Zeitreihendaten für CAPTCHA-Lösungsleistungstrends

Point-in-Time-Metriken sagen Ihnen, was gerade passiert. Zeitreihendaten geben Aufschluss darüber, was sich wann geändert hat und ob etwas auf ein Problem hindeutet. Verfolgen Sie CAPTCHA-Lösungsraten, Latenz und Kosten im Laufe der Zeit, um Verschlechterungen zu erkennen, bevor sie sich auf Ihre Pipeline auswirken.

Was zu verfolgen ist

Prometheus + Python (Push Gateway)

Instrumentieren Sie Ihren Solver

import os
import time
import requests
from prometheus_client import CollectorRegistry, Counter, Histogram, Gauge, push_to_gateway

registry = CollectorRegistry()

SOLVE_TOTAL = Counter(
    "captcha_solve_total", "Total CAPTCHA solve attempts",
    ["type", "status"], registry=registry
)
SOLVE_LATENCY = Histogram(
    "captcha_solve_latency_seconds", "CAPTCHA solve latency",
    ["type"], buckets=[5, 10, 15, 20, 30, 45, 60, 90, 120],
    registry=registry
)
SOLVE_COST = Counter(
    "captcha_solve_cost_dollars", "Total cost of CAPTCHA solves",
    ["type"], registry=registry
)
API_BALANCE = Gauge(
    "captcha_api_balance_dollars", "CaptchaAI account balance",
    registry=registry
)

API_KEY = os.environ["CAPTCHAAI_API_KEY"]
PUSHGATEWAY = os.environ.get("PUSHGATEWAY_URL", "localhost:9091")


def solve_with_metrics(sitekey, pageurl, captcha_type="recaptcha_v2"):
    start = time.time()

    resp = requests.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:
        SOLVE_TOTAL.labels(type=captcha_type, status="submit_error").inc()
        push_metrics()
        return {"error": data.get("request")}

    captcha_id = data["request"]

    for _ in range(60):
        time.sleep(5)
        result = requests.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 = time.time() - start
            SOLVE_TOTAL.labels(type=captcha_type, status="solved").inc()
            SOLVE_LATENCY.labels(type=captcha_type).observe(elapsed)
            SOLVE_COST.labels(type=captcha_type).inc(0.00299)
            push_metrics()
            return {"solution": result["request"]}

        if result.get("request") != "CAPCHA_NOT_READY":
            SOLVE_TOTAL.labels(type=captcha_type, status="error").inc()
            push_metrics()
            return {"error": result.get("request")}

    SOLVE_TOTAL.labels(type=captcha_type, status="timeout").inc()
    push_metrics()
    return {"error": "TIMEOUT"}


def push_metrics():
    try:
        push_to_gateway(PUSHGATEWAY, job="captcha_solver", registry=registry)
    except Exception:
        pass  # Don't fail solving because metrics push failed


def update_balance():
    resp = requests.get("https://ocr.captchaai.com/res.php", params={
        "key": API_KEY, "action": "getbalance"
    })
    try:
        balance = float(resp.text)
        API_BALANCE.set(balance)
        push_metrics()
    except ValueError:
        pass

Prometheus-Anfragen

# Success rate over last hour
rate(captcha_solve_total{status="solved"}[1h])
/ rate(captcha_solve_total[1h]) * 100

# P95 solve latency
histogram_quantile(0.95, rate(captcha_solve_latency_seconds_bucket[1h]))

# Error rate by type
rate(captcha_solve_total{status="error"}[1h])

# Hourly cost
increase(captcha_solve_cost_dollars_total[1h])

InfluxDB + Python

Schreiben Sie Lösungsmetriken

from influxdb_client import InfluxDBClient, Point
from influxdb_client.client.write_api import SYNCHRONOUS

INFLUX_URL = os.environ.get("INFLUX_URL", "http://localhost:8086")
INFLUX_TOKEN = os.environ.get("INFLUX_TOKEN", "")
INFLUX_ORG = os.environ.get("INFLUX_ORG", "captcha")
INFLUX_BUCKET = os.environ.get("INFLUX_BUCKET", "captcha_metrics")

influx_client = InfluxDBClient(url=INFLUX_URL, token=INFLUX_TOKEN, org=INFLUX_ORG)
write_api = influx_client.write_api(write_options=SYNCHRONOUS)


def record_solve_metric(captcha_type, status, elapsed_ms, cost=0.0, error=None):
    point = (
        Point("captcha_solve")
        .tag("type", captcha_type)
        .tag("status", status)
        .field("elapsed_ms", elapsed_ms)
        .field("cost", cost)
        .field("success", 1 if status == "solved" else 0)
    )
    if error:
        point = point.tag("error_code", error)
    write_api.write(bucket=INFLUX_BUCKET, record=point)


def record_balance(balance):
    point = Point("captcha_balance").field("balance", balance)
    write_api.write(bucket=INFLUX_BUCKET, record=point)

InfluxDB-Abfragen (Flux)

// Success rate over last 24 hours (1-hour windows)
from(bucket: "captcha_metrics")
  |> range(start: -24h)
  |> filter(fn: (r) => r._measurement == "captcha_solve" and r._field == "success")
  |> aggregateWindow(every: 1h, fn: mean)
  |> map(fn: (r) => ({r with _value: r._value * 100.0}))
  |> yield(name: "success_rate")

// Average solve time by type
from(bucket: "captcha_metrics")
  |> range(start: -24h)
  |> filter(fn: (r) => r._measurement == "captcha_solve" and r._field == "elapsed_ms" and r.status == "solved")
  |> group(columns: ["type"])
  |> aggregateWindow(every: 1h, fn: mean)
  |> yield(name: "avg_latency")

// Cumulative cost
from(bucket: "captcha_metrics")
  |> range(start: -24h)
  |> filter(fn: (r) => r._measurement == "captcha_solve" and r._field == "cost")
  |> cumulativeSum()
  |> yield(name: "cumulative_cost")

JavaScript-Implementierung (Prometheus)

const client = require("prom-client");
const axios = require("axios");

const register = new client.Registry();
const API_KEY = process.env.CAPTCHAAI_API_KEY;

const solveTotal = new client.Counter({
  name: "captcha_solve_total",
  help: "Total CAPTCHA solve attempts",
  labelNames: ["type", "status"],
  registers: [register],
});

const solveLatency = new client.Histogram({
  name: "captcha_solve_latency_seconds",
  help: "CAPTCHA solve latency",
  labelNames: ["type"],
  buckets: [5, 10, 15, 20, 30, 45, 60, 90, 120],
  registers: [register],
});

async function solveWithMetrics(sitekey, pageurl, type = "recaptcha_v2") {
  const start = Date.now();

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

  if (submit.data.status !== 1) {
    solveTotal.inc({ type, status: "submit_error" });
    return { error: submit.data.request };
  }

  const captchaId = submit.data.request;

  for (let i = 0; i < 60; i++) {
    await new Promise((r) => setTimeout(r, 5000));
    const poll = await axios.get("https://ocr.captchaai.com/res.php", {
      params: { key: API_KEY, action: "get", id: captchaId, json: 1 },
    });

    if (poll.data.status === 1) {
      const elapsed = (Date.now() - start) / 1000;
      solveTotal.inc({ type, status: "solved" });
      solveLatency.observe({ type }, elapsed);
      return { solution: poll.data.request };
    }

    if (poll.data.request !== "CAPCHA_NOT_READY") {
      solveTotal.inc({ type, status: "error" });
      return { error: poll.data.request };
    }
  }

  solveTotal.inc({ type, status: "timeout" });
  return { error: "TIMEOUT" };
}

// Expose metrics endpoint
const express = require("express");
const app = express();
app.get("/metrics", async (req, res) => {
  res.set("Content-Type", register.contentType);
  res.end(await register.metrics());
});
app.listen(9090);

Datenbankvergleich

Fehlerbehebung

Verwandte Leitfäden

• Strukturiertes Logging für CAPTCHA-Vorgänge
• SQLite für lokales CAPTCHA-Lösungs-Caching
• API-Antwortformate und Fehlercodes