Cloudflare Turnstile 正在取代数百万网站上的传统验证码。本指南向您展示如何使用 Python 的 requests 库和 CaptchaAI 的 API 解决 Turnstile 挑战 - 成功率达 100%。
先决条件
pip install requests
您需要：
- 来自的 CaptchaAI API 密钥验证码网站
- 目标页面 URL
- Turnstile sitekey
第 1 步：提取 Turnstile 站点密钥
import re
import requests
def extract_turnstile_sitekey(url):
"""Extract Cloudflare Turnstile sitekey from page HTML."""
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 Chrome/120.0.0.0",
"Accept": "text/html,*/*;q=0.8",
"Accept-Language": "en-US,en;q=0.9",
}
response = requests.get(url, headers=headers, timeout=15)
patterns = [
r'data-sitekey=["\']([0-9x][A-Za-z0-9_-]+)["\']',
r"sitekey\s*:\s*['\"]([0-9x][A-Za-z0-9_-]+)['\"]",
r"siteKey\s*[=:]\s*['\"]([0-9x][A-Za-z0-9_-]+)['\"]",
]
for pattern in patterns:
match = re.search(pattern, response.text)
if match:
return match.group(1)
return None
sitekey = extract_turnstile_sitekey("https://example.com/signup")
print(f"Sitekey: {sitekey}")
第二步：提交至CaptchaAI
import requests
API_KEY = "YOUR_API_KEY"
def submit_turnstile(sitekey, page_url):
"""Submit Turnstile solving task to CaptchaAI."""
response = requests.post("https://ocr.captchaai.com/in.php", data={
"key": API_KEY,
"method": "turnstile",
"sitekey": sitekey,
"pageurl": page_url,
"json": 1,
})
data = response.json()
if data.get("status") != 1:
raise Exception(f"Submit failed: {data.get('request')}")
return data["request"]
task_id = submit_turnstile("0x4AAAAAAAC3DHQhMMQ_Rxrg", "https://example.com/signup")
print(f"Task ID: {task_id}")
第 3 步：投票结果
import time
def poll_result(task_id, timeout=120):
"""Poll CaptchaAI for the solved Turnstile token."""
start = time.time()
while time.time() - start < timeout:
time.sleep(5)
result = requests.get("https://ocr.captchaai.com/res.php", params={
"key": API_KEY,
"action": "get",
"id": task_id,
"json": 1,
}).json()
if result.get("status") == 1:
return result["request"]
if result.get("request") == "ERROR_CAPTCHA_UNSOLVABLE":
raise Exception("Turnstile could not be solved")
raise TimeoutError("Solve timed out")
token = poll_result(task_id)
print(f"Token: {token[:50]}...")
完整的工作示例
import re
import time
import requests
API_KEY = "YOUR_API_KEY"
TARGET_URL = "https://example.com/signup"
def solve_turnstile(sitekey, page_url):
"""Full Turnstile solve: submit + poll."""
# Submit
submit = requests.post("https://ocr.captchaai.com/in.php", data={
"key": API_KEY,
"method": "turnstile",
"sitekey": sitekey,
"pageurl": page_url,
"json": 1,
})
data = submit.json()
if data.get("status") != 1:
raise Exception(f"Submit error: {data.get('request')}")
task_id = data["request"]
print(f"Task submitted: {task_id}")
# Poll
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,
}).json()
if result.get("status") == 1:
return result["request"]
raise TimeoutError("Solve timed out")
# --- Main flow ---
session = requests.Session()
session.headers.update({
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 Chrome/120.0.0.0",
"Accept": "text/html,*/*;q=0.8",
"Accept-Language": "en-US,en;q=0.9",
})
# 1. Get page and extract sitekey
response = session.get(TARGET_URL, timeout=15)
match = re.search(r'data-sitekey=["\']([0-9x][A-Za-z0-9_-]+)["\']', response.text)
if not match:
raise ValueError("Turnstile sitekey not found")
sitekey = match.group(1)
print(f"Sitekey: {sitekey}")
# 2. Solve Turnstile
token = solve_turnstile(sitekey, TARGET_URL)
print(f"Token: {token[:50]}...")
# 3. Submit form with token
form_response = session.post(TARGET_URL, data={
"cf-turnstile-response": token,
"email": "user@example.com",
"password": "SecurePass123",
})
print(f"Form status: {form_response.status_code}")
使用操作参数处理旋转门
一些站点在服务器端验证 action 参数：
def solve_turnstile_with_action(sitekey, page_url, action):
"""Solve Turnstile that requires an action parameter."""
submit = requests.post("https://ocr.captchaai.com/in.php", data={
"key": API_KEY,
"method": "turnstile",
"sitekey": sitekey,
"pageurl": page_url,
"action": action, # Include the action from data-action attribute
"json": 1,
})
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,
}).json()
if result.get("status") == 1:
return result["request"]
raise TimeoutError("Solve timed out")
令牌提交模式
模式 1：使用 cf-turnstile-response 形成 POST
# Most common — Turnstile uses cf-turnstile-response field
response = session.post(form_url, data={
"cf-turnstile-response": token,
"email": "user@example.com",
})
模式 2：JSON API
response = session.post(api_url, json={
"turnstileToken": token,
"email": "user@example.com",
})
模式3：自定义字段名称
# Some sites rename the field — check the form HTML
response = session.post(form_url, data={
"cf-turnstile-response": token,
"captcha_token": token, # Custom duplicate field
"action": "signup",
})
生产就绪类
import re
import time
import requests
class TurnstileSolver:
"""Production-ready Turnstile solver with retry logic."""
API_URL = "https://ocr.captchaai.com"
def __init__(self, api_key, max_retries=3):
self.api_key = api_key
self.max_retries = max_retries
def extract_sitekey(self, session, url):
"""Extract Turnstile sitekey from page."""
response = session.get(url, timeout=15)
match = re.search(
r'data-sitekey=["\']([0-9x][A-Za-z0-9_-]+)["\']', response.text
)
return match.group(1) if match else None
def solve(self, sitekey, page_url, action=None):
"""Solve Turnstile with retry logic. Returns token string."""
for attempt in range(1, self.max_retries + 1):
try:
token = self._solve_once(sitekey, page_url, action)
return token
except TimeoutError:
print(f"Attempt {attempt} timed out")
except Exception as e:
error_str = str(e)
if "ERROR_ZERO_BALANCE" in error_str:
raise # Don't retry billing errors
if "ERROR_WRONG_USER_KEY" in error_str:
raise
print(f"Attempt {attempt} failed: {e}")
raise Exception(f"Failed after {self.max_retries} attempts")
def _solve_once(self, sitekey, page_url, action=None):
"""Single solve attempt."""
params = {
"key": self.api_key,
"method": "turnstile",
"sitekey": sitekey,
"pageurl": page_url,
"json": 1,
}
if action:
params["action"] = action
submit = requests.post(f"{self.API_URL}/in.php", data=params, timeout=30)
submit.raise_for_status()
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(f"{self.API_URL}/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"]
if result.get("request") == "ERROR_CAPTCHA_UNSOLVABLE":
raise Exception("CAPTCHA unsolvable")
raise TimeoutError("Poll timed out")
# Usage
solver = TurnstileSolver("YOUR_API_KEY")
token = solver.solve("0x4AAAAAAAC3DHQhMMQ_Rxrg", "https://example.com/signup")
故障排除
| 症状 | 原因 | 处理方式 |
|---|---|---|
| 已收到令牌但表单被拒绝 | 站点密钥错误或缺少操作 | 重新提取站点密钥，包括操作（如果存在） |
| “未找到站点密钥” | 通过 JavaScript 加载Turnstile | 使用 Selenium 进行动态页面 |
| 获取页面之前的 HTTP 403 | Cloudflare BIC 阻止请求 | 添加适当的浏览器标头 |
| 求解需要 >60 秒 | 队列拥堵 | 高峰时段正常，等待时间较长 |
| 令牌有效一次然后失败 | 站点每次尝试都需要新令牌 | 为每次提交解决一个新的 token |
常见问题
成功率是多少？
CaptchaAI 在所有小部件模式下 Cloudflare Turnstile 的成功率达到 100%。
解决需要多长时间？
典型的求解时间为 5-15 秒。 Turnstile 通常比 reCAPTCHA 更快。
Turnstile 模式重要吗？
不会。托管、非交互和不可见模式都使用相同的 API 调用。 CaptchaAI 在内部处理模式差异。
如果页面同时具有 Turnstile 和 reCAPTCHA 该怎么办？
不常见但有可能。确定哪一个验证码保护您提交的表单并解决该问题。他们使用不同的响应字段名称。
概括
用 Python requests 解决 Cloudflare Turnstile 需要三个步骤：从页面 HTML 中提取 sitekey，提交到CaptchaAI使用 method=turnstile 并轮询令牌。在表单数据中提交作为 cf-turnstile-response 的令牌。 CaptchaAI 在所有 Turnstile 模式下都能提供 100% 的成功率。
