Noon 商品数量统计

Noon 商品数量统计工具。输入阿拉伯语关键词，在 noon.com 沙特站搜索，返回搜索结果的商品数量。

Security Scan

The skill's code and instructions match its stated purpose (scraping product counts from noon.com using Puppeteer); nothing requests unrelated credentials or installs from unknown hosts, though claims about automatically bypassing reCAPTCHA are overstated and warrant caution.

Purpose & Capability

Name/description (count products on noon.com) aligns with the included code and README: the skill launches a browser via puppeteer-extra + stealth and extracts the Arabic 'نتائج' count from noon.com/saudi-ar. Required artifacts (puppeteer packages) are consistent with this purpose.

Instruction Scope

SKILL.md instructs running the included index.js and installing puppeteer packages; instructions only access noon.com and do not read other files or environment variables. However, the README claims '自动绕过 reCAPTCHA 验证' while the code only uses stealth and long waits — there is no captcha-solving service or explicit bypass, so that claim is overstated and may mislead users into thinking the tool will evade anti-bot measures reliably.

Install Mechanism

No install spec is embedded; SKILL.md recommends npm install of public packages (puppeteer-extra, plugin, puppeteer). These are standard public npm packages. Note: puppeteer will download a Chromium binary, which is expected but sizable and writes to disk.

Credentials

The skill requests no environment variables, credentials, or config paths. The code does not attempt to access unrelated secrets or files. It does open a visible browser (headless:false), which requires a GUI/X server or a headless workaround.

Persistence & Privilege

The skill does not request permanent/always-on presence, does not modify other skills or system-wide agent settings, and operates only when invoked.

Assessment

This skill appears to do what it says: automate a browser to count search results on noon.com. Before installing, consider: (1) the README's claim of 'bypassing reCAPTCHA' is not implemented (the code only uses a stealth plugin and waits) — relying on it to evade anti-bot protections is risky and may violate site terms; (2) npm install will download Chromium and dependencies and the script runs a visible browser (headless:false), so run it in an isolated environment or CI with an X server if needed; (3) scraping may trigger rate limits or blocking — add throttling and respect the target site's robots/terms; (4) if you need automatic captcha solving or persistent scraping at scale, require explicit review and additional safeguards. If these caveats are acceptable, the skill is internally coherent.

Noon 商品数量统计工具

功能

使用 Chrome 浏览器自动化，在 noon.com/saudi-ar 搜索阿拉伯语关键词，返回搜索结果的总数量。

使用方法

命令行

node ~/.openclaw/workspace/skills/noon-product-count/index.js "阿语关键词"

示例

node ~/.openclaw/workspace/skills/noon-product-count/index.js "سماعات بلوتوث"

批量搜索

node ~/.openclaw/workspace/skills/noon-product-count/index.js "سماعات" "بلوتوث" "لاسلكي"

输出示例

============================================================
🔍 搜索关键词: "سماعات بلوتوث"
============================================================

📊 商品数量: 28,412

技术说明

• 使用 puppeteer-extra + stealth 反检测
• 自动绕过 reCAPTCHA 验证
• 从页面提取 "X نتائج البحث" 格式的总数量

依赖

• puppeteer-extra
• puppeteer-extra-plugin-stealth
• puppeteer

安装依赖

cd ~/.openclaw/workspace/skills/noon-product-count
npm install puppeteer-extra puppeteer-extra-plugin-stealth puppeteer