WeChat Article Extractor
Extracts title, author, and content (in Markdown format) from WeChat official account articles via URL, supporting both MCP stdio and HTTP server modes.
README
微信公众号文章信息提取服务
这是一个基于Python的微信公众号文章信息提取服务,支持两种模式:
- MCP Server模式 (基于stdio通信)
- HTTP Server模式 (基于HTTP通信)
功能特性
- 提取微信公众号文章的标题
- 提取文章作者信息
- 提取文章正文内容(以Markdown格式返回)
安装依赖
pip install -r requirements.txt
本地测试
在正式使用服务之前,可以先运行简单的测试脚本验证功能:
python simple_test.py
或者使用交互式测试脚本:
python test_extractor.py
MCP协议说明
MCP(Model Context Protocol)使用JSON-RPC 2.0标准进行通信,所有请求和响应均为JSON格式。
通信示例
工具列表请求:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list",
"params": {}
}
工具调用请求:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "extract_article_info",
"arguments": {
"url": "https://mp.weixin.qq.com/s/example"
}
}
}
响应格式:
{
"jsonrpc": "2.0",
"id": 2,
"result": {
"title": "文章标题",
"author": "作者",
"content": "# Markdown格式内容..."
}
}
启动服务
MCP Server模式 (stdio通信)
python mcp_server.py
服务将通过stdio与客户端通信,需要使用支持MCP协议的客户端来调用。
HTTP Server模式 (HTTP通信)
python http_mcp_server.py
服务将在 http://localhost:5002 上运行。
API接口
提取文章信息
POST /extract
请求体:
{
"url": "微信公众号文章链接"
}
响应:
{
"title": "文章标题",
"author": "作者",
"content": "文章内容(Markdown格式)"
}
健康检查
GET /health
使用示例
HTTP模式使用示例
curl -X POST http://localhost:5002/extract \
-H "Content-Type: application/json" \
-d '{"url": "your_wechat_article_url"}'
MCP模式使用示例
MCP Server需要通过支持MCP协议的客户端来调用,例如:
- Cherry Studio
- Cursor
- Cline
- Dify
- FastGPT
- N8N等
这些客户端会自动发现并调用本服务提供的工具。
JSON配置方式
STDIO模式配置
{
"mcpServers": {
"wechat-extractor-stdio": {
"command": "python3",
"args": [
"/Users/guanshilong/app/code/lingma/mcp/mcp_server.py"
],
"env": {
"PYTHONPATH": "/Users/guanshilong/app/code/lingma/mcp"
}
}
}
}
HTTP模式配置
{
"mcpServers": {
"wechat-extractor-http": {
"type": "http",
"url": "http://localhost:5002/sse"
}
}
}
不同客户端的配置文件位置:
- Claude Desktop:
~/.claude/claude_desktop_config.json - Cursor:
.cursor/mcp.json - VS Code:
.vscode/mcp.json
常见问题排查
端口冲突问题
如果遇到类似以下错误:
ERROR: [Errno 48] error while attempting to bind on address ('0.0.0.0', 5001): address already in use
这表示指定端口已被占用,请修改 [http_mcp_server.py](file:///Users/guanshilong/app/code/lingma/mcp/http_mcp_server.py) 文件中的端口号。
服务启动检查
可以通过以下方式验证服务是否正常运行:
# 检查端口是否被监听
netstat -an | grep 5002
# 或者使用lsof命令(macOS/Linux)
lsof -i :5002
微信文章提取失败
由于微信有反爬虫机制,可能会出现提取失败的情况。如果返回的结果中字段为空,请稍后再试或者检查文章链接是否有效。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases