2025 年如何爬取 YouTube：提取视频数据和评论

from playwright.sync_api import sync_playwright

def scrape_youtube_comments(url):
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto(url)
        page.evaluate('window.scrollTo(0, 600)')
        page.wait_for_selector('#comments', timeout=10000)
        for _ in range(3):
            page.evaluate('window.scrollBy(0, 2000)')
            page.wait_for_timeout(2000)
        comments = page.query_selector_all('#content-text')
        for comment in comments[:10]:
            print(f'找到评论: {comment.inner_text()}')
        browser.close()

scrape_youtube_comments('https://www.youtube.com/watch?v=uIJuGOBhxSs')

import scrapy

class YoutubeSpider(scrapy.Spider):
    name = 'youtube_spider'
    start_urls = ['https://www.youtube.com/watch?v=uIJuGOBhxSs']

    def parse(self, response):
        yield {
            'title': response.css('meta[property="og:title"]::attr(content)').get(),
            'views': response.css('meta[itemprop="interactionCount"]::attr(content)').get(),
            'upload_date': response.css('meta[itemprop="datePublished"]::attr(content)').get()
        }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.goto('https://www.youtube.com/watch?v=uIJuGOBhxSs');
  await page.evaluate(() => window.scrollBy(0, window.innerHeight));
  await page.waitForSelector('#content-text', { timeout: 15000 });
  const comments = await page.evaluate(() => {
    const elements = Array.from(document.querySelectorAll('#content-text'));
    return elements.map(el => el.textContent.trim());
  });
  console.log('示例评论:', comments.slice(0, 5));
  await browser.close();
})();