كيفية كشط Guru.com: دليل شامل حول web scraping

from playwright.sync_api import sync_playwright

def scrape_guru():
    with sync_playwright() as p:
        # Launching a headed browser can sometimes help bypass basic bot checks
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) ...')
        page = context.new_page()
        
        page.goto('https://www.guru.com/d/jobs/')
        
        # Wait for the job records to render via JS
        page.wait_for_selector('.jobRecord')
        
        jobs = page.query_selector_all('.jobRecord')
        for job in jobs:
            title_el = job.query_selector('.jobTitle')
            if title_el:
                print(f'Scraped Job: {title_el.inner_text().strip()}')
        
        browser.close()

scrape_guru()

import scrapy

class GuruSpider(scrapy.Spider):
    name = 'guru_spider'
    start_urls = ['https://www.guru.com/d/jobs/']

    def parse(self, response):
        # Scrapy requires a JS-rendering middleware like Scrapy-Playwright for Guru
        for job in response.css('.jobRecord'):
            yield {
                'title': job.css('.jobTitle::text').get(default='').strip(),
                'budget': job.css('.jobBudget::text').get(default='').strip(),
                'posted': job.css('.jobPostedDate::text').get(default='').strip(),
            }
        
        # Handle simple pagination link extraction
        next_page = response.css('a.next-page-selector::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();
  
  // Setting a realistic user agent
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36');
  
  await page.goto('https://www.guru.com/d/jobs/', { waitUntil: 'networkidle2' });
  
  const jobs = await page.evaluate(() => {
    const items = document.querySelectorAll('.jobRecord');
    return Array.from(items).map(item => ({
      title: item.querySelector('.jobTitle')?.innerText.trim(),
      budget: item.querySelector('.jobBudget')?.innerText.trim()
    }));
  });

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