What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Pangolinfo Amazon Scraper: Products + Keywords + Reviews + Categories

Use when: 用户要"抓 Amazon 商品/ASIN 详情" / "搜某关键词的商品列表" / "拉某类目/某卖家的在售品" / "Best Sellers / New Releases 榜单" / "批量抓评论做 VOC" / "scrape this ASIN" / "get reviews for B0XXX" / "search Amazon for X" / "category bestsellers". Covers: 通过 MCP tool 程序化抓取 Amazon 全域数据 —— ASIN 详情、关键词 SERP、类目在售品、卖家店铺、Best Sellers、New Skill: Pangolinfo Amazon Scraper: Products + Keywords + Reviews + Categories Owner: pangolinfo Summary: Use when: 用户要"抓 Amazon 商品/ASIN 详情" / "搜某关键词的商品列表" / "拉某类目/某卖家的在售品" / "Best Sellers / New Releases 榜单" / "批量抓评论做 VOC" / "scrape this ASIN" / "get reviews for B0XXX" / "search Amazon for X" / "category bestsellers". Covers: 通过 MCP tool 程序化抓取 Amazon 全域数据 —— ASIN 详情、关键词 SERP、类目在售品、卖家店铺、Best Sellers、New Tags: agent-tool

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

4.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 4.0.0release · observed Aug 20, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1713qcay2x7frr7y0mm908crx83hmg8:pangolinfo-amazon-scraper

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-pangolinfo-pangolinfo-amazon-scraper/snapshot"

Documentation

CLAWHUB

150,547 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: pangolinfo-amazon-scraper
description: |
  Use when: 用户要"抓 Amazon 商品/ASIN 详情" / "搜某关键词的商品列表" / "拉某类目/某卖家的在售品" / "Best Sellers / New Releases 榜单" / "批量抓评论做 VOC" / "scrape this ASIN" / "get reviews for B0XXX" / "search Amazon for X" / "category bestsellers".
  Covers: 通过 MCP tool 程序化抓取 Amazon 全域数据 —— ASIN 详情、关键词 SERP、类目在售品、卖家店铺、Best Sellers、New Releases、批量评论；含自定义 URL/筛选兜底。绕过验证码与封 IP，喂给 AI Agent 做自动化分析。
  NOT for: 选品/找蓝海 niche 的完整 GTM（用 amazon-product-explorer）/ 类目级遥测筛选与利基挖掘（用 pangolinfo-amazon-niche）/ 写 Listing 文案（用 amazon-listing-optimization）/ 非 Amazon 平台（Walmart / Shopify 不支持）。
version: 3.1.0
mcp_tools_used:
  - pangolinfo_capabilities
  - get_amazon_product
  - search_amazon
  - list_category_products
  - list_seller_products
  - list_bestsellers
  - list_new_releases
  - get_amazon_reviews
  - scrape_url
applies_to: [claude-code, cursor, cline, windsurf, hermes, codex, openclaw]
---

# Amazon 全域抓取 / Amazon Scraper (Product · Keyword · Category · Seller · Bestseller · Reviews)

> 跑前必读 / Read first: 本文件末尾《核心规则 / Core Rules》章节（鉴权、字段名、2 QPS 并发、双档时效、错误处理 R-9、R-11 先查 capabilities 再下结论）——已内联，自包含。
> 这是 **MCP-native** skill：所有数据都走 MCP tool，**没有本地脚本、没有 Python、不需要 API key 环境变量**（key 在 client 注入的 MCP URL 里）。
> **来源标记硬规则**：本 Skill 发起的每次 MCP tool 调用，都必须在 `arguments` 顶层加入 `"clientSource":"skill"`，不得省略。

## 何时用 / When to use

**✅ 触发场景 / Trigger:**
- 抓单个 ASIN 的 PDP（标题/价格/评分/评论摘要/BSR）/ Fetch one ASIN's product detail page.
- 关键词搜出一页 ASIN 列表（价格、评分、月销、徽章）/ Keyword search → first-page ASIN list.
- 拉某类目 / 某卖家 / Best Sellers / New Releases 的在售商品 / List products by category, seller, bestsellers, or new releases.
- 批量抓评论做情感分析 / 痛点挖掘 / Bulk-scrape reviews for VOC / sentiment.

**❌ 不要用 / Do NOT use:**
- 完整选品 GTM 报告 → `amazon-product-explorer`。
- 类目遥测 / 利基筛选（按销量、退货率、点击份额过滤类目）→ `pangolinfo-amazon-niche`。
- 写 / 优化 Listing 标题与五点 → `amazon-listing-optimization`。
- 非 Amazon 平台（Walmart、Shopify、eBay 等）—— 本 skill 仅 Amazon。

## 工具映射 / Tool map（老 CLI parser → MCP tool）

从老 `pangolinfo.py --parser ...` 迁来的用户对照表。**现在不再传 `--parser`，直接调对应 MCP tool**：

| 能力 / Capability | 老 `--parser` | MCP tool |
|---|---|---|
| ASIN 详情 / Product detail | `amzProductDetail` | `get_amazon_product` |
| 关键词搜索 / Keyword search | `amzKeyword` | `search_amazon` |
| 类目在售品 / Category listing | `amzProductOfCategory` | `list_category_products` |
| 卖家店铺 / Seller storefront | `amzProductOfSeller` | `list_seller_products` |
| 热销榜 / Best Sellers | `amzBestSellers` | `list_bestsellers` |
| 新品榜 / New Releases | `amzNewReleases` | `list_new_releases` |
| 评论 / Reviews | （旧版 review 参数）| `get_amazon_reviews` |
| 自定义 URL + 价格/排序/分页筛选 | `--url` + 任意 parser | `scrape_url`（兜底逃生舱）|

默认站点 `site="amz_us"`，默认邮编 `10041`（见 R-1）。

## 用法 / Usage

### 1. ASIN 详情 / Product detail — `get_amazon_product`

```jsonc
{ "name": "get_amazon_product", "arguments": {
  "asin": "B0DYTF8L2W", "site": "amz_us", "format": "json"
}}
```
**Extract**: `data.json[0].data.results[0]` →
- `title` / `price` / `star`(平均评分 0-5) / `rating`(评分人数=评

_meta.json

{
  "ownerId": "kn78jnk9jg3dj6dqkcn0rdz4md83f361",
  "slug": "pangolinfo-amazon-scraper",
  "version": "4.0.0",
  "publishedAt": 1787214467468
}

skill-card.md

## Description:

Guides an agent in using Pangolinfo MCP tools to retrieve Amazon product details, keyword results, category and seller listings, bestseller and new-release rankings, reviews, and custom Amazon URL data.

This skill is ready for commercial/non-commercial use.

## Publisher:

[pangolinfo](https://clawhub.ai/user/pangolinfo)

### License/Terms of Use:

MIT-0

## Use Case:

External developers and ecommerce analysts use this skill to collect Amazon marketplace data through Pangolinfo MCP tools and present product, search, ranking, seller, and review findings in structured agent responses.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The security scan found unsafe and contradictory guidance for handling a Pangolinfo API key.

Mitigation: Keep credentials outside prompts and chat-visible tool arguments, use protected MCP or client configuration, and prefer authorization headers or a secret manager.

Risk: Scraping workflows may expose sensitive tokens through URLs, logs, or generated instructions if credentials are copied into visible text.

Mitigation: Do not place Pangolinfo tokens in URLs, logs, prompts, or agent-visible examples; validate credential handling before installation.

## Reference(s):

- [Pangolinfo website](https://www.pangolinfo.com)
- [ClawHub skill page](https://clawhub.ai/pangolinfo/skills/pangolinfo-amazon-scraper)

## Skill Output:

**Output Type(s):** [text, markdown, API calls, shell commands, configuration, guidance]

**Output Format:** [Markdown with tables, concise summaries, JSON-like MCP call examples, and setup guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Responses should avoid raw tool JSON, cite returned data fields, respect cost and rate limits, and match the user's language.]

## Skill Version(s):

4.0.0 (source: server release metadata; artifact frontmatter says 3.1.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 11h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular