使用验证码处理进行供应链监控

供应链可视性需要来自数百个供应商门户、物流平台和库存系统的数据。其中许多都通过验证码保护其数据。 CaptchaAI 可以应对这些挑战，使监控管道不间断地运行。

验证码在哪里阻止供应链数据

多供应商监控

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))

运费监控

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 []

库存变动警报

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)

提供商后备政策

• 将关键供应商与可选来源分开，这样一次故障就不会导致整个监控报告消失。
• 定义何时可以接受过时的数据以及何时缺失的供应商必须触发明确的事件。
• 将供应商面临的持续验证码压力升级为采购风险，而不仅仅是工程错误。

故障排除

常问问题

我应该多久检查一次供应商库存？

大多数供应商每天都会这样做。供应短缺期间，关键部件按小时计算。过于频繁的检查会更快地触发验证码。

我可以监控数百家供应商吗？

是的。轮换供应商，每个供应商之间都有延迟。使用QA 测试会话在 IP 之间分配负载。

哪种验证码类型在供应链网站上最常见？

reCAPTCHA v2 在供应商门户网站上，Cloudflare Turnstile 在物流/carrier 网站上。较旧的制造商网站通常使用图像验证码。

相关指南

• 轮换自有服务器基础设施
• 粘性会话与轮换会话
• 浏览器会话持久性

保持您的供应链可见——获取您的 CaptchaAI 密钥并自动收集所有供应商门户的数据。