如何抓取 Vimeo：视频元数据提取指南

from playwright.sync_api import sync_playwright

def scrape_vimeo_dynamic():
    with sync_playwright() as p:
        # 启动有界面浏览器有时可以绕过基础的机器人检测
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/119.0.0.0 Safari/537.36')
        page = context.new_page()
        
        # 导航到类别页面
        page.goto('https://vimeo.com/channels/staffpicks')
        
        # 等待视频卡片渲染
        page.wait_for_selector('div[data-testid="video-card"]', timeout=10000)
        
        # 提取标题
        titles = page.locator('h3').all_inner_texts()
        for title in titles:
            print(f'发现视频: {title}')
            
        browser.close()

if __name__ == '__main__':
    scrape_vimeo_dynamic()

import scrapy

class VimeoSpider(scrapy.Spider):
    name = 'vimeo_spider'
    start_urls = ['https://vimeo.com/search?q=animation']
    
    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
        'CONCURRENT_REQUESTS': 1,
        'DOWNLOAD_DELAY': 3
    }

    def parse(self, response):
        # Scrapy 可以解析 script 标签内的 JSON，以获取更可靠的数据
        for video in response.css('div.iris_video-vital'):
            yield {
                'title': video.css('a::text').get(),
                'link': response.urljoin(video.css('a::attr(href)').get()),
                'author': video.css('span.author::text').get()
            }
            
        next_page = response.css('a[rel="next"]::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/115.0.0.0 Safari/537.36');
  
  await page.goto('https://vimeo.com/watch', { waitUntil: 'networkidle2' });

  // 滚动以触发懒加载
  await page.evaluate(() => window.scrollBy(0, window.innerHeight));
  
  const videoData = await page.evaluate(() => {
    const titles = Array.from(document.querySelectorAll('h3'));
    return titles.map(t => t.innerText);
  });

  console.log('抓取到的视频标题:', videoData);

  await browser.close();
})();