Thrillophiliaのツアーパッケージとレビューをスクレイピングする方法

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # Launching with a real browser profile helps bypass basic detections
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://www.thrillophilia.com/destinations/egypt/tours', wait_until='networkidle')
        
        # Wait for tour cards to load dynamically
        page.wait_for_selector('.tour-card')
        
        tours = page.query_selector_all('.tour-card')
        for tour in tours:
            title = tour.query_selector('h3').inner_text()
            print(f'Extracted: {title}')
            
        browser.close()

run()

import scrapy

class ThrillSpider(scrapy.Spider):
    name = 'thrillophilia'
    start_urls = ['https://www.thrillophilia.com/destinations/japan/tours']

    def parse(self, response):
        for tour in response.css('.tour-card'):
            yield {
                'title': tour.css('h3::text').get(),
                'price': tour.css('.current-price::text').get(),
                'rating': tour.css('.rating-value::text').get()
            }
        
        # Handling pagination
        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();
  await page.goto('https://www.thrillophilia.com/destinations/maldives');
  
  // Execute script in browser context to extract data
  const tours = await page.evaluate(() => {
    const items = document.querySelectorAll('.tour-card');
    return Array.from(items).map(item => ({
      title: item.querySelector('h3')?.innerText,
      price: item.querySelector('.price')?.innerText
    }));
  });

  console.log(tours);
  await browser.close();
})();