Supply Chain Monitoring with CAPTCHA Handling

Supply chain visibility requires data from hundreds of supplier portals, logistics platforms, and inventory systems. Many of these protect their data behind CAPTCHAs. CaptchaAI handles these challenges so monitoring pipelines run uninterrupted.

Where CAPTCHAs Block Supply Chain Data

Source Type	CAPTCHA Type	Data	Frequency
Supplier portals	reCAPTCHA v2	Inventory, pricing, lead times	Daily
Shipping carriers	Cloudflare Turnstile	Tracking, rates, delivery ETAs	Hourly
Manufacturer catalogs	Image CAPTCHA	Product specs, MOQs	Weekly
Customs portals	reCAPTCHA v2	Duty rates, tariff codes	Daily
Port authorities	Image CAPTCHA	Vessel schedules, port congestion	Every 6 hours
Commodity exchanges	reCAPTCHA v3	Spot prices, futures	Real-time

Multi-Supplier Monitor

import requests
import time
import re
import json
import base64
from datetime import datetime

CAPTCHAAI_KEY = "YOUR_API_KEY"
CAPTCHAAI_URL = "https://ocr.captchaai.com"


def solve_recaptcha(sitekey, pageurl):
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "userrecaptcha",
        "googlekey": sitekey, "pageurl": pageurl, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(60):
        time.sleep(5)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


def solve_turnstile(sitekey, pageurl):
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "turnstile",
        "sitekey": sitekey, "pageurl": pageurl, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(60):
        time.sleep(5)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


def solve_image(image_bytes):
    img_b64 = base64.b64encode(image_bytes).decode()
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data={
        "key": CAPTCHAAI_KEY, "method": "base64",
        "body": img_b64, "json": 1,
    })
    task_id = resp.json()["request"]
    for _ in range(20):
        time.sleep(3)
        result = requests.get(f"{CAPTCHAAI_URL}/res.php", params={
            "key": CAPTCHAAI_KEY, "action": "get",
            "id": task_id, "json": 1,
        })
        data = result.json()
        if data["request"] != "CAPCHA_NOT_READY":
            return data["request"]
    raise TimeoutError("Timeout")


class SupplyChainMonitor:
    def __init__(self, suppliers, proxy=None):
        self.suppliers = suppliers
        self.session = requests.Session()
        if proxy:
            self.session.proxies = {"http": proxy, "https": proxy}
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 Chrome/126.0.0.0 Safari/537.36",
        })

    def check_all(self):
        """Check inventory and pricing across all suppliers."""
        report = {
            "timestamp": datetime.now().isoformat(),
            "suppliers": {},
        }

        for supplier in self.suppliers:
            try:
                data = self._check_supplier(supplier)
                report["suppliers"][supplier["name"]] = {
                    "status": "success",
                    "data": data,
                }
            except Exception as e:
                report["suppliers"][supplier["name"]] = {
                    "status": "error",
                    "error": str(e),
                }
            time.sleep(3)

        return report

    def _check_supplier(self, supplier):
        url = supplier["url"]
        resp = self.session.get(url, timeout=30)

        # Handle CAPTCHA based on type
        captcha_type = supplier.get("captcha_type")
        if captcha_type and self._has_captcha(resp.text):
            resp = self._solve_captcha(resp, url, supplier)

        from bs4 import BeautifulSoup
        soup = BeautifulSoup(resp.text, "html.parser")

        return {
            "products": self._extract_inventory(soup),
            "last_updated": self._extract_date(soup),
        }

    def _has_captcha(self, html):
        return any(tag in html.lower() for tag in [
            'data-sitekey', 'g-recaptcha', 'cf-turnstile', 'captcha',
        ])

    def _solve_captcha(self, resp, url, supplier):
        captcha_type = supplier.get("captcha_type", "recaptcha")
        sitekey = supplier.get("sitekey", "")

        if not sitekey:
            match = re.search(r'data-sitekey="([^"]+)"', resp.text)
            sitekey = match.group(1) if match else ""

        if captcha_type == "turnstile":
            token = solve_turnstile(sitekey, url)
            return self.session.post(url, data={"cf-turnstile-response": token})
        elif captcha_type == "image":
            match = re.search(r'src="(/captcha[^"]+)"', resp.text)
            if match:
                img_resp = self.session.get(url.rstrip("/") + match.group(1))
                answer = solve_image(img_resp.content)
                return self.session.post(url, data={"captcha": answer})
        else:
            token = solve_recaptcha(sitekey, url)
            return self.session.post(url, data={"g-recaptcha-response": token})

        return resp

    def _extract_inventory(self, soup):
        items = []
        for row in soup.select("table.inventory tr, .product-row"):
            cols = row.select("td, .col")
            if len(cols) >= 3:
                items.append({
                    "sku": cols[0].get_text(strip=True),
                    "stock": cols[1].get_text(strip=True),
                    "price": cols[2].get_text(strip=True),
                })
        return items

    def _extract_date(self, soup):
        date_el = soup.select_one(".last-updated, .update-time")
        return date_el.get_text(strip=True) if date_el else ""


# Configure suppliers
suppliers = [
    {
        "name": "Supplier A",
        "url": "https://supplier-a.example.com/inventory",
        "captcha_type": "recaptcha",
        "sitekey": "6Lc_xxxxxxx",
    },
    {
        "name": "Carrier B",
        "url": "https://carrier-b.example.com/rates",
        "captcha_type": "turnstile",
        "sitekey": "0x4AAAAAAA_xxx",
    },
    {
        "name": "Manufacturer C",
        "url": "https://manufacturer-c.example.com/catalog",
        "captcha_type": "image",
    },
]

monitor = SupplyChainMonitor(
    suppliers=suppliers,
    proxy="http://user:pass@residential.proxy.com:5000",
)
report = monitor.check_all()
print(json.dumps(report, indent=2))

Shipping Rate Monitoring

class ShippingRateTracker:
    def __init__(self, proxy=None):
        self.session = requests.Session()
        if proxy:
            self.session.proxies = {"http": proxy, "https": proxy}
        self.session.headers.update({
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
            "AppleWebKit/537.36 Chrome/126.0.0.0 Safari/537.36",
        })

    def get_rates(self, carrier_url, origin, destination, weight):
        """Fetch shipping rates, handling Turnstile CAPTCHA."""
        resp = self.session.get(carrier_url, timeout=30)

        sitekey_match = re.search(r'data-sitekey="([^"]+)"', resp.text)
        if sitekey_match:
            token = solve_turnstile(sitekey_match.group(1), carrier_url)
            resp = self.session.post(carrier_url, data={
                "origin": origin,
                "destination": destination,
                "weight": weight,
                "cf-turnstile-response": token,
            })

        if resp.status_code == 200:
            return resp.json().get("rates", [])
        return []

Alerting on Stock Changes

def monitor_with_alerts(monitor, alert_thresholds, check_interval=3600):
    """Continuously monitor and alert on inventory changes."""
    previous_data = {}

    while True:
        report = monitor.check_all()

        for supplier, info in report["suppliers"].items():
            if info["status"] != "success":
                continue

            for product in info["data"].get("products", []):
                sku = product["sku"]
                stock = product.get("stock", "")

                # Parse stock level
                try:
                    stock_qty = int(re.sub(r'\D', '', stock))
                except ValueError:
                    continue

                key = f"{supplier}:{sku}"
                prev_qty = previous_data.get(key, stock_qty)

                threshold = alert_thresholds.get(sku, 10)
                if stock_qty < threshold and prev_qty >= threshold:
                    print(f"ALERT: {supplier} - {sku} dropped to {stock_qty}")

                previous_data[key] = stock_qty

        time.sleep(check_interval)

Troubleshooting

Issue	Cause	Fix
Supplier page layout changed	Site redesign	Update CSS selectors
CAPTCHA on every check	Checking too frequently	Increase interval between checks
Session expires mid-check	Portal timeout	Use sticky session, check faster
Rate data missing	Login required	Add authentication step
Wrong prices displayed	Geo-based pricing	Match proxy location to market