GeeTest Slide 验证码参数及API指南

掌握GeeTest验证码提交中的每个参数。了解如何提取 gt、challenge 和其他值，并将它们正确提交到 CaptchaAI。

GeeTest v3 参数

从页面中提取参数

# extract_geetest_params.py
import requests
import re
import json


def extract_geetest_v3(page_url, session=None):
    """Extract GeeTest v3 gt and challenge from a page."""
    if session is None:
        session = requests.Session()
        session.headers["User-Agent"] = (
            "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 Chrome/125.0.0.0 Safari/537.36"
        )

    resp = session.get(page_url, timeout=15)
    html = resp.text

    # Method 1: Extract gt from HTML
    gt_match = re.search(r'gt["\']?\s*[:=]\s*["\']([a-f0-9]{32})', html)
    gt = gt_match.group(1) if gt_match else None

    # Method 2: Find API endpoint that returns challenge
    api_match = re.search(r'(https?://[^"\']+register-slide[^"\']*)', html)

    challenge = None
    if api_match:
        api_url = api_match.group(1)
        api_resp = session.get(api_url, timeout=10)
        try:
            data = api_resp.json()
            challenge = data.get("challenge")
            gt = gt or data.get("gt")
        except json.JSONDecodeError:
            pass

    if not challenge:
        # Try embedded challenge
        ch_match = re.search(r'challenge["\']?\s*[:=]\s*["\']([a-f0-9]+)', html)
        challenge = ch_match.group(1) if ch_match else None

    return {"gt": gt, "challenge": challenge, "pageurl": page_url}


# Usage
params = extract_geetest_v3("https://staging.example.com/qa-login")
print(f"gt: {params['gt']}")
print(f"challenge: {params['challenge']}")

向 CaptchaAI 提交 GeeTest

# solve_geetest.py
import requests
import time
import os


def solve_geetest(gt, challenge, pageurl, api_server=None):
    """Solve GeeTest v3 slide CAPTCHA via CaptchaAI."""
    api_key = os.environ["CAPTCHAAI_API_KEY"]

    payload = {
        "key": api_key,
        "method": "geetest",
        "gt": gt,
        "challenge": challenge,
        "pageurl": pageurl,
        "json": 1,
    }

    if api_server:
        payload["api_server"] = api_server

    # Submit
    resp = requests.post(
        "https://ocr.captchaai.com/in.php",
        data=payload,
        timeout=30,
    )
    result = resp.json()

    if result.get("status") != 1:
        raise RuntimeError(f"Submit failed: {result.get('request')}")

    task_id = result["request"]

    # Poll — GeeTest typically solves in 10-20 seconds
    time.sleep(10)
    for _ in range(30):
        resp = requests.get("https://ocr.captchaai.com/res.php", params={
            "key": api_key,
            "action": "get",
            "id": task_id,
            "json": 1,
        }, timeout=15)
        data = resp.json()

        if data.get("status") == 1:
            return data["request"]  # Returns challenge, validate, seccode
        if data["request"] != "CAPCHA_NOT_READY":
            raise RuntimeError(data["request"])
        time.sleep(5)

    raise TimeoutError("GeeTest solve timeout")

使用解决方案

该解决方案返回必须提交到目标站点的验证端点的三个值：

# submit_solution.py
import json


def submit_geetest_solution(session, validation_url, solution, original_challenge):
    """Submit GeeTest solution to the target site."""
    # Parse solution if string
    if isinstance(solution, str):
        solution = json.loads(solution)

    payload = {
        "geetest_challenge": solution.get("challenge", original_challenge),
        "geetest_validate": solution.get("validate", ""),
        "geetest_seccode": solution.get("seccode", ""),
    }

    resp = session.post(validation_url, data=payload, timeout=30)
    return resp


# Complete flow
def full_geetest_flow(page_url, validation_url):
    import requests
    from extract_geetest_params import extract_geetest_v3

    session = requests.Session()
    session.headers["User-Agent"] = (
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
        "AppleWebKit/537.36 Chrome/125.0.0.0 Safari/537.36"
    )

    # Step 1: Extract parameters
    params = extract_geetest_v3(page_url, session)
    print(f"gt: {params['gt']}, challenge: {params['challenge'][:16]}...")

    # Step 2: Solve
    solution = solve_geetest(
        params["gt"], params["challenge"], params["pageurl"],
    )
    print("Solved!")

    # Step 3: Submit
    resp = submit_geetest_solution(
        session, validation_url, solution, params["challenge"],
    )
    print(f"Validation response: {resp.status_code}")
    return resp

挑战新鲜感

challenge 参数是特定于会话的并且很快就会过期：

# fresh_challenge.py
import time


def get_fresh_challenge(session, register_url):
    """Always fetch a fresh challenge before solving."""
    resp = session.get(register_url, timeout=10)
    data = resp.json()

    challenge = data.get("challenge")
    if not challenge:
        raise ValueError("No challenge returned")

    return challenge


def solve_with_fresh_challenge(session, gt, register_url, pageurl):
    """Ensure challenge is fresh before submitting to CaptchaAI."""
    challenge = get_fresh_challenge(session, register_url)

    # Submit immediately — don't let it expire
    solution = solve_geetest(gt, challenge, pageurl)
    return solution

关键规则： 提取挑战并在几秒钟内提交给 CaptchaAI。陈旧的挑战总是会失败。

自定义API服务器

一些网站使用自定义 GeeTest 子域：

# The api_server parameter specifies a custom GeeTest backend
# Default: api.geetest.com
# Custom examples: api-na.geetest.com, api.geetest.com/ajax-custom

solution = solve_geetest(
    gt="abc123...",
    challenge="def456...",
    pageurl="https://staging.example.com/qa-login",
    api_server="api-na.geetest.com",  # North America endpoint
)

故障排除

常问问题

gt 和 challenge 有什么区别？

gt 是站点的 GeeTest 帐户 ID - 它保持不变。challenge 每次会话都会生成，并且每次都必须重新提取。

挑战的有效期是多长时间？

通常为 60-120 秒。提取并立即提交给CaptchaAI。

api_server 是做什么的？

它告诉 CaptchaAI 使用哪个 GeeTest API 服务器。仅当站点使用非默认 GeeTest 端点时才需要。检查页面的网络请求是否为 api-*.geetest.com。

相关指南

• GeeTest v4 变更
• GeeTest 与 BLS 比较

掌握GeeTest参数——以 CaptchaAI 开头.