ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified browser automation Safety 3/5

xianyu-data-grabber

闲鱼数据抓取技能。使用 Playwright + OCR 技术突破反爬虫，抓取闲鱼商品数据（标题、价格、想要人数等），自动上传截图和数据到 Gitee 仓库。支持批量关键词搜索、竞品分析、市场调研。

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/beipian261/xianyu-data-grabber
Or

What This Skill Does

xianyu-data-grabber is a powerful automation skill designed for market research and competitive analysis on Xianyu. By leveraging Playwright for browser automation and Tesseract OCR for data extraction, it bypasses traditional anti-scraping measures to collect granular product data including titles, pricing, and buyer interest levels. The skill automates the entire lifecycle of market intelligence: searching, capturing screenshots, extracting text, generating structured Markdown/JSON reports, and pushing the final results to a remote Gitee repository for collaborative access.

Installation

To install this skill, use the OpenClaw CLI tool: clawhub install openclaw/skills/skills/beipian261/xianyu-data-grabber

After installation, you must configure your authentication credentials in ~/.openclaw/workspace/.xianyu-grabber-config.json. Ensure you provide a valid Gitee Personal Access Token (with project read/write scope) and your session cookies to maintain the session state and successfully navigate Xianyu's authentication layers.

Use Cases

  • Competitive Benchmarking: Track the pricing strategies of top-selling accounts in specific niches to adjust your own listings.
  • Market Research: Gather massive amounts of data on trending electronics, repairs, or software services to identify supply-demand gaps.
  • Inventory Monitoring: Automatically capture the state of various goods over time to spot price fluctuations and volume changes.
  • Reporting: Generate professional, data-driven analysis reports without manual entry or data cleaning, thanks to the automated JSON-to-Markdown pipeline.

Example Prompts

  1. "帮我抓取闲鱼上'Magisk'相关的商品数据并上传到仓库。"
  2. "调研闲鱼手机维修类目的竞品，分析前20名的定价策略。"
  3. "看看闲鱼上root服务卖得怎么样，整理一份调研报告。"

Tips & Limitations

  • Cookies: Since Xianyu implements aggressive anti-scraping, ensure your cookie is fresh. If the script fails to load content, refresh your browser's session.
  • OCR Accuracy: OCR performance depends on the image resolution. The skill currently performs best with clean screenshots; avoid resizing browser windows during the capture process.
  • Rate Limiting: Do not set keyword search lists too aggressively in a single session to avoid triggering platform-side IP blocks.
Read Full Documentation on GitHub

Metadata

Author@beipian261
Stars4473
Views10
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-beipian261-xianyu-data-grabber": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags

#闲鱼#数据抓取#竞品分析#市场调研#playwright#ocr
Safety Score: 3/5

Flags: network-access, file-write, file-read, data-collection, external-api

Related Skills

DocPilot

智能文档处理专家，支持文档解析、信息抽取、文档分类

ankylala 4473

AB-Agents-Vision-MiniMax

👁️ Image analysis via MiniMax VL API. Describe images, extract text from screenshots, analyze photos. Requires MiniMax Token Plan API key (free tier available).

alexburrstudio 4473

AB-Agents-Vision

👁️ Image analysis using MiniMax VL API. Describe images, extract text from screenshots, analyze photos. Works with local files and URLs. Simple shell wrapper.

alexburrstudio 4473

DocPilot

智能文档处理专家，支持文档解析、信息抽取、文档分类

ankylala 4473

akashic-doc-analyzer

Parse, analyze, and extract content from documents (PDF, DOCX, PPTX, audio). Supports OCR, table extraction, and semantic chunking.

c7934597 4097