如何在Crawl4AI中通过CapSolver集成解决reCAPTCHA v3

import asyncio
import capsolver
from crawl4ai import *


# TODO: 设置您的配置
api_key = "CAP-xxxxxxxxxxxxxxxxxxxxx"                                             # 您的 CapSolver API 密钥
site_key = "6LdKlZEpAAAAAAOQjzC2v_d36tWxCl6dWsozdSy9"                             # 您目标网站的站点密钥
site_url = "https://recaptcha-demo.appspot.com/recaptcha-v3-request-scores.php"   # 您目标网站的页面 URL
page_action = "examples/v3scores"                                                 # 您目标网站的页面操作
captcha_type = "ReCaptchaV3TaskProxyLess"                                         # 您目标验证码的类型
capsolver.api_key = api_key


async def main():
    browser_config = BrowserConfig(
        verbose=True,
        headless=False,
        use_persistent_context=True,
    )

    # 使用 CapSolver SDK 获取 reCAPTCHA 令牌
    solution = capsolver.solve({
        "type": captcha_type,
        "websiteURL": site_url,
        "websiteKey": site_key,
        "pageAction": page_action,
    })
    token = solution["gRecaptchaResponse"]
    print("reCAPTCHA 令牌:", token)

    async with AsyncWebCrawler(config=browser_config) as crawler:
        await crawler.arun(
            url=site_url,
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test"
        )

        js_code = """
            const originalFetch = window.fetch;
            
            window.fetch = function(...args) {
              if (typeof args[0] === \'string\' && args[0].includes(\'/recaptcha-v3-verify.php\')) {
                const url = new URL(args[0], window.location.origin);
                url.searchParams.set(\'action\', \""" + token + """\");
                args[0] = url.toString();
                document.querySelector(\".token\").innerHTML = \"fetch(\\'/recaptcha-v3-verify.php?action=examples/v3scores&token="""+token+"""\')\";
                console.log(\'Fetch URL 钩住:\', args[0]);
              }
              return originalFetch.apply(this, args);
            };
        """

        wait_condition = """() => {
            return document.querySelector(\".step3:not(.hidden)\");
        }"""

        run_config = CrawlerRunConfig(
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test",
            js_code=js_code,
            js_only=True,
            wait_for=f"js:{wait_condition}"
        )

        result_next = await crawler.arun(
            url=site_url,
            config=run_config,
        )
        print(result_next.markdown)


if __name__ == "__main__":
    asyncio.run(main())

import asyncio
import time

from crawl4ai import *


# TODO: 设置您的配置
user_data_dir = "/browser-profile/Default1" # 确保此路径正确设置并包含您的配置扩展

browser_config = BrowserConfig(
    verbose=True,
    headless=False,
    user_data_dir=user_data_dir,
    use_persistent_context=True,
    proxy="http://127.0.0.1:13120", # 可选：如需配置代理
)

async def main():
    async with AsyncWebCrawler(config=browser_config) as crawler:
        result_initial = await crawler.arun(
            url="https://recaptcha-demo.appspot.com/recaptcha-v3-request-scores.php", # 使用 reCAPTCHA v3 演示 URL
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test"
        )

        # reCAPTCHA v3 通常在页面加载时由扩展自动求解。
        # 您可能需要添加等待条件或 time.sleep 以在继续依赖令牌的进一步操作之前等待 CAPTCHA 求解完成。
        time.sleep(30) # 示例等待，根据扩展操作需要进行调整

        # 在 CAPTCHA 求解后继续其他 Crawl4AI 操作
        # 例如，检查在成功验证后出现的元素或内容
        # print(result_initial.markdown) # 您可以在等待后检查页面内容


if __name__ == "__main__":
    asyncio.run(main())