ELK Stack لتحليل سجل حل اختبار CAPTCHA

عندما يقوم مسار CAPTCHA الخاص بك بمعالجة آلاف المهام، لا يتم توسيع نطاق grep. يتيح لك ELK Stack (Elasticsearch وLogstash وKibana) البحث عن سجلات الحل وتجميعها وتصورها - والعثور على أنماط الأخطاء وتتبع اتجاهات زمن الاستجابة وتشخيص المشكلات في ثوانٍ.

الهندسة المعمارية

[CAPTCHA Workers] → JSON logs → [Filebeat] → [Logstash] → [Elasticsearch]
                                                                ↓
                                                           [Kibana]

التسجيل المنظم

بايثون - إخراج سجل JSON

import os
import json
import time
import logging
import sys
import requests

API_KEY = os.environ["CAPTCHAAI_API_KEY"]


class JSONFormatter(logging.Formatter):
    def format(self, record):
        log_entry = {
            "timestamp": self.formatTime(record),
            "level": record.levelname,
            "logger": record.name,
            "message": record.getMessage(),
        }
        # Add extra fields
        if hasattr(record, "captcha_id"):
            log_entry["captcha_id"] = record.captcha_id
        if hasattr(record, "captcha_type"):
            log_entry["captcha_type"] = record.captcha_type
        if hasattr(record, "solve_time"):
            log_entry["solve_time"] = record.solve_time
        if hasattr(record, "error_code"):
            log_entry["error_code"] = record.error_code
        if hasattr(record, "target_url"):
            log_entry["target_url"] = record.target_url
        if hasattr(record, "poll_count"):
            log_entry["poll_count"] = record.poll_count
        return json.dumps(log_entry)


# Configure logger
logger = logging.getLogger("captchaai")
logger.setLevel(logging.INFO)
handler = logging.StreamHandler(sys.stdout)
handler.setFormatter(JSONFormatter())
logger.addHandler(handler)

session = requests.Session()


def solve_captcha(sitekey, pageurl, captcha_type="recaptcha_v2"):
    extra = {"captcha_type": captcha_type, "target_url": pageurl}

    # Submit
    resp = session.post("https://ocr.captchaai.com/in.php", data={
        "key": API_KEY,
        "method": "userrecaptcha",
        "googlekey": sitekey,
        "pageurl": pageurl,
        "json": 1
    })
    data = resp.json()

    if data.get("status") != 1:
        logger.error("Submit failed", extra={
            **extra, "error_code": data.get("request")
        })
        return {"error": data.get("request")}

    captcha_id = data["request"]
    extra["captcha_id"] = captcha_id
    logger.info("Task submitted", extra=extra)

    # Poll
    start = time.time()
    poll_count = 0
    for _ in range(60):
        time.sleep(5)
        poll_count += 1
        result = session.get("https://ocr.captchaai.com/res.php", params={
            "key": API_KEY, "action": "get", "id": captcha_id, "json": 1
        }).json()

        if result.get("status") == 1:
            elapsed = round(time.time() - start, 2)
            logger.info("Solve success", extra={
                **extra,
                "solve_time": elapsed,
                "poll_count": poll_count
            })
            return {"solution": result["request"]}

        if result.get("request") != "CAPCHA_NOT_READY":
            logger.error("Solve failed", extra={
                **extra,
                "error_code": result.get("request"),
                "poll_count": poll_count
            })
            return {"error": result.get("request")}

    logger.error("Solve timeout", extra={
        **extra,
        "error_code": "TIMEOUT",
        "poll_count": poll_count
    })
    return {"error": "TIMEOUT"}

JavaScript - التسجيل المنظم

const axios = require("axios");

const API_KEY = process.env.CAPTCHAAI_API_KEY;

function log(level, message, fields = {}) {
  const entry = {
    timestamp: new Date().toISOString(),
    level,
    message,
    service: "captcha-worker",
    ...fields,
  };
  console.log(JSON.stringify(entry));
}

async function solveCaptcha(sitekey, pageurl, captchaType = "recaptcha_v2") {
  const fields = { captchaType, targetUrl: pageurl };

  const submitResp = await axios.post("https://ocr.captchaai.com/in.php", null, {
    params: {
      key: API_KEY, method: "userrecaptcha",
      googlekey: sitekey, pageurl, json: 1,
    },
  });

  if (submitResp.data.status !== 1) {
    log("error", "Submit failed", { ...fields, errorCode: submitResp.data.request });
    return { error: submitResp.data.request };
  }

  const captchaId = submitResp.data.request;
  fields.captchaId = captchaId;
  log("info", "Task submitted", fields);

  const startTime = Date.now();
  let pollCount = 0;

  for (let i = 0; i < 60; i++) {
    await new Promise((r) => setTimeout(r, 5000));
    pollCount++;

    const pollResp = await axios.get("https://ocr.captchaai.com/res.php", {
      params: { key: API_KEY, action: "get", id: captchaId, json: 1 },
    });

    if (pollResp.data.status === 1) {
      const solveTime = ((Date.now() - startTime) / 1000).toFixed(2);
      log("info", "Solve success", { ...fields, solveTime: parseFloat(solveTime), pollCount });
      return { solution: pollResp.data.request };
    }

    if (pollResp.data.request !== "CAPCHA_NOT_READY") {
      log("error", "Solve failed", { ...fields, errorCode: pollResp.data.request, pollCount });
      return { error: pollResp.data.request };
    }
  }

  log("error", "Solve timeout", { ...fields, errorCode: "TIMEOUT", pollCount });
  return { error: "TIMEOUT" };
}

module.exports = { solveCaptcha };

تكوين Filebeat

# filebeat.yml
filebeat.inputs:

  - type: log
    paths:

      - /var/log/captcha-worker/*.log
    json:
      keys_under_root: true
      add_error_key: true
      message_key: message

output.logstash:
  hosts: ["logstash:5044"]

خط أنابيب لوجستاش

# logstash-captcha.conf
input {
  beats {
    port => 5044
  }
}

filter {
  # Parse JSON logs
  json {
    source => "message"
    target => "captcha"
  }

  # Add computed fields
  if [captcha][solve_time] {
    mutate {
      add_field => {
        "solve_time_bucket" => "fast"
      }
    }
    if [captcha][solve_time] > 30 {
      mutate { update => { "solve_time_bucket" => "medium" } }
    }
    if [captcha][solve_time] > 90 {
      mutate { update => { "solve_time_bucket" => "slow" } }
    }
  }

  # Extract date
  date {
    match => ["[captcha][timestamp]", "ISO8601"]
    target => "@timestamp"
  }
}

output {
  elasticsearch {
    hosts => ["elasticsearch:9200"]
    index => "captcha-logs-%{+YYYY.MM.dd}"
  }
}

قالب فهرس Elasticsearch

{
  "index_patterns": ["captcha-logs-*"],
  "template": {
    "settings": {
      "number_of_shards": 1,
      "number_of_replicas": 0
    },
    "mappings": {
      "properties": {
        "captcha_type": { "type": "keyword" },
        "captcha_id": { "type": "keyword" },
        "error_code": { "type": "keyword" },
        "solve_time": { "type": "float" },
        "poll_count": { "type": "integer" },
        "target_url": { "type": "keyword" },
        "level": { "type": "keyword" },
        "message": { "type": "text" }
      }
    }
  }
}

لوحات تحكم كيبانا

استفسارات مفيدة

# All errors in the last hour
level:error AND @timestamp:[now-1h TO now]

# Timeout errors for reCAPTCHA
error_code:TIMEOUT AND captcha_type:recaptcha_v2

# Slow solves (> 60 seconds)
solve_time:>60

# Errors for a specific target URL
level:error AND target_url:"example.com"

# Specific CAPTCHA ID investigation
captcha_id:"73519847"

استكشاف الأخطاء وإصلاحها

الخطوات التالية

• البدء السريع مع CaptchaAI: حلّ أول كابتشا في 5 دقائق
• كيفية حلّ reCAPTCHA v2 عبر الـ API: دليل خطوة بخطوة
• كيفية حل Cloudflare Turnstile باستخدام واجهة API
• كيفية حل GeeTest v3 باستخدام API

أدلة ذات صلة

• البدء السريع مع CaptchaAI: حلّ أول كابتشا في 5 دقائق
• مراقبة أسعار التجارة الإلكترونية عند ظهور اختبارات CAPTCHA