CAPTCHA-Behandlung zur Flugstatusüberwachung

Die Überwachung des Flugstatus erfordert häufige Überprüfungen über mehrere Fluglinien- und Flughafenportale hinweg. Diese Portale schützen ihre Echtzeitdaten mit Cloudflare Turnstile, reCAPTCHA und benutzerdefinierten CAPTCHAs – insbesondere, wenn sie wiederholte automatisierte Abfragen erkennen. Hier erfahren Sie, wie Sie mit CAPTCHAs umgehen und gleichzeitig zuverlässige Flugverfolgungstools erstellen.

Wo CAPTCHAs erscheinen

Flugüberwachungsarchitektur

import requests
import time
from datetime import datetime

class FlightMonitor:
    def __init__(self, api_key):
        self.api_key = api_key
        self.session = requests.Session()
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
        })

    def check_flight(self, airline_url, flight_number):
        """Check flight status, handling CAPTCHAs if encountered."""
        response = self.session.get(
            f"{airline_url}/flight-status/{flight_number}"
        )

        if self._is_captcha_page(response):
            response = self._solve_and_retry(response, airline_url)

        return self._parse_flight_data(response.text)

    def _is_captcha_page(self, response):
        return (
            response.status_code == 403 or
            "cf-turnstile" in response.text or
            "g-recaptcha" in response.text
        )

    def _solve_and_retry(self, response, url):
        import re

        # Detect CAPTCHA type
        if "cf-turnstile" in response.text:
            match = re.search(r'data-sitekey="(0x[^"]+)"', response.text)
            token = self._solve_turnstile(match.group(1), url)
            field = "cf-turnstile-response"
        else:
            match = re.search(r'data-sitekey="([^"]+)"', response.text)
            token = self._solve_recaptcha(match.group(1), url)
            field = "g-recaptcha-response"

        return self.session.post(url, data={field: token})

    def _solve_turnstile(self, site_key, page_url):
        resp = requests.post("https://ocr.captchaai.com/in.php", data={
            "key": self.api_key,
            "method": "turnstile",
            "sitekey": site_key,
            "pageurl": page_url,
            "json": 1
        })
        task_id = resp.json()["request"]
        return self._poll_result(task_id)

    def _solve_recaptcha(self, site_key, page_url):
        resp = requests.post("https://ocr.captchaai.com/in.php", data={
            "key": self.api_key,
            "method": "userrecaptcha",
            "googlekey": site_key,
            "pageurl": page_url,
            "json": 1
        })
        task_id = resp.json()["request"]
        return self._poll_result(task_id)

    def _poll_result(self, task_id):
        for _ in range(60):
            time.sleep(3)
            result = requests.get("https://ocr.captchaai.com/res.php", params={
                "key": self.api_key,
                "action": "get",
                "id": task_id,
                "json": 1
            })
            data = result.json()
            if data["status"] == 1:
                return data["request"]
        raise TimeoutError("CAPTCHA solve timed out")

    def _parse_flight_data(self, html):
        # Parse flight status from HTML
        from bs4 import BeautifulSoup
        soup = BeautifulSoup(html, "html.parser")

        def text_or_none(node):
            return node.text.strip() if node and node.text else None

        return {
            "status": text_or_none(soup.select_one(".flight-status")),
            "departure": text_or_none(soup.select_one(".departure-time")),
            "arrival": text_or_none(soup.select_one(".arrival-time")),
            "gate": text_or_none(soup.select_one(".gate-info")),
            "checked_at": datetime.now().isoformat()
        }

Regelmäßige Überwachung mit CAPTCHA-Verwaltung

def monitor_flight(monitor, airline_url, flight_number, 
                   interval_seconds=300, max_checks=48):
    """Monitor a flight every N seconds, handling CAPTCHAs as needed."""
    history = []

    for check_num in range(max_checks):
        try:
            status = monitor.check_flight(airline_url, flight_number)
            history.append(status)

            # Alert on changes
            if len(history) > 1 and status["status"] != history[-2]["status"]:
                print(f"Status changed: {history[-2]['status']} → {status['status']}")

            print(f"Check {check_num + 1}: {status['status']} "
                  f"(Gate: {status.get('gate', 'Coming soon')})")

        except Exception as e:
            print(f"Check {check_num + 1} failed: {e}")

        time.sleep(interval_seconds)

    return history

# Usage
monitor = FlightMonitor("YOUR_API_KEY")
monitor_flight(monitor, "https://airline.example.com", "AA1234")

Multi-Airline-Überwachung (JavaScript)

class FlightTracker {
  constructor(apiKey) {
    this.apiKey = apiKey;
    this.flights = new Map();
  }

  async addFlight(airline, flightNumber, checkUrl) {
    this.flights.set(flightNumber, {
      airline,
      url: checkUrl,
      history: [],
      lastCheck: null
    });
  }

  async checkAll() {
    const results = [];

    for (const [flightNum, flight] of this.flights) {
      try {
        const status = await this.checkFlight(flight.url, flightNum);
        flight.history.push(status);
        flight.lastCheck = new Date();
        results.push({ flight: flightNum, ...status });
      } catch (error) {
        results.push({ flight: flightNum, error: error.message });
      }
    }

    return results;
  }

  async checkFlight(url, flightNumber) {
    const response = await fetch(`${url}/status/${flightNumber}`);
    const html = await response.text();

    // Check for CAPTCHA
    if (html.includes('cf-turnstile') || response.status === 403) {
      return this.solveAndRetry(url, flightNumber, html);
    }

    return this.parseStatus(html);
  }

  async solveAndRetry(url, flightNumber, html) {
    const siteKeyMatch = html.match(/data-sitekey="(0x[^"]+)"/);
    if (!siteKeyMatch) throw new Error('No sitekey found');

    const token = await this.solveTurnstile(siteKeyMatch[1], url);

    const response = await fetch(`${url}/status/${flightNumber}`, {
      method: 'POST',
      body: new URLSearchParams({ 'cf-turnstile-response': token })
    });

    return this.parseStatus(await response.text());
  }
}

Überwachungshäufigkeit und CAPTCHA-Raten

Sitzungsoptimierung

Reduzieren Sie CAPTCHA-Begegnungen, indem Sie den Sitzungsstatus beibehalten:

Fehlerbehebung

Verwandte Leitfäden

• Cloudflare Turnstile per API lösen
• Airline-Ticketpreise überwachen
• Geschützte Websites scrapen