← 返回 Skills 市场
95
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ecommerce-scraper-pro
功能描述
智能数据抓取工具 - 从网页/API 提取结构化数据,支持批量处理
使用说明 (SKILL.md)
Data Scraper - 智能数据抓取工具
从网页、API 自动提取结构化数据,支持批量处理和多种输出格式。
功能特性
- 🕷️ 网页数据抓取 - 自动识别并提取目标数据
- 📊 结构化输出 - JSON、CSV、Excel 格式
- 🔄 批量处理 - 支持多页面/多 URL 批量抓取
- 🛡️ 反爬规避 - 智能请求频率控制
- 🔌 API 集成 - 支持 REST/GraphQL API
- 📝 数据清洗 - 自动去重、格式化
使用方法
基础用法
# 抓取单个网页
uv run scripts/data-scraper.py scrape --url "https://example.com/products" --selector ".product"
# 抓取多个页面
uv run scripts/data-scraper.py scrape --urls-file urls.txt --output data.json
# 从 API 获取数据
uv run scripts/data-scraper.py api --endpoint "https://api.example.com/data" --auth "Bearer TOKEN"
高级选项
# 指定输出格式
uv run scripts/data-scraper.py scrape --url "https://example.com" --format csv --output products.csv
# 设置请求延迟(避免被封)
uv run scripts/data-scraper.py scrape --url "https://example.com" --delay 2
# 使用代理
uv run scripts/data-scraper.py scrape --url "https://example.com" --proxy "http://proxy:port"
# 定时抓取
uv run scripts/data-scraper.py scrape --url "https://example.com" --schedule "0 */6 * * *"
支持的数据类型
| 类型 | 描述 | 示例 |
|---|---|---|
product |
电商产品 | 价格、名称、评分、库存 |
article |
新闻/博客 | 标题、作者、日期、内容 |
job |
招聘信息 | 职位、公司、薪资、要求 |
real_estate |
房产信息 | 价格、面积、位置、户型 |
social |
社交媒体 | 帖子、评论、点赞数 |
custom |
自定义 | 通过 CSS/XPath 选择器定义 |
输出格式
JSON(默认)
{
"url": "https://example.com",
"scrapedAt": "2026-02-28T01:13:00Z",
"data": [
{
"title": "产品标题",
"price": "$99.99",
"rating": 4.5
}
]
}
CSV
title,price,rating,url
产品标题,$99.99,4.5,https://...
Excel
- 多工作表支持
- 自动格式化
- 数据透视表
定价建议
| 版本 | 功能 | 价格 |
|---|---|---|
| 基础版 | 单次抓取,100 页/月 | $49 |
| 专业版 | 批量抓取,1000 页/月,定时任务 | $149 |
| 企业版 | 无限抓取,API 访问,定制支持 | $499 |
示例
电商产品价格监控
输入:
uv run scripts/data-scraper.py scrape \
--url "https://amazon.com/s?k=wireless+headphones" \
--type product \
--fields "title,price,rating,reviews" \
--output headphones.json
输出:
{
"scrapedAt": "2026-02-28T01:13:00Z",
"count": 50,
"data": [
{
"title": "Sony WH-1000XM5",
"price": "$349.99",
"rating": 4.7,
"reviews": 12453
}
]
}
招聘信息抓取
输入:
uv run scripts/data-scraper.py scrape \
--url "https://linkedin.com/jobs/search?keywords=python+developer" \
--type job \
--fields "title,company,location,salary" \
--output jobs.csv
技术实现
- 使用 Playwright/BeautifulSoup 进行网页解析
- 支持 JavaScript 渲染页面
- 智能重试和错误处理
- 可集成到 OpenClaw 工作流
注意事项
⚠️ 合法合规使用
- 遵守目标网站 robots.txt
- 不要过度请求导致服务器压力
- 尊重数据版权和隐私
- 仅抓取公开数据
更新日志
v0.1.0 (2026-02-28)
- 初始版本发布
- 支持基础网页抓取
- 支持 JSON/CSV 输出
- 支持批量处理
待开发功能
- 图形化配置界面
- 数据可视化
- 自动字段识别
- 云存储集成
- 实时监控告警
开发者: VIC ai-company
许可: MIT
支持: 联系 main agent
安全使用建议
This skill is internally consistent with its stated purpose, but take these precautions before installing or running it: 1) Review the scripts/data-scraper.py source yourself (it is included) to confirm it matches your expectations. 2) Install dependencies from official package sources (pip) in a virtual environment. 3) Do not pass sensitive credentials to the tool unless necessary; when using --auth prefer scoped/temporary tokens. 4) Respect target sites' robots.txt, terms of service, and privacy laws — examples in the docs (Amazon, LinkedIn) may violate their terms. 5) Use rate limiting (--delay) and proxies responsibly to avoid IP blocking or causing service issues. 6) Run the tool in a sandbox or with limited filesystem/network permissions if you do not fully trust the publisher. 7) Verify what your platform's "uv run" runner does (it executes the bundled script) so you understand execution context.
功能分析
Type: OpenClaw Skill
Name: ecommerce-scraper-pro
Version: 1.0.1
The skill bundle provides a legitimate data scraping tool for extracting structured information from websites and APIs. The Python script (scripts/data-scraper.py) uses standard libraries like requests and BeautifulSoup, implements polite scraping with delays, and lacks any indicators of data exfiltration, unauthorized execution, or malicious prompt injection.
能力评估
Purpose & Capability
The name/description (web/API data scraper) match the included files and code. Required libraries (requests, beautifulsoup4) are appropriate and the code implements scraping, batch processing, and output formatting as described.
Instruction Scope
SKILL.md and README instruct the agent/user to run the local Python script (uv run / python3 scripts/data-scraper.py) and pass URLs, optional auth, proxy, delay, and output paths. The instructions do not ask the agent to read unrelated system files or secrets. Note: examples show scraping high-profile sites (Amazon, LinkedIn); users should consider legal/terms-of-service and privacy implications before using the tool on such targets.
Install Mechanism
No install spec is embedded in the skill bundle (instruction-only from platform perspective). Dependencies are listed in requirements.txt and README recommends pip install -r requirements.txt — a standard, low-risk approach. There are no downloads from untrusted URLs or archive extraction steps in the skill metadata.
Credentials
The skill requests no environment variables or credentials in metadata. The CLI accepts an --auth argument and --proxy, which is appropriate for interacting with authenticated APIs or proxies. Exercise caution about supplying sensitive credentials to any third-party tool; this skill does not appear to transmit credentials to unexpected endpoints, but it will send provided auth to target endpoints.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. It runs as a local script and writes outputs to user-specified paths only.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install ecommerce-scraper-pro - 安装完成后,直接呼叫该 Skill 的名称或使用
/ecommerce-scraper-pro触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
- Updated skill name and description to "data-scraper" with broader data extraction capabilities.
- Expanded supported features: now includes API integration, structured outputs (JSON, CSV, Excel), bulk processing, anti-blocking measures, automatic data cleaning, and scheduling options.
- Added usage instructions for web and API data scraping, output formatting, proxy support, and scheduled tasks.
- Included detailed data type and output format support, new pricing tiers, and real-world usage examples for multiple scenarios.
- Outlined technical implementation notes and compliance guidelines.
- Published initial release notes and outlined planned future features.
元数据
常见问题
E-commerce Data Scraper Pro 是什么?
智能数据抓取工具 - 从网页/API 提取结构化数据,支持批量处理. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 95 次。
如何安装 E-commerce Data Scraper Pro?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ecommerce-scraper-pro」即可一键安装,无需额外配置。
E-commerce Data Scraper Pro 是免费的吗?
是的,E-commerce Data Scraper Pro 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
E-commerce Data Scraper Pro 支持哪些平台?
E-commerce Data Scraper Pro 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 E-commerce Data Scraper Pro?
由 chungvic(@chungvic)开发并维护,当前版本 v1.0.1。
推荐 Skills