Mehrsprachiges Bild-CAPTCHA: Zeichensatzkonfiguration

Der Image/OCR-Löser von CaptchaAI unterstützt über 27.500 CAPTCHA-Typen in mehreren Schreibsystemen. Der Parameter language teilt dem Solver mit, welchen Zeichensatz er erwarten soll, was sich direkt auf die Erkennungsgenauigkeit auswirkt. Wenn Sie die falsche Einstellung verwenden, sucht der Solver nach den falschen Zeichen.

Sprachparameterreferenz

Wann die einzelnen Einstellungen verwendet werden sollten

Python: Sprachbewusste CAPTCHA-Lösung

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_image_captcha(image_path: str, language: int = 0) -> str:
    """Solve an image CAPTCHA with the specified language setting.

    Args:
        image_path: Path to the CAPTCHA image file.
        language: 0=Latin, 1=Cyrillic, 2=non-Latin/mixed.
    """
    with open(image_path, "rb") as f:
        image_b64 = base64.b64encode(f.read()).decode()

    params = {
        "key": API_KEY,
        "method": "base64",
        "body": image_b64,
        "json": 1,
    }

    # Only set language if non-default
    if language > 0:
        params["language"] = language

    resp = requests.post(SUBMIT_URL, data=params, 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 detect_script(text: str) -> str:
    """Detect the primary script of solved text."""
    for ch in text:
        cp = ord(ch)
        if 0x0400 <= cp <= 0x04FF:
            return "cyrillic"
        if 0x4E00 <= cp <= 0x9FFF:
            return "cjk"
        if 0x3040 <= cp <= 0x30FF:
            return "japanese"
        if 0xAC00 <= cp <= 0xD7AF:
            return "korean"
        if 0x0600 <= cp <= 0x06FF:
            return "arabic"
        if 0x0590 <= cp <= 0x05FF:
            return "hebrew"
    return "latin"


# --- Usage examples ---

# Latin CAPTCHA (default)
latin_text = solve_image_captcha("english_captcha.png", language=0)
print(f"Latin: {latin_text} (script: {detect_script(latin_text)})")

# Russian CAPTCHA
cyrillic_text = solve_image_captcha("russian_captcha.png", language=1)
print(f"Cyrillic: {cyrillic_text} (script: {detect_script(cyrillic_text)})")

# Chinese CAPTCHA
chinese_text = solve_image_captcha("chinese_captcha.png", language=2)
print(f"CJK: {chinese_text} (script: {detect_script(chinese_text)})")

# Mixed script CAPTCHA
mixed_text = solve_image_captcha("mixed_captcha.png", language=2)
print(f"Mixed: {mixed_text} (script: {detect_script(mixed_text)})")

JavaScript: Mehrsprachiger Löser

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 solveImageCaptcha(imagePath, language = 0) {
  const imageB64 = fs.readFileSync(imagePath, "base64");

  const params = {
    key: API_KEY,
    method: "base64",
    body: imageB64,
    json: "1",
  };

  if (language > 0) params.language = String(language);

  const body = new URLSearchParams(params);
  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 detectScript(text) {
  for (const ch of text) {
    const cp = ch.codePointAt(0);
    if (cp >= 0x0400 && cp <= 0x04ff) return "cyrillic";
    if (cp >= 0x4e00 && cp <= 0x9fff) return "cjk";
    if (cp >= 0x3040 && cp <= 0x30ff) return "japanese";
    if (cp >= 0xac00 && cp <= 0xd7af) return "korean";
    if (cp >= 0x0600 && cp <= 0x06ff) return "arabic";
  }
  return "latin";
}

// Auto-detect-and-solve helper
async function solveWithAutoLanguage(imagePath, hint = "auto") {
  const languageMap = {
    latin: 0,
    cyrillic: 1,
    russian: 1,
    chinese: 2,
    japanese: 2,
    korean: 2,
    arabic: 2,
    auto: 2, // language=2 handles all scripts
  };

  const language = languageMap[hint] ?? 2;
  return solveImageCaptcha(imagePath, language);
}

// Usage
const text = await solveWithAutoLanguage("captcha.png", "auto");
console.log(`Text: ${text}, Script: ${detectScript(text)}`);

Häufige Fehler

Fehlerbehebung

Verwandte Leitfäden

• CAPTCHA-Lösung auf Chinesischen Webseiten
• CAPTCHA-Lösung auf Japanischen und Koreanischen Webseiten
• Arabisch und RTL CAPTCHA-Verwaltung