نحوه استخراج داده‌ها و پست‌های خالقان Patreon

import asyncio
from playwright.async_api import async_playwright

async def scrape_patreon():
    async with async_playwright() as p:
        # Launching a headed browser can sometimes help bypass basic detection
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36')
        page = await context.new_page()
        
        # Navigate to a creator profile
        await page.goto('https://www.patreon.com/explore', wait_until='networkidle')
        
        # Wait for dynamic creator cards to load
        await page.wait_for_selector('[data-tag="creator-card"]')
        
        creators = await page.query_selector_all('[data-tag="creator-card"]')
        for creator in creators:
            name_el = await creator.query_selector('h3')
            if name_el:
                name = await name_el.inner_text()
                print(f'Scraped Creator: {name}')
        
        await browser.close()

asyncio.run(scrape_patreon())

import scrapy

class PatreonSpider(scrapy.Spider):
    name = 'patreon_spider'
    start_urls = ['https://www.patreon.com/explore']
    
    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36',
        'DOWNLOAD_DELAY': 2
    }

    def parse(self, response):
        # Patreon often requires JS rendering; standard Scrapy might only see limited data
        # Use a tool like Scrapy-Playwright for best results
        for creator in response.css('div[data-tag="creator-card"]'):
            yield {
                'name': creator.css('h3::text').get(),
                'link': creator.css('a::attr(href)').get(),
                'category': creator.css('span.category-label::text').get()
            }
        
        # Follow pagination if available
        next_page = response.css('a[data-tag="next-button"]::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 viewport
  await page.setViewport({ width: 1280, height: 800 });
  
  await page.goto('https://www.patreon.com/explore', { waitUntil: 'networkidle2' });
  
  // Wait for the dynamic content to render
  await page.waitForSelector('[data-tag="creator-card"]');
  
  const creatorData = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('[data-tag="creator-card"]'));
    return cards.map(card => ({
      name: card.querySelector('h3')?.innerText,
      description: card.querySelector('p')?.innerText
    }));
  });
  
  console.log(creatorData);
  await browser.close();
})();