What makes 1688图片下载器 notable?

1.8K downloads. Trust evidence available

How should 1688图片下载器 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

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

1688图片下载器

从淘宝/1688下载商品图片。触发词：淘宝下载图片、1688下载图片、商品图片下载、淘宝主图、下载商品图、1688图片。支持通过商品名搜索或直接提供商品URL下载主图和详情图。 Skill: 1688图片下载器 Owner: gufusheng1994-dev Summary: 从淘宝/1688下载商品图片。触发词：淘宝下载图片、1688下载图片、商品图片下载、淘宝主图、下载商品图、1688图片。支持通过商品名搜索或直接提供商品URL下载主图和详情图。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-02T02:07:09.808Z | auto 1688图片下载器 1.0.0 初始版本 - 支持通过淘宝/1688商品URL或商品名称搜索下载主图和详情图 - 实现浏览器快照与页面解析，自动提取和下载商品图片 - 图片智能分类保存：主图、颜色图、详情图，规范文件命名 - 提供脚本与交互式浏览器操作两种下载方式 - 自动报告下载结果，包括数量、大小、保存路径 - 兼容反爬/登录/防盗链等常见限制，附常见问题与使用示例 Archive index: A

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

1.0.0

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: 1.0.0release · observed Apr 2, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17etv1pqh59787rn1nn34129n843jpp:1688

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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-gufusheng1994-dev-1688/snapshot"

Documentation

CLAWHUB

5,615 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: 1688图片下载器
description: 从淘宝/1688下载商品图片。触发词：淘宝下载图片、1688下载图片、商品图片下载、淘宝主图、下载商品图、1688图片。支持通过商品名搜索或直接提供商品URL下载主图和详情图。
---

# 淘宝/1688 商品图片下载器

从淘宝、1688等电商平台下载商品图片到本地。

## 工作流程

### 方式一：通过商品URL下载

1. 用户提供商品页面URL
2. 使用浏览器打开页面
3. 快照获取页面内容
4. 提取图片URL
5. 下载保存

### 方式二：通过商品名搜索下载

1. 用户提供商品名称
2. 使用浏览器搜索淘宝/1688
3. 找到目标商品
4. 进入商品详情页
5. 提取并下载图片

## 使用方法

### 下载脚本

脚本位置: `scripts/download_images.py`

```bash
# 直接下载图片URL列表
python scripts/download_images.py --images /tmp/image_urls.txt --output ./商品图片

# 使用配置文件
python scripts/download_images.py --config /tmp/download_config.json
```

### 浏览器操作（推荐）

由于淘宝/1688有反爬机制，**必须使用浏览器**来访问和获取图片：

```javascript
// 使用 browser 工具打开商品页面
browser open --url "商品URL" --profile openclaw

// 获取页面快照，提取图片URL
browser snapshot

// 从快照中识别图片元素，提取src或data-src
```

## 图片保存位置

- 默认保存到: `~/.openclaw/sharespace/商品图片/{商品名}/`
- 主图命名: `main_01.jpg`, `main_02.jpg`, ...
- 详情图命名: `detail_01.jpg`, `detail_02.jpg`, ...

## 执行步骤

当用户请求下载商品图片时：

1. **确认信息**
   - 商品URL 或 商品名称
   - 是否需要详情图（默认只下载主图）
   - 保存目录（默认共享文件夹）

2. **打开浏览器**
   ```
   browser open --url "<商品URL>" --profile openclaw
   ```

3. **获取页面快照**
   ```
   browser snapshot
   ```

4. **提取图片URL**（关键步骤）

   1688的图片URL格式：
   - 主图: `https://cbu01.alicdn.com/img/ibank/O1CN01xxxxx_!!店铺ID-0-cib.jpg`
   - 颜色图: 同上，在颜色选择区域
   - 详情图: 需要从页面script标签或data-src中提取

   **正确提取方法：**
   ```javascript
   // 1. 获取所有img标签的src
   document.querySelectorAll('img').forEach(img => {
     const src = img.src;
     if (src.includes('cbu01.alicdn.com/img/ibank')) {
       images.push(src);
     }
   });
   
   // 2. 从script标签提取详情图（重要！）
   document.querySelectorAll('script').forEach(script => {
     const text = script.textContent;
     const matches = text.match(/https?:\/\/cbu01\.alicdn\.com\/img\/ibank[^"'\s]+/g);
     if (matches) detailImages.push(...matches);
   });
   ```
   
   **URL处理：**
   - 去掉 `.webp` 后缀获取原图
   - 去掉 `220x220.jpg`、`250x250.jpg`、`310x310.jpg` 等缩略图后缀
   - 详情图URL通常以 `!!3827449935-0-cib.jpg` 结尾

5. **创建保存目录**
   ```bash
   mkdir -p ~/.openclaw/sharespace/商品图片/{商品名}/{主图,颜色图,详情图}
   ```

6. **下载图片**
   - 使用 requests 下载，设置 Referer 头
   - 主图命名: `main_01.jpg`, `main_02.jpg`, ...
   - 颜色图命名: `color_01.jpg`, `color_02.jpg`, ...
   - 详情图命名: `detail_01.jpg`, `detail_02.jpg`, ...

7. **报告结果**
   - 下载成功数量
   - 每张图片的文件大小
   - 保存路径
   - 失败的图片（如有）

## 注意事项

- 淘宝/1688 需要登录才能查看部分内容
- 图片URL可能带有防盗链，需要设置 Referer
- 部分图片是懒加载，需要滚动触发
- 主图通常是 800x800 或更大的正方形图
- 详情图可能是长图，需要特别处理

## 示例对话

**用户**: 帮我下载这个商品的图片 https://detail.1688.com/offer/123456.html

**Agent**:
1. 打开浏览器访问该URL
2. 获取页面快照
3. 提取图片URL（找到5张主图，12张详情图）
4. 创建目录并下载
5. 报告: 已保存到 `~/.openclaw/sharespace/商品图片/商品名/`

**用户**: 帮我在淘宝搜"无线蓝牙耳机"下载主图

**Agent**:
1. 打开淘宝搜索页面
2. 搜索"无线蓝牙耳机"
3. 从搜索结果提取商品主图
4. 下载保存

_meta.json

{
  "ownerId": "kn784yth8y5w44jjjcbwjw58qs82sxpb",
  "slug": "1688",
  "version": "1.0.0",
  "publishedAt": 1775095629808
}

skill-card.md

## Description:

Downloads product images from Taobao and 1688 by using product URLs or product-name search to collect main and detail images.

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

## Publisher:

[gufusheng1994-dev](https://clawhub.ai/user/gufusheng1994-dev)

### License/Terms of Use:

MIT-0

## Use Case:

External users and agents use this skill to gather e-commerce product imagery from Taobao or 1688 listings, save the images locally, and report download results. It is most useful when a user provides a product URL, product name, or curated image URL list.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The helper script can fetch and save arbitrary URL contents without strong validation or scope controls.

Mitigation: Use only trusted image URL lists or product pages, avoid internal or private network URLs, and review the destination directory before running downloads.

Risk: The advertised product URL and search workflow depends on separate browser extraction and may be incomplete when the script runs by itself.

Mitigation: Confirm browser extraction has produced the intended image URLs before invoking the download helper, and review failed or missing downloads in the final report.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/gufusheng1994-dev/skills/1688)
- [Publisher profile](https://clawhub.ai/user/gufusheng1994-dev)

## Skill Output:

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

**Output Format:** [Markdown guidance with shell commands, browser-operation steps, and local file paths]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create downloaded image files and report counts, file sizes, save paths, and failures.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## 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 8h 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