2Captchaのスクレイピング方法：CAPTCHA解決率と価格統計の抽出

from playwright.sync_api import sync_playwright

def scrape_2captcha_stats():
    with sync_playwright() as p:
        # ヘッドレスブラウザを起動
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        # 統計ページに移動
        page.goto("https://2captcha.com/statistics")
        # 動的テーブルの読み込みを待機
        page.wait_for_selector(".stats-table")
        # JS実行を使用してデータを抽出
        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):
        # DOM内の価格項目をループ
        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 () => {
    // ブラウザインスタンスを起動
    const browser = await puppeteer.launch();
    const page = await browser.newPage();
    // 価格ページに移動し、コンテンツを待機
    await page.goto('https://2captcha.com/pricing', { waitUntil: 'networkidle2' });
    // ページコンテンツを評価
    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();
})();