Solving CAPTCHAs on Japanese and Korean Websites

Japanese and Korean websites present unique CAPTCHA challenges. Japanese sites may use three writing systems — hiragana (ひらがな), katakana (カタカナ), and kanji (漢字) — sometimes mixed in a single image. Korean sites use hangul (한글) characters. Standard Latin-focused OCR fails on these character sets.

CAPTCHA Types by Region

Python: Japanese Image CAPTCHA

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_japanese_captcha(image_path: str) -> str:
    """Solve a Japanese 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,          # CJK 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_korean_captcha(image_path: str) -> str:
    """Solve a Korean hangul 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,
        "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_captcha_from_session(session: requests.Session,
                                captcha_url: str,
                                language: int = 2) -> str:
    """Download and solve a 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": str(language),
        "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")


# --- Usage ---

# Japanese CAPTCHA
jp_text = solve_japanese_captcha("japanese_captcha.png")
print(f"Japanese CAPTCHA: {jp_text}")

# Korean CAPTCHA from a live session
session = requests.Session()
session.headers["Accept-Language"] = "ko-KR,ko;q=0.9"
session.get("https://example.kr/login")  # establish session
kr_text = solve_captcha_from_session(session, "https://example.kr/captcha/image")
print(f"Korean CAPTCHA: {kr_text}")

JavaScript: Japanese/Korean CAPTCHA Solving

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 solveAsianCaptcha(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 solveFromUrl(captchaUrl, cookies = "") {
  const resp = await fetch(captchaUrl, {
    headers: { Cookie: cookies, "Accept-Language": "ja-JP,ja;q=0.9" },
  });
  const buffer = await resp.arrayBuffer();
  const imageB64 = Buffer.from(buffer).toString("base64");

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

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

  const taskId = submitResp.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");
}

// Usage
const jpText = await solveAsianCaptcha("japanese_captcha.png");
console.log(`Japanese: ${jpText}`);

Character Set Considerations

Troubleshooting

FAQ

Can CaptchaAI distinguish between similar hiragana and katakana characters?

Yes. With language=2, CaptchaAI uses models trained on CJK character sets that distinguish between visually similar characters across Japanese writing systems. Accuracy is highest on clear, high-resolution images.

Do I need different API parameters for Japanese vs. Korean?

No. Both use language=2 for CJK character recognition. CaptchaAI automatically detects whether the characters are Japanese, Korean, or Chinese. The only difference is the website context — use appropriate Accept-Language headers.

What about reCAPTCHA on Japanese/Korean sites?

reCAPTCHA on Japanese/Korean sites works identically to any other site — it's token-based and language-independent. Use CaptchaAI's reCAPTCHA solver with the sitekey from the page. The localized UI doesn't affect the solving process.

Related Articles

• Solving Captchas Chinese Websites

Next Steps

Start solving Japanese and Korean website CAPTCHAs — get your CaptchaAI API key and handle any CJK character CAPTCHA.

Related guides:

• Solving CAPTCHAs on Chinese Websites
• Multi-Language Image CAPTCHA Character Set
• CAPTCHA Localization and Language Settings