提取标题
        items = page.query_selector_all('.item-ia')
        for item in items:
            title = item.query_selector('.ttl').inner_text()
            print(f'提取的标题: {title}')
            
        browser.close()

if __name__ == '__main__':
    scrape_archive()

import scrapy

class ArchiveSpider(scrapy.Spider):
    name = 'archive_spider'
    start_urls = ['https://archive.org/details/movies']

    def parse(self, response):
        # 遍历项目容器
        for item in response.css('.item-ia'):
            yield {
                'title': item.css('.ttl::text').get().strip(),
                'url': response.urljoin(item.css('a::attr(href)').get()),
                'views': item.css('.views::text').get()
            }

        # 使用“下一页”链接处理分页
        next_page = response.css('a.next::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  
  // 访问特定媒体板块
  await page.goto('https://archive.org/details/audio');
  
  // 确保元素已渲染
  await page.waitForSelector('.item-ia');
  
  // 从页面上下文中提取数据
  const data = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.item-ia'));
    return cards.map(card => ({
      title: card.querySelector('.ttl')?.innerText.trim(),
      id: card.getAttribute('data-id')
    }));
  });
  
  console.log(data);
  await browser.close();
})();