通过验证码处理进行零售库存监控

电子商务平台使用验证码保护产品页面和库存数据，以防止竞争对手抓取和机器人购买。 CaptchaAI 支持自动库存监控、价格跟踪和可用性警报。

电商平台验证码

产品监控

import requests
import time
import re
import json
from datetime import datetime
from bs4 import BeautifulSoup

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


def solve_captcha(method, sitekey, pageurl, **kwargs):
    data = {
        "key": CAPTCHAAI_KEY, "method": method,
        "googlekey": sitekey, "pageurl": pageurl, "json": 1,
    }
    data.update(kwargs)
    resp = requests.post(f"{CAPTCHAAI_URL}/in.php", data=data)
    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,
        })
        r = result.json()
        if r["request"] != "CAPCHA_NOT_READY":
            return r["request"]
    raise TimeoutError("Timeout")


class RetailMonitor:
    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",
            "Accept": "text/html,application/xhtml+xml,*/*;q=0.8",
            "Accept-Language": "en-US,en;q=0.9",
        })

    def check_product(self, url):
        """Check single product's price and availability."""
        resp = self.session.get(url, timeout=30)

        # Handle CAPTCHA
        if self._has_captcha(resp.text):
            resp = self._solve_and_retry(resp.text, url)

        soup = BeautifulSoup(resp.text, "html.parser")
        return {
            "url": url,
            "title": self._text(soup, "h1, .product-title, #productTitle"),
            "price": self._text(soup, ".price, .a-price .a-offscreen, .prod-price"),
            "availability": self._text(soup, "#availability, .stock-status, .fulfillment"),
            "in_stock": self._check_stock(soup),
            "timestamp": datetime.now().isoformat(),
        }

    def monitor_products(self, product_urls, interval_sec=1800):
        """Continuously monitor products for changes."""
        history = {}

        while True:
            for url in product_urls:
                try:
                    current = self.check_product(url)

                    # Check for changes
                    prev = history.get(url)
                    if prev:
                        changes = self._detect_changes(prev, current)
                        if changes:
                            self._alert(current["title"], changes)

                    history[url] = current
                    time.sleep(3)

                except Exception as e:
                    print(f"Error checking {url}: {e}")

            print(f"Cycle complete: {len(product_urls)} products checked")
            time.sleep(interval_sec)

    def track_prices(self, product_urls, output_file="prices.json"):
        """Single price check across all products."""
        results = []
        for url in product_urls:
            try:
                data = self.check_product(url)
                results.append(data)
                time.sleep(3)
            except Exception as e:
                results.append({"url": url, "error": str(e)})

        with open(output_file, "w") as f:
            json.dump(results, f, indent=2)
        print(f"Tracked {len(results)} products → {output_file}")
        return results

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

    def _solve_and_retry(self, html, url):
        match = re.search(r'data-sitekey="([^"]+)"', html)
        if not match:
            return self.session.get(url)

        sitekey = match.group(1)
        if 'cf-turnstile' in html:
            token = solve_captcha("turnstile", sitekey, url)
            return self.session.post(url, data={"cf-turnstile-response": token})
        else:
            token = solve_captcha("userrecaptcha", sitekey, url)
            return self.session.post(url, data={"g-recaptcha-response": token})

    def _text(self, soup, selector):
        el = soup.select_one(selector)
        return el.get_text(strip=True) if el else ""

    def _check_stock(self, soup):
        stock_el = soup.select_one("#availability, .stock-status")
        if stock_el:
            text = stock_el.get_text(strip=True).lower()
            return "in stock" in text or "available" in text
        return None

    def _detect_changes(self, prev, current):
        changes = []
        if prev["price"] != current["price"]:
            changes.append(f"Price: {prev['price']} → {current['price']}")
        if prev["in_stock"] != current["in_stock"]:
            status = "In Stock" if current["in_stock"] else "Out of Stock"
            changes.append(f"Stock: → {status}")
        return changes

    def _alert(self, title, changes):
        print(f"ALERT [{title}]: {', '.join(changes)}")


# Usage
monitor = RetailMonitor(
    proxy="http://user:pass@residential.proxy.com:5000"
)

products = [
    "https://store.example.com/product/abc123",
    "https://store.example.com/product/def456",
    "https://store.example.com/product/ghi789",
]

# One-time price check
results = monitor.track_prices(products)

# Or continuous monitoring (every 30 min)
# monitor.monitor_products(products, interval_sec=1800)

全品类库存扫描

def scan_category(base_url, category, max_pages=20):
    """Scan an entire product category for stock status."""
    monitor = RetailMonitor(
        proxy="http://user:pass@residential.proxy.com:5000"
    )

    all_products = []
    for page in range(1, max_pages + 1):
        url = f"{base_url}/{category}?page={page}"
        resp = monitor.session.get(url, timeout=30)

        if monitor._has_captcha(resp.text):
            resp = monitor._solve_and_retry(resp.text, url)

        soup = BeautifulSoup(resp.text, "html.parser")
        items = soup.select(".product-card, .s-result-item")

        if not items:
            break

        for item in items:
            all_products.append({
                "name": monitor._text(item, ".product-name, .a-text-normal"),
                "price": monitor._text(item, ".price, .a-price"),
                "stock": monitor._text(item, ".stock, .a-color-success"),
                "url": item.select_one("a")["href"] if item.select_one("a") else "",
            })

        time.sleep(3)

    return all_products

竞争对手价格比较

def compare_product_across_stores(product_name, stores):
    """Compare prices across retailers for the same product."""
    results = []

    for store in stores:
        monitor = RetailMonitor(proxy=store.get("proxy"))
        search_url = f"{store['base_url']}/search?q={product_name}"

        try:
            resp = monitor.session.get(search_url, timeout=30)
            if monitor._has_captcha(resp.text):
                resp = monitor._solve_and_retry(resp.text, search_url)

            soup = BeautifulSoup(resp.text, "html.parser")
            first_result = soup.select_one(".product-card, .s-result-item")

            if first_result:
                results.append({
                    "store": store["name"],
                    "price": monitor._text(first_result, ".price"),
                    "in_stock": "in stock" in first_result.get_text().lower(),
                })
        except Exception as e:
            results.append({"store": store["name"], "error": str(e)})

        time.sleep(5)

    results.sort(key=lambda x: x.get("price", "zzzz"))
    return results

监控时间表

故障排除

常问问题

我多久可以检查一次产品页面？

对于大多数零售商来说，每种产品每 30-60 分钟一次是安全的。较高频率的监控（1-5 分钟）有效，但需要更多代理并触发验证码。

我应该使用轮换会话还是粘性会话？

轮换——每个产品页面都是一个独立的请求。只有在检查产品详细信息需要导航时才需要粘性会话。

我可以监控数千种产品吗？

是的。将请求分散到多个代理 IP 并交错检查。如果有 1,000 个产品延迟 3 秒，则完整周期大约需要 50 分钟。

相关指南

• 轮换自有服务器基础设施
• 粘性会话与轮换会话
• 供应链监控

实时跟踪零售库存——获取您的 CaptchaAI 密钥用于自动验证码处理。