如何抓取 Maven.com 课程和讲师数据

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://maven.com/courses')
        
        # 等待课程渲染
        page.wait_for_selector('h3')
        
        # 向下滚动以触发懒加载
        page.evaluate('window.scrollBy(0, 1000)')
        
        # 提取数据
        courses = page.query_selector_all('div[class*="CourseCard"]')
        for course in courses:
            title = course.query_selector('h3').inner_text()
            print(f'已抓取: {title}')
            
        browser.close()

run()

import scrapy

class MavenSpider(scrapy.Spider):
    name = 'maven_spider'
    start_urls = ['https://maven.com/courses']

    def parse(self, response):
        for course in response.css('div[class*="CourseCard"]'):
            yield {
                'title': course.css('h3::text').get(),
                'instructor': course.css('span[class*="InstructorName"]::text').get(),
                'price': course.css('div[class*="Price"]::text').get()
            }
            
        # 分页逻辑（如果存在下一页链接）
        next_page = response.css('a[aria-label="Next page"]::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://maven.com/courses', { waitUntil: 'networkidle2' });

  const results = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('h3')).map(el => el.innerText);
  });

  console.log('课程:', results);
  await browser.close();
})();