كيفية scraping موقع RethinkEd: دليل تقني لاستخراج البيانات

import asyncio
from playwright.async_api import async_playwright

async def scrape_rethinked():
    async with async_playwright() as p:
        # Launch a headed or headless browser
        browser = await p.chromium.launch(headless=True)
        # Create a new context with custom User-Agent
        context = await browser.new_context(
            user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36'
        )
        page = await context.new_page()
        
        # Navigate to the Success Stories page
        await page.goto('https://www.rethinked.com/success-stories/', wait_until='networkidle')
        
        # Wait for Elementor post items to render
        await page.wait_for_selector('.elementor-post__title')
        
        stories = await page.query_selector_all('.elementor-post__title')
        for story in stories:
            text = await story.inner_text()
            print(f'Success Story: {text.strip()}')
        
        await browser.close()

asyncio.run(scrape_rethinked())

import scrapy

class RethinkEdSpider(scrapy.Spider):
    name = 'rethink_spider'
    allowed_domains = ['rethinked.com']
    start_urls = ['https://www.rethinked.com/resources/']

    def parse(self, response):
        # Iterate through Elementor post elements
        for item in response.css('article.elementor-post'):
            yield {
                'title': item.css('h2.elementor-post__title a::text').get(default='').strip(),
                'link': item.css('a.elementor-post__read-more::attr(href)').get(),
                'category': item.css('.elementor-post__badge::text').get(),
                'excerpt': item.css('.elementor-post__excerpt p::text').get(),
            }

        # Follow pagination link for next page
        next_page = response.css('a.next.page-numbers::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();

  // Set a realistic User-Agent
  await page.setUserAgent('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');

  try {
    await page.goto('https://www.rethinked.com/resources/', { waitUntil: 'networkidle2' });

    // Extract data from the page content
    const resources = await page.evaluate(() => {
      const items = Array.from(document.querySelectorAll('article'));
      return items.map(el => ({
        title: el.querySelector('h2')?.innerText.trim(),
        url: el.querySelector('a')?.href,
        badge: el.querySelector('.elementor-post__badge')?.innerText.trim()
      }));
    });

    console.log(resources);
  } catch (err) {
    console.error('Scraping failed:', err);
  } finally {
    await browser.close();
  }
})();