Lösen von CAPTCHAs auf chinesischen Websites mit CaptchaAI

Chinesische Websites verwenden CAPTCHA-Typen, die in westlichen Märkten selten zu finden sind – Bild-CAPTCHAs mit chinesischen Schriftzeichen, Rechenrätsel auf Mandarin, GeeTest-Folienüberprüfungen und proprietäre Anbieter wie Tencent CAPTCHA. Wenn Sie Daten von Baidu, Taobao, Regierungsportalen oder akademischen Datenbanken sammeln, müssen Sie diese regionalspezifischen Herausforderungen bewältigen.

Gängige CAPTCHA-Typen auf chinesischen Websites

Python: Bild-CAPTCHA für chinesische Schriftzeichen

Chinesische Bild-CAPTCHAs zeigen Zeichen wie 请输入验è¯ç  an (bitte geben Sie den Bestätigungscode ein) und erfordern OCR von chinesischem Text.

import requests
import base64
import time

API_KEY = "YOUR_API_KEY"
SUBMIT_URL = "https://ocr.captchaai.com/in.php"
RESULT_URL = "https://ocr.captchaai.com/res.php"


def solve_chinese_image_captcha(image_path: str) -> str:
    """Solve a Chinese character image CAPTCHA."""
    with open(image_path, "rb") as f:
        image_b64 = base64.b64encode(f.read()).decode()

    resp = requests.post(SUBMIT_URL, data={
        "key": API_KEY,
        "method": "base64",
        "body": image_b64,
        "language": 2,          # 2 = Chinese characters supported
        "json": 1,
    }, timeout=30).json()

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

    task_id = resp["request"]
    start = time.monotonic()

    while time.monotonic() - start < 120:
        time.sleep(5)
        poll = requests.get(RESULT_URL, params={
            "key": API_KEY, "action": "get",
            "id": task_id, "json": 1,
        }, timeout=15).json()

        if poll.get("request") == "CAPCHA_NOT_READY":
            continue
        if poll.get("status") == 1:
            return poll["request"]
        raise RuntimeError(f"Solve failed: {poll.get('request')}")

    raise RuntimeError("Timeout")


def solve_chinese_captcha_from_url(captcha_url: str, cookies: dict = None) -> str:
    """Download and solve a Chinese CAPTCHA from a URL."""
    session = requests.Session()
    if cookies:
        session.cookies.update(cookies)

    resp = session.get(captcha_url, timeout=15)
    image_b64 = base64.b64encode(resp.content).decode()

    submit = requests.post(SUBMIT_URL, data={
        "key": API_KEY,
        "method": "base64",
        "body": image_b64,
        "language": 2,
        "json": 1,
    }, timeout=30).json()

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

    task_id = submit["request"]
    for _ in range(24):
        time.sleep(5)
        poll = requests.get(RESULT_URL, params={
            "key": API_KEY, "action": "get", "id": task_id, "json": 1,
        }, timeout=15).json()

        if poll.get("request") == "CAPCHA_NOT_READY":
            continue
        if poll.get("status") == 1:
            return poll["request"]
        raise RuntimeError(f"Solve: {poll.get('request')}")

    raise RuntimeError("Timeout")


# --- GeeTest on Chinese platforms ---

def solve_geetest_chinese(gt: str, challenge: str, pageurl: str) -> dict:
    """Solve GeeTest v3 commonly found on Baidu, Bilibili, etc."""
    resp = requests.post(SUBMIT_URL, data={
        "key": API_KEY,
        "method": "geetest",
        "gt": gt,
        "challenge": challenge,
        "pageurl": pageurl,
        "json": 1,
    }, timeout=30).json()

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

    task_id = resp["request"]
    for _ in range(36):
        time.sleep(5)
        poll = requests.get(RESULT_URL, params={
            "key": API_KEY, "action": "get", "id": task_id, "json": 1,
        }, timeout=15).json()

        if poll.get("request") == "CAPCHA_NOT_READY":
            continue
        if poll.get("status") == 1:
            # GeeTest returns challenge, validate, seccode
            return poll["request"]
        raise RuntimeError(f"Solve: {poll.get('request')}")

    raise RuntimeError("Timeout")


# Usage — Chinese government portal
text = solve_chinese_image_captcha("chinese_captcha.png")
print(f"Chinese CAPTCHA text: {text}")

# GeeTest on a Chinese platform
geetest_result = solve_geetest_chinese(
    gt="b46d1900d0a894591f1561f8c35670a7",
    challenge="dynamic_challenge_string",
    pageurl="https://www.example.cn/login",
)

JavaScript: CAPTCHA-Flow für chinesische Websites

const API_KEY = "YOUR_API_KEY";
const SUBMIT_URL = "https://ocr.captchaai.com/in.php";
const RESULT_URL = "https://ocr.captchaai.com/res.php";
const fs = require("fs");

async function solveChineseImageCaptcha(imagePath) {
  const imageB64 = fs.readFileSync(imagePath, "base64");

  const body = new URLSearchParams({
    key: API_KEY,
    method: "base64",
    body: imageB64,
    language: "2",
    json: "1",
  });

  const resp = await (await fetch(SUBMIT_URL, { method: "POST", body })).json();
  if (resp.status !== 1) throw new Error(`Submit: ${resp.request}`);

  const taskId = resp.request;
  for (let i = 0; i < 24; i++) {
    await new Promise((r) => setTimeout(r, 5000));
    const url = `${RESULT_URL}?key=${API_KEY}&action=get&id=${taskId}&json=1`;
    const poll = await (await fetch(url)).json();
    if (poll.request === "CAPCHA_NOT_READY") continue;
    if (poll.status === 1) return poll.request;
    throw new Error(`Solve: ${poll.request}`);
  }
  throw new Error("Timeout");
}

async function solveGeeTest(gt, challenge, pageurl) {
  const body = new URLSearchParams({
    key: API_KEY,
    method: "geetest",
    gt,
    challenge,
    pageurl,
    json: "1",
  });

  const resp = await (await fetch(SUBMIT_URL, { method: "POST", body })).json();
  if (resp.status !== 1) throw new Error(`Submit: ${resp.request}`);

  const taskId = resp.request;
  for (let i = 0; i < 36; i++) {
    await new Promise((r) => setTimeout(r, 5000));
    const url = `${RESULT_URL}?key=${API_KEY}&action=get&id=${taskId}&json=1`;
    const poll = await (await fetch(url)).json();
    if (poll.request === "CAPCHA_NOT_READY") continue;
    if (poll.status === 1) return poll.request;
    throw new Error(`Solve: ${poll.request}`);
  }
  throw new Error("Timeout");
}

// Usage
const text = await solveChineseImageCaptcha("chinese_captcha.png");
console.log(`Chinese text: ${text}`);

Tipps für chinesisches Website-Scraping

Fehlerbehebung

Verwandte Leitfäden

• CAPTCHAs auf japanischen und koreanischen Websites lösen
• GeeTest mit CaptchaAI lösen
• Cloudflare Turnstile mit Node.js lösen