如何爬取 Lapa Ninja 获取设计灵感

from playwright.sync_api import sync_playwright

def scrape_lapa():
    with sync_playwright() as p:
        # Launch headless browser
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://www.lapa.ninja/post/')
        
        # Handle infinite scroll
        for _ in range(5):
            page.evaluate('window.scrollBy(0, 1500)')
            page.wait_for_timeout(2000)
        
        # Extract design titles
        titles = page.locator('.post-item h3').all_text_contents()
        print(f'Extracted {len(titles)} designs')
        browser.close()

scrape_lapa()

import scrapy

class LapaSpider(scrapy.Spider):
    name = 'lapa_ninja'
    start_urls = ['https://www.lapa.ninja/post/']

    def parse(self, response):
        # Loop through each design item
        for post in response.css('.post-item'):
            yield {
                'title': post.css('h3::text').get(),
                'link': post.css('a::attr(href)').get(),
                'image': post.css('img::attr(src)').get()
            }
        
        # Follow simple pagination link if available
        next_page = response.css('a.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();
  // Go to homepage with network idle condition
  await page.goto('https://www.lapa.ninja/', { waitUntil: 'networkidle2' });
  
  // Extract titles using document evaluation
  const data = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.post-item h3')).map(h => h.innerText);
  });
  
  console.log('Design Titles:', data);
  await browser.close();
})();