如何在 Crawl4AI 中通过 CapSolver 集成解决 reCAPTCHA v2

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 = "6LfW6wATAAAAAHLqO2pb8bDBahxlMxNdo9g947u9"                      # 您的目标网站的 siteKey
site_url = "https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php"  # 您的目标网站的页面 URL
captcha_type = "ReCaptchaV2TaskProxyLess"                                  # 您的目标 CAPTCHA 类型
capsolver.api_key = api_key


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

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

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

        js_code = """
            const textarea = document.getElementById('g-recaptcha-response');
            if (textarea) {
                textarea.value = '""" + token + """';
                document.querySelector('button.form-field[type="submit"]').click();
            }
        """

        wait_condition = """() => {
            const items = document.querySelectorAll('h2');
            return items.length > 1;
        }"""

        run_config = CrawlerRunConfig(
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test",
            js_code=js_code,
            js_only=True,
            wait_for="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" # 确保此路径正确并包含您配置好的扩展

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：如果需要配置代理
)

async def main():
    async with AsyncWebCrawler(config=browser_config) as crawler:
        result_initial = await crawler.arun(
            url="https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php",
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test"
        )

        # 扩展会自动在页面加载时解决 CAPTCHA。
        # 您可能需要添加等待条件或 time.sleep 来允许 CAPTCHA 解决后再继续后续操作。
        time.sleep(30) # 示例等待，根据需要调整

        # CAPTCHA 解决后继续其他 Crawl4AI 操作
        # 例如，检查成功提交后出现的元素
        # print(result_initial.markdown) # 您可以在等待后检查页面内容


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" # 确保此路径正确并包含您配置好的扩展

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：如果需要配置代理
)

async def main():
    async with AsyncWebCrawler(config=browser_config) as crawler:
        result_initial = await crawler.arun(
            url="https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php",
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test"
        )

        # 等待片刻，让页面加载并让扩展准备就绪
        time.sleep(6)

        # 使用 js_code 触发 CapSolver 扩展提供的手动解决按钮
        js_code = """
            let solverButton = document.querySelector('#capsolver-solver-tip-button');
            if (solverButton) {
                const clickEvent = new MouseEvent('click', {
                    bubbles: true,
                    cancelable: true,
                    view: window
                });
                solverButton.dispatchEvent(clickEvent);
            }
        """
        print(js_code)
        run_config = CrawlerRunConfig(
            cache_mode=CacheMode.BYPASS,
            session_id="session_captcha_test",
            js_code=js_code,
            js_only=True,
        )
        result_next = await crawler.arun(
            url="https://recaptcha-demo.appspot.com/recaptcha-v2-checkbox.php",
            config=run_config
        )
        print("JS 执行结果:", result_next.js_execution_result)

        # 在手动触发后允许 CAPTCHA 解决的时间
        time.sleep(30) # 示例等待，根据需要调整

        # 继续其他 Crawl4AI 操作


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