wechat-article-extractor

{
  "dependencies": {
    "cheerio": "^1.2.0",
    "dayjs": "^1.11.19",
    "lodash.unescape": "^4.0.1",
    "qs": "^6.15.0",
    "request-promise": "^4.2.6"
  }
}

# WeChat Article Extractor

[![Node.js](https://img.shields.io/badge/Node.js-14+-green.svg)](https://nodejs.org/)
[![License](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

一个 Claude Code Skill，用于提取微信公众号文章的元数据和内容。支持多种文章类型，包括图文、视频、图片集、语音和转载文章。当用户需要提供微信公众号文章链接（mp.weixin.qq.com）时，Claude 会自动触发此 Skill 来提取文章信息。

## 功能特性

- 解析微信公众号文章 URL (`mp.weixin.qq.com`)
- 提取文章元数据：标题、作者、摘要、发布时间
- 获取公众号信息：名称、头像、微信号、功能介绍
- 提取文章内容（HTML 格式）
- 获取封面图片 URL
- 支持多种文章类型：图文、视频、图片集、语音、纯文字、转载
- 处理各种异常情况：内容删除、链接过期、访问限制、账号迁移等
- 支持搜狗微信搜索结果的解析 (`weixin.sogou.com`)
- 可选提取文章标签和内嵌链接

## 安装

这是一个 Claude Code Skill，可以通过以下方式安装：

### 通过 Claude Code 安装（推荐）

在 Claude Code 中运行：

```
/skill install wechat-article-extractor
```

或指定目录安装：

```
/skill install /path/to/wechat-article-extractor-skill
```

### 手动克隆安装

```bash
git clone https://github.com/yourusername/wechat-article-extractor-skill.git
cd wechat-article-extractor-skill
npm install
```

然后在 Claude Code 中将该目录作为 Skill 加载。

## 使用方法

### 基本用法 - 从 URL 提取

```javascript
const { extract } = require('./scripts/extract.js');

async function main() {
  const url = 'https://mp.weixin.qq.com/s?__biz=...&mid=...&idx=...&sn=...';
  const result = await extract(url);

 

---
name: wechat-article-extractor
description: Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos, images, voice messages, and reposts.
---

# WeChat Article Extractor

Extract metadata and content from WeChat Official Account (微信公众号) articles.

## Capabilities

- Parse WeChat article URLs (`mp.weixin.qq.com`)
- Extract article metadata: title, author, description, publish time
- Extract account info: name, avatar, alias, description
- Get article content (HTML)
- Get cover image URL
- Support multiple article types: post, video, image, voice, text, repost
- Handle various error cases: deleted content, expired links, access limits

## Usage

### Basic Extraction from URL

```javascript
const { extract } = require('./scripts/extract.js');

const result = await extract('https://mp.weixin.qq.com/s?__biz=...');
// Returns: { done: true, code: 0, data: {...} }
```

### Extraction from HTML

```javascript
const html = await fetch