كيفية القيام بـ scraping لموقع Signal NFX | دليل استخراج بيانات المستثمرين وشركات رأس المال الجريء (VC)

from playwright.sync_api import sync_playwright

def scrape_signal():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        # Navigate to login
        page.goto('https://signal.nfx.com/login')
        page.fill('input[name="email"]', 'your_email@example.com')
        page.fill('input[name="password"]', 'your_password')
        page.click('button:has-text("Log In")')
        
        # Wait for the listing page to load after login
        page.wait_for_url('**/investors')
        page.goto('https://signal.nfx.com/investor-lists/top-ai-seed-investors')
        page.wait_for_selector('.investor-card')
        
        # Scroll to load infinite content
        for _ in range(5):
            page.mouse.wheel(0, 4000)
            page.wait_for_timeout(2000)
            
        investors = page.query_selector_all('.investor-card')
        for investor in investors:
            name = investor.query_selector('.name').inner_text()
            print(f'Found Investor: {name}')
            
        browser.close()

scrape_signal()

import scrapy

class SignalSpider(scrapy.Spider):
    name = 'signal_spider'
    # Note: Requires scrapy-playwright for JavaScript rendering
    start_urls = ['https://signal.nfx.com/investor-lists/top-saas-seed-investors']

    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(url, meta={'playwright': True})

    def parse(self, response):
        for investor in response.css('.investor-card'):
            yield {
                'name': investor.css('.name::text').get(),
                'firm': investor.css('.firm-name::text').get(),
                'link': response.urljoin(investor.css('a::attr(href)').get())
            }
        
        # Scrapy logic for infinite scroll would require a custom Playwright handler
        # to scroll down before passing the response back to parse

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36');
  
  // Handle Login first
  await page.goto('https://signal.nfx.com/login');
  await page.type('#user_email', 'your_email');
  await page.type('#user_password', 'your_password');
  await page.click('.btn-primary');
  
  await page.waitForNavigation();
  await page.goto('https://signal.nfx.com/investor-lists/top-fintech-seed-investors');
  await page.waitForSelector('.investor-card');
  
  const investors = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('.investor-card'));
    return items.map(item => ({
      name: item.querySelector('.name')?.innerText.trim(),
      firm: item.querySelector('.firm-name')?.innerText.trim()
    }));
  });

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