如何爬取 2Captcha：提取 CAPTCHA 识别率与价格统计

from playwright.sync_api import sync_playwright

def scrape_2captcha_stats():
    with sync_playwright() as p:
        # 启动无头浏览器
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        # 导航至统计页面
        page.goto("https://2captcha.com/statistics")
        # 等待动态表格加载
        page.wait_for_selector(".stats-table")
        # 使用 JS 执行提取数据
        stats = page.evaluate('''() => {
            const data = [];
            const rows = document.querySelectorAll(".stats-table tr");
            rows.forEach(row => {
                const cells = row.querySelectorAll("td");
                if (cells.length > 0) {
                    data.push({ type: cells[0].innerText, speed: cells[1].innerText });
                }
            });
            return data;
        }''')
        print(stats)
        browser.close()

scrape_2captcha_stats()

import scrapy

class TwoCaptchaSpider(scrapy.Spider):
    name = '2captcha_spider'
    start_urls = ['https://2captcha.com/pricing']

    def parse(self, response):
        # 循环遍历 DOM 中的价格项
        for item in response.css('div.pricing-item'):
            yield {
                'type': item.css('h3::text').get(),
                'price': item.css('span.price::text').get(),
                'description': item.css('p.desc::text').get()
            }

const puppeteer = require('puppeteer');

(async () => {
    // 启动浏览器实例
    const browser = await puppeteer.launch();
    const page = await browser.newPage();
    // 导航至价格页面并等待内容加载
    await page.goto('https://2captcha.com/pricing', { waitUntil: 'networkidle2' });
    // 评估页面内容
    const results = await page.evaluate(() => {
        const items = Array.from(document.querySelectorAll('.pricing-row'));
        return items.map(item => ({
            title: item.querySelector('.title')?.innerText,
            rate: item.querySelector('.rate')?.innerText
        }));
    });
    console.log(results);
    await browser.close();
})();