Python Selenium + CaptchaAI 完整集成指南 (实用指南)

Selenium 处理浏览器自动化； CaptchaAI 处理验证码解决。它们共同解决了最常见的自动化挑战 - 需要 JavaScript 执行和验证码完成的页面。本指南涵盖了 reCAPTCHA v2/v3、Cloudflare Turnstile 和图像验证码的完整集成模式。

先决条件

pip install selenium requests webdriver-manager

设置：标准配置 Selenium

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager

def create_driver():
    """Create a Selenium driver with stealth-configuredion settings."""
    options = webdriver.ChromeOptions()
    options.add_argument("--no-sandbox")
    options.add_experimental_option("excludeSwitches", ["enable-automation"])
    options.add_experimental_option("useAutomationExtension", False)

    driver = webdriver.Chrome(
        service=Service(ChromeDriverManager().install()),
        options=options,
    )

    # Remove webdriver flag
    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
    })

    return driver

CaptchaAI 求解器助手

import time
import requests

API_KEY = "YOUR_API_KEY"

def solve_captcha(method, **params):
    """Generic CaptchaAI solver — works for all supported CAPTCHA types."""
    submit_data = {
        "key": API_KEY,
        "method": method,
        "json": 1,
        **params,
    }

    submit = requests.post("https://ocr.captchaai.com/in.php", data=submit_data, timeout=30)
    data = submit.json()

    if data.get("status") != 1:
        raise Exception(f"Submit error: {data.get('request')}")

    task_id = data["request"]

    for _ in range(30):
        time.sleep(5)
        result = requests.get("https://ocr.captchaai.com/res.php", params={
            "key": API_KEY,
            "action": "get",
            "id": task_id,
            "json": 1,
        }, timeout=30).json()

        if result.get("status") == 1:
            return result["request"]
        if result.get("request") == "ERROR_CAPTCHA_UNSOLVABLE":
            raise Exception("CAPTCHA unsolvable")

    raise TimeoutError("Solve timed out")

reCAPTCHA v2 与硒

全流程：检测、解决、注入令牌、提交

from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import re

def solve_recaptcha_v2_selenium(driver, url):
    """Complete reCAPTCHA v2 solve in Selenium."""
    driver.get(url)

    # Wait for page to load
    WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.TAG_NAME, "body"))
    )

    # Extract sitekey
    page_source = driver.page_source
    match = re.search(r'data-sitekey=["\']([A-Za-z0-9_-]{40})["\']', page_source)
    if not match:
        raise ValueError("reCAPTCHA sitekey not found")
    sitekey = match.group(1)
    print(f"Sitekey: {sitekey}")

    # Solve via CaptchaAI
    token = solve_captcha(
        "userrecaptcha",
        googlekey=sitekey,
        pageurl=url,
    )
    print(f"Token received: {token[:50]}...")

    # Inject token into the page
    driver.execute_script(f"""
        document.getElementById('g-recaptcha-response').value = '{token}';
        document.getElementById('g-recaptcha-response').style.display = 'block';
    """)

    # If there's a callback function, call it
    driver.execute_script(f"""
        if (typeof ___grecaptcha_cfg !== 'undefined') {{
            var clients = ___grecaptcha_cfg.clients;
            for (var key in clients) {{
                var client = clients[key];
                if (client.rr && client.rr.l) {{
                    client.rr.l.callback('{token}');
                }}
            }}
        }}
    """)

    # Submit the form
    submit_button = driver.find_element(By.CSS_SELECTOR, "button[type='submit'], input[type='submit']")
    submit_button.click()

    return token

# Usage
driver = create_driver()
try:
    solve_recaptcha_v2_selenium(driver, "https://staging.example.com/qa-login")
    print(f"Current URL: {driver.current_url}")
finally:
    driver.quit()

Cloudflare Turnstile 与硒

def solve_turnstile_selenium(driver, url):
    """Complete Turnstile solve in Selenium."""
    driver.get(url)

    WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.TAG_NAME, "body"))
    )

    # Extract sitekey
    page_source = driver.page_source
    match = re.search(r'data-sitekey=["\']([0-9x][A-Za-z0-9_-]+)["\']', page_source)
    if not match:
        # Try JavaScript API pattern
        match = re.search(r"sitekey\s*:\s*['\"]([0-9x][A-Za-z0-9_-]+)['\"]", page_source)
    if not match:
        raise ValueError("Turnstile sitekey not found")

    sitekey = match.group(1)
    print(f"Turnstile sitekey: {sitekey}")

    # Solve via CaptchaAI
    token = solve_captcha(
        "turnstile",
        sitekey=sitekey,
        pageurl=url,
    )
    print(f"Turnstile token: {token[:50]}...")

    # Inject token
    driver.execute_script(f"""
        // Set the hidden input value
        var inputs = document.querySelectorAll('[name="cf-turnstile-response"]');
        inputs.forEach(function(input) {{ input.value = '{token}'; }});

        // Also try the callback approach
        if (typeof turnstile !== 'undefined' && turnstile.getResponse) {{
            // Widget already rendered
        }}
    """)

    # Submit form
    submit_button = driver.find_element(By.CSS_SELECTOR, "button[type='submit'], input[type='submit']")
    submit_button.click()

    return token

使用 Selenium 进行图像验证码

对于传统图像/text 验证码（输入您看到的字母）：

import base64

def solve_image_captcha_selenium(driver, captcha_selector):
    """Solve image CAPTCHA visible in the browser."""
    # Find the CAPTCHA image element
    captcha_img = driver.find_element(By.CSS_SELECTOR, captcha_selector)

    # Get image as base64
    img_base64 = captcha_img.screenshot_as_base64

    # Solve via CaptchaAI
    answer = solve_captcha("base64", body=img_base64)
    print(f"CAPTCHA answer: {answer}")

    # Type the answer into the input field
    captcha_input = driver.find_element(
        By.CSS_SELECTOR, "input[name='captcha'], input[name='code'], input.captcha-input"
    )
    captcha_input.clear()
    captcha_input.send_keys(answer)

    return answer

reCAPTCHA v3 与硒

def solve_recaptcha_v3_selenium(driver, url, sitekey, action="verify"):
    """Solve reCAPTCHA v3 in Selenium."""
    driver.get(url)

    # Solve via CaptchaAI
    token = solve_captcha(
        "userrecaptcha",
        googlekey=sitekey,
        pageurl=url,
        version="v3",
        action=action,
    )

    # Inject token
    driver.execute_script(f"""
        // Set reCAPTCHA response
        var textarea = document.getElementById('g-recaptcha-response');
        if (textarea) {{
            textarea.value = '{token}';
            textarea.style.display = 'block';
        }}

        // Set any hidden input fields
        var inputs = document.querySelectorAll('input[name="g-recaptcha-response"]');
        inputs.forEach(function(input) {{ input.value = '{token}'; }});
    """)

    return token

完整的自动化示例

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import re
import time
import requests

API_KEY = "YOUR_API_KEY"

class SeleniumCaptchaSolver:
    """Complete Selenium + CaptchaAI automation class."""

    def __init__(self, api_key):
        self.api_key = api_key
        self.driver = None

    def start(self):
        """Initialize the browser."""
        options = webdriver.ChromeOptions()
        options.add_argument("--no-sandbox")
        options.add_experimental_option("excludeSwitches", ["enable-automation"])
        self.driver = webdriver.Chrome(options=options)
        self.driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
            "source": "Object.defineProperty(navigator, 'webdriver', {get: () => undefined})"
        })

    def stop(self):
        """Close the browser."""
        if self.driver:
            self.driver.quit()

    def navigate(self, url):
        """Navigate to URL and wait for load."""
        self.driver.get(url)
        WebDriverWait(self.driver, 15).until(
            lambda d: d.execute_script("return document.readyState") == "complete"
        )

    def detect_captcha(self):
        """Detect which CAPTCHA type is on the page."""
        source = self.driver.page_source

        if re.search(r'data-sitekey=["\'][A-Za-z0-9_-]{40}["\']', source):
            if "recaptcha/api.js" in source or "grecaptcha" in source:
                return "recaptcha_v2"

        if "cf-turnstile" in source or "challenges.cloudflare.com/turnstile" in source:
            return "turnstile"

        if re.search(r'recaptcha.*v3|render=[A-Za-z0-9_-]{40}', source):
            return "recaptcha_v3"

        captcha_imgs = self.driver.find_elements(
            By.CSS_SELECTOR, "img.captcha, img[alt*='captcha'], img[src*='captcha']"
        )
        if captcha_imgs:
            return "image"

        return None

    def solve_and_submit(self, url, form_data=None):
        """Navigate, solve CAPTCHA, fill form, and submit."""
        self.navigate(url)
        captcha_type = self.detect_captcha()

        if not captcha_type:
            print("No CAPTCHA detected")
            return self._fill_and_submit(form_data)

        print(f"Detected: {captcha_type}")

        if captcha_type == "recaptcha_v2":
            self._solve_recaptcha_v2()
        elif captcha_type == "turnstile":
            self._solve_turnstile()
        elif captcha_type == "image":
            self._solve_image()

        return self._fill_and_submit(form_data)

    def _solve_recaptcha_v2(self):
        source = self.driver.page_source
        match = re.search(r'data-sitekey=["\']([A-Za-z0-9_-]{40})["\']', source)
        sitekey = match.group(1)

        token = self._api_solve("userrecaptcha", googlekey=sitekey, pageurl=self.driver.current_url)

        self.driver.execute_script(f"""
            document.getElementById('g-recaptcha-response').value = '{token}';
        """)

    def _solve_turnstile(self):
        source = self.driver.page_source
        match = re.search(r'data-sitekey=["\']([0-9x][A-Za-z0-9_-]+)["\']', source)
        sitekey = match.group(1)

        token = self._api_solve("turnstile", sitekey=sitekey, pageurl=self.driver.current_url)

        self.driver.execute_script(f"""
            document.querySelectorAll('[name="cf-turnstile-response"]')
                .forEach(function(el) {{ el.value = '{token}'; }});
        """)

    def _solve_image(self):
        img = self.driver.find_element(
            By.CSS_SELECTOR, "img.captcha, img[alt*='captcha'], img[src*='captcha']"
        )
        answer = self._api_solve("base64", body=img.screenshot_as_base64)

        captcha_input = self.driver.find_element(
            By.CSS_SELECTOR, "input[name='captcha'], input[name='code']"
        )
        captcha_input.clear()
        captcha_input.send_keys(answer)

    def _fill_and_submit(self, form_data):
        if form_data:
            for name, value in form_data.items():
                try:
                    field = self.driver.find_element(By.NAME, name)
                    field.clear()
                    field.send_keys(value)
                except Exception:
                    pass

        submit = self.driver.find_element(
            By.CSS_SELECTOR, "button[type='submit'], input[type='submit']"
        )
        submit.click()
        time.sleep(3)
        return self.driver.current_url

    def _api_solve(self, method, **params):
        submit = requests.post("https://ocr.captchaai.com/in.php", data={
            "key": self.api_key, "method": method, "json": 1, **params,
        }, timeout=30)
        data = submit.json()
        if data.get("status") != 1:
            raise Exception(f"Submit error: {data.get('request')}")

        task_id = data["request"]
        for _ in range(30):
            time.sleep(5)
            result = requests.get("https://ocr.captchaai.com/res.php", params={
                "key": self.api_key, "action": "get", "id": task_id, "json": 1,
            }, timeout=30).json()
            if result.get("status") == 1:
                return result["request"]
        raise TimeoutError("Solve timed out")

# Usage
solver = SeleniumCaptchaSolver(API_KEY)
solver.start()
try:
    result_url = solver.solve_and_submit(
        "https://staging.example.com/qa-login",
        form_data={"username": "user@example.com", "password": "pass123"},
    )
    print(f"Result: {result_url}")
finally:
    solver.stop()

故障排除

症状	原因	处理方式
检测到验证码但token 提交失败	`g-recaptcha-response` 未找到	检查 iframe - reCAPTCHA 可能位于 iframe 中
令牌已注入但表单未提交	回调未触发	显式调用 reCAPTCHA 回调函数
网站“检测到网络驱动程序”	未应用标准配置	添加 CDP 命令以删除 webdriver 标志
图片验证码截图空白	元素不可见	首先将元素滚动到视图中
Turnstile令牌被拒绝	错误的站点密钥	从实时页面源中重新提取

常见问题

我应该使用 Selenium 还是纯请求？

当网站需要 JavaScript 执行、动态内容加载或复杂的多页面流时，请使用 Selenium。使用 requests 进行简单的基于 API 的表单提交，您只需要令牌。

如何在 iframe 中处理 reCAPTCHA？

首先切换到 reCAPTCHA iframe：driver.switch_to.frame(driver.find_element(By.CSS_SELECTOR, "iframe[src*='recaptcha']"))。提取站点密钥，然后切换回来：driver.switch_to.default_content()。

我可以无头运行 Selenium 吗？

是的，但有些验证码会检测无头模式。使用 --headless=new 并确保 WebGL/Canvas 特征有效。 CaptchaAI 自行求解，因此无头检测不会影响求解。

Selenium 与 requests 相比慢了多少？

Selenium 为浏览器启动和页面渲染增加了 3-5 秒的开销。验证码解决时间是相同的。尽可能使用 requests，必要时使用 Selenium。

概括

Python 硒 +CaptchaAI处理浏览器自动化中的任何验证码：从页面源检测验证码类型，通过 CaptchaAI 的 API 进行解析，通过 JavaScript 注入令牌，然后提交表单。 SeleniumCaptchaSolver 类自动执行完整的检测-解决-提交工作流程。

Python Selenium + CaptchaAI 完整集成指南

先决条件

设置：标准配置 Selenium

CaptchaAI 求解器助手

reCAPTCHA v2 与硒

全流程：检测、解决、注入令牌、提交

Cloudflare Turnstile 与硒

使用 Selenium 进行图像验证码

reCAPTCHA v3 与硒

完整的自动化示例

故障排除

常见问题

我应该使用 Selenium 还是纯请求？

如何在 iframe 中处理 reCAPTCHA？

我可以无头运行 Selenium 吗？

Selenium 与 requests 相比慢了多少？

概括

相关文章

Selenium Grid + CaptchaAI：分布式验证码求解

使用 CaptchaAI 构建客户端验证码管道

弹出模式中的验证码：检测和token 提交

高需求 e-commerce checkout 的 CAPTCHA 测试

使用 CaptchaAI 进行 QA 浏览器配置文件隔离

Cloudflare Turnstile 令牌到期时间和竞争条件