使用 CaptchaAI 解决西里尔文字验证码

俄语、乌克兰语、保加利亚语和塞尔维亚语网站使用西里尔文文本验证码，这些验证码看起来与拉丁文非常相似，例如“Д、“Д、“С”、“Е”、“Д、“О”等字符与拉丁文对应字符看起来相同，但 Unicode 代码点完全不同。这造成了标准拉丁文 OCR 所忽略的独特识别和提交挑战。

西里尔字母与拉丁字母易混淆字符

提交错误的代码点会导致表单验证拒绝外观正确的文本。

Python：西里尔文字图像验证码

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_cyrillic_captcha(image_path: str) -> str:
    """Solve a Cyrillic text 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,          # Non-Latin character support
        "json": 1,
    }, timeout=30).json()

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

    task_id = resp["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")


def solve_cyrillic_from_session(session: requests.Session,
                                 captcha_url: str) -> str:
    """Solve a Cyrillic CAPTCHA within a session context."""
    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")


def verify_cyrillic(text: str) -> bool:
    """Verify that solved text contains Cyrillic characters."""
    return any('\u0400' <= ch <= '\u04FF' for ch in text)


# --- Russian website form flow ---

def solve_russian_form(form_url: str, captcha_url: str,
                       form_data: dict) -> requests.Response:
    """Complete a Russian website form with CAPTCHA."""
    session = requests.Session()
    session.headers.update({
        "Accept-Language": "ru-RU,ru;q=0.9",
    })

    # Establish session
    session.get(form_url, timeout=15)

    # Solve CAPTCHA
    captcha_text = solve_cyrillic_from_session(session, captcha_url)
    print(f"Cyrillic CAPTCHA: {captcha_text}")

    if verify_cyrillic(captcha_text):
        print("Confirmed: contains Cyrillic characters")

    form_data["captcha"] = captcha_text
    return session.post(form_url, data=form_data, timeout=30)


# --- Usage ---

text = solve_cyrillic_captcha("russian_captcha.png")
print(f"Solved: {text}")
print(f"Is Cyrillic: {verify_cyrillic(text)}")
print(f"Unicode codepoints: {[hex(ord(c)) for c in text]}")

JavaScript：西里尔验证码处理

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 solveCyrillicCaptcha(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");
}

function isCyrillic(text) {
  return /[\u0400-\u04FF]/.test(text);
}

function showCodepoints(text) {
  return [...text].map((ch) => `${ch}=U+${ch.codePointAt(0).toString(16).padStart(4, "0")}`);
}

// Usage
const text = await solveCyrillicCaptcha("russian_captcha.png");
console.log(`Solved: ${text}`);
console.log(`Is Cyrillic: ${isCyrillic(text)}`);
console.log(`Codepoints: ${showCodepoints(text).join(", ")}`);

常见的西里尔验证码模式

故障排除

常问问题

CaptchaAI 如何区分西里尔字母 В 和拉丁字母 B？

CaptchaAI 的 OCR 模型经过上下文和字形特征的训练。当设置 language=2 时，求解器使用西里尔字母识别模型返回正确的 Unicode 代码点。返回的文本将使用西里尔字符 (U+0400–U+04FF) 表示俄语文本。

它可以处理乌克兰语特定字符吗？

是的。乌克兰语使用俄语中不存在的字符 - ґ (U+0491)、є (U+0454)、і (U+0456)、ї (U+0457)。 CaptchaAI 通过 language=2 识别这些。该求解器可以处理所有西里尔文字，包括俄语、乌克兰语、保加利亚语和塞尔维亚语。

如果验证码混合了西里尔字母和拉丁字母怎么办？

一些验证码故意混合脚本以造成歧义。 CaptchaAI 返回每个字符具有正确 Unicode 代码点的文本。使用 verify_cyrillic() 函数或通过检查代码点进行验证。

下一步

解决俄语和斯拉夫网站上的西里尔验证码 -”获取您的 CaptchaAI API 密钥。

相关指南：

• 解决中文网站上的验证码
• 多语言图像验证码字符集
• 验证码本地化和语言设置