WeChat Article Parser - 微信公众号文章解析
解析微信公众号文章,提取标题、作者、正文内容、图片等信息。当用户发送微信公众号链接(mp.weixin.qq.com)并希望获取文章内容、摘要或保存时触发。支持自动提取内容并可选保存到飞书表格。 Skill: WeChat Article Parser - 微信公众号文章解析 Owner: harven-droid Summary: 解析微信公众号文章,提取标题、作者、正文内容、图片等信息。当用户发送微信公众号链接(mp.weixin.qq.com)并希望获取文章内容、摘要或保存时触发。支持自动提取内容并可选保存到飞书表格。 Tags: article:1.0.0, chinese:1.0.0, latest:1.0.1, parser:1.0.0, wechat:1.0.0, weixin:1.0.0 Version history: v1.0.1 | 2026-04-02T10:10:35.631Z | user - Added metadata file _meta.json to the project. - No changes to user-facing functionality or documenta
Rank
62
Safety
84
Downloads
2.8k
Updated
Oct 9, 2026
Version
1.0.1
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 2.8K downloads reported by the source. Last updated 10/9/2026.
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 9, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 9, 2026
- Adoption signal
- 2.8K downloadsadoption · observed Oct 9, 2026
- Latest release
- 1.0.1release · observed Apr 2, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s17b95kvfzb5cdt2sy8s534dns842jax:wechat-article-parser- 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-harven-droid-wechat-article-parser/snapshot"
Documentation
CLAWHUB
16,020 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: wechat-article-parser
description: 解析微信公众号文章,提取标题、作者、正文内容、图片等信息。当用户发送微信公众号链接(mp.weixin.qq.com)并希望获取文章内容、摘要或保存时触发。支持自动提取内容并可选保存到飞书表格。
---
# 微信公众号文章解析器
解析微信公众号文章,自动提取标题、作者、发布时间、正文内容等信息。
## 功能特性
- ✅ 自动提取文章标题、作者、发布时间
- ✅ 完整正文内容提取
- ✅ 图片链接提取
- ✅ 字数统计
- ✅ 支持保存为 JSON/TXT
- ✅ 可选保存到飞书表格
## 使用方法
### 基本用法:解析文章
```bash
python3 scripts/wechat_parser.py "https://mp.weixin.qq.com/s/xxxxx"
```
**输出示例:**
```
================================================================================
📰 标题: 文章标题
✍️ 作者: 公众号名称
🕐 发布时间: 2026-03-10
📊 字数: 3500
🖼️ 图片数: 5
================================================================================
📝 正文内容:
这是文章的正文内容...
================================================================================
```
### 保存到文件
```bash
# 保存为 JSON(包含全部信息)
python3 scripts/wechat_parser.py "URL" --save
# 指定输出文件名
python3 scripts/wechat_parser.py "URL" --save --output article.json
```
### 保存到飞书表格
```bash
python3 scripts/save_to_feishu.py "https://mp.weixin.qq.com/s/xxxxx"
# 手动指定标题
python3 scripts/save_to_feishu.py "https://mp.weixin.qq.com/s/xxxxx" "自定义标题"
```
### 在 OpenClaw 对话中使用
直接发送微信公众号链接,AI 会自动调用此 skill 解析内容:
```
https://mp.weixin.qq.com/s/xxxxx
```
或带指令:
```
解析这篇文章 https://mp.weixin.qq.com/s/xxxxx
```
```
收藏 https://mp.weixin.qq.com/s/xxxxx
```
## 输出格式
### JSON 格式
```json
{
"title": "文章标题",
"author": "公众号名称",
"publish_time": "2026-03-10",
"content": "正文内容...",
"word_count": 3500,
"images_count": 5,
"images": ["url1", "url2", ...],
"url": "原始链接",
"parsed_at": "2026-03-10 12:00:00"
}
```
## 飞书保存配置
如需使用飞书保存功能,需配置 `.env` 文件:
```env
FEISHU_APP_ID=your_app_id
FEISHU_APP_SECRET=your_app_secret
FEISHU_APP_TOKEN=your_bitable_app_token
FEISHU_TABLE_ID=your_table_id
```
## 支持的链接格式
- `https://mp.weixin.qq.com/s/xxxxx`
- `https://mp.weixin.qq.com/s?__biz=xxx&mid=xxx&idx=xxx`
- 微信短链接
## 常见问题
**Q: 提取内容不完整?**
A: 微信有反爬机制,部分文章可能提取不完整。建议:
1. 使用浏览器 Cookie(高级用法)
2. 手动复制重要段落
**Q: 图片无法显示?**
A: 微信图片有防盗链机制,需要带 Referer 头访问。
## 文件结构
```
wechat-article-parser/
├── SKILL.md # 本文档
├── scripts/
│ ├── wechat_parser.py # 核心解析脚本
│ └── save_to_feishu.py # 飞书保存脚本
├── .env.example # 配置模板
└── requirements.txt # 依赖
```
## 依赖
```
requests
beautifulsoup4
python-dotenv
```
安装:
```bash
pip3 install requests beautifulsoup4 python-dotenv
```
## 许可证
MIT LicenseREADME.md
# 微信公众号文章解析器
解析微信公众号文章,自动提取标题、作者、正文内容,支持保存到飞书多维表格。
## 📦 安装
### 步骤 1:安装依赖
```bash
pip3 install requests beautifulsoup4 python-dotenv
```
或使用 requirements.txt:
```bash
pip3 install -r requirements.txt
```
### 步骤 2:验证安装
```bash
python3 scripts/wechat_parser.py
```
应该显示使用说明,表示安装成功。
## 🚀 快速开始
### 基本用法:解析文章
```bash
python3 scripts/wechat_parser.py "https://mp.weixin.qq.com/s/xxxxx"
```
无需任何配置,开箱即用!
## ⚙️ 飞书保存功能配置(可选)
如需将文章保存到飞书多维表格,需要额外配置。
### 步骤 1:创建飞书应用
1. 访问 [飞书开放平台](https://open.feishu.cn)
2. 创建企业自建应用
3. 获取 `App ID` 和 `App Secret`
### 步骤 2:开通权限
在应用的「权限管理」中开通:
- `bitable:app:readonly` - 查看多维表格
- `bitable:app` - 读写多维表格
### 步骤 3:创建多维表格
创建一个飞书多维表格,包含以下字段:
| 字段名 | 类型 | 说明 |
|--------|------|------|
| 文本 | 文本 | 文章标题 |
| 链接 | 超链接 | 文章 URL |
| 来源 | 单选 | 平台来源 |
| 保存时间 | 日期时间 | 保存时间 |
| 摘要 | 多行文本 | 摘要+正文 |
**单选「来源」的选项:**
- 微信公众号
- 知乎
- 今日头条
- 小红书
- B站
- 抖音
- 其他
### 步骤 4:获取表格信息
从表格 URL 中获取:
```
https://xxx.feishu.cn/base/APP_TOKEN?table=TABLE_ID
↑ ↑
APP_TOKEN TABLE_ID
```
### 步骤 5:配置环境变量
复制配置模板:
```bash
cp .env.example .env
```
编辑 `.env` 文件:
```env
FEISHU_APP_ID=cli_xxxxxxxxx
FEISHU_APP_SECRET=xxxxxxxxx
FEISHU_APP_TOKEN=xxxxxxxxx
FEISHU_TABLE_ID=tblxxxxxxxxx
```
### 步骤 6:验证配置
```bash
python3 scripts/save_to_feishu.py "https://mp.weixin.qq.com/s/xxxxx"
```
## 📖 使用指南
### 解析文章(无需配置)
```bash
# 基本解析
python3 scripts/wechat_parser.py "URL"
# 解析并保存到文件
python3 scripts/wechat_parser.py "URL" --save
# 指定输出文件名
python3 scripts/wechat_parser.py "URL" --save --output article.json
```
### 保存到飞书(需配置)
```bash
# 自动提取标题
python3 scripts/save_to_feishu.py "URL"
# 手动指定标题
python3 scripts/save_to_feishu.py "URL" "自定义标题"
```
## 📁 文件结构
```
wechat-article-parser/
├── README.md # 本文档(安装说明)
├── SKILL.md # Skill 描述文件
├── QUICKSTART.md # 快速开始指南
├── requirements.txt # Python 依赖
├── .env.example # 配置模板
├── .gitignore # Git 忽略文件
└── scripts/
├── wechat_parser.py # 核心解析脚本
└── save_to_feishu.py # 飞书保存脚本
```
## ❓ 常见问题
### Q1: 提取的内容不完整?
微信有反爬机制,部分文章可能提取不完整。建议:
- 多尝试几次
- 手动复制重要段落
### Q2: 飞书保存失败?
检查:
1. `.env` 配置是否正确
2. 飞书应用权限是否开通
3. 表格字段名是否匹配
### Q3: 表格字段名和脚本不一致?
修改 `scripts/save_to_feishu.py` 中的字段名映射:
```python
fields = {
"你的标题字段名": title,
"你的链接字段名": {"link": url},
...
}
```
### Q4: 如何批量处理多个链接?
创建链接列表文件 `links.txt`,每行一个 URL:
```bash
while read url; do
python3 scripts/wechat_parser.py "$url" --save
sleep 2 # 避免请求过快
done < links.txt
```
## 📄 许可证
MIT License
## 🔗 相关链接
- [飞书开放平台](https://open.feishu.cn)
- [飞书多维表格 API](https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/create)_meta.json
{
"ownerId": "kn72j0qng9f6mm49z983cyzw1982naag",
"slug": "wechat-article-parser",
"version": "1.0.1",
"publishedAt": 1775124635631
}QUICKSTART.md
# ⚡ 快速开始 30 秒上手微信文章解析器。 ## 1️⃣ 安装依赖 ```bash pip3 install requests beautifulsoup4 ``` ## 2️⃣ 解析文章 ```bash python3 scripts/wechat_parser.py "https://mp.weixin.qq.com/s/xxxxx" ``` **输出示例:** ``` ================================================================================ 📰 标题: AI 时代的一人公司 ✍️ 作者: 某某公众号 🕐 发布时间: 2026-03-10 📊 字数: 3500 🖼️ 图片数: 5 ================================================================================ 📝 正文内容: 这是文章的正文内容... ================================================================================ ``` ## 3️⃣ 保存到文件 ```bash python3 scripts/wechat_parser.py "URL" --save ``` 会生成 `文章标题.json` 文件。 --- ## 🎉 完成! 就这么简单,无需任何配置。 --- ## 📦 进阶:保存到飞书 如需保存到飞书表格,请参考 [README.md](README.md) 中的飞书配置部分。
skill-card.md
## Description: Parses WeChat public-account article URLs to extract article metadata, body text, image links, and optional Feishu table records. This skill is ready for commercial/non-commercial use. ## Publisher: [harven-droid](https://clawhub.ai/user/harven-droid) ### License/Terms of Use: MIT-0 ## Use Case: External users and developers use this skill to parse public WeChat article links into readable article text, metadata, image references, and optional saved records in Feishu Bitable. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The Feishu save path can automatically alter table schema. Mitigation: Use a dedicated test or disposable Feishu table until automatic field creation is reviewed or gated by explicit confirmation. Risk: The Feishu save path can read all records and batch-delete blank rows. Mitigation: Do not connect shared or important Feishu tables unless broad read/write access and blank-row deletion are acceptable. Risk: Article parsing depends on remote public URLs and may return incomplete content. Mitigation: Use the parser only with public article URLs you trust and review extracted content before relying on it. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/harven-droid/skills/wechat-article-parser) - [Feishu Open Platform](https://open.feishu.cn) - [Feishu Bitable create record API](https://open.feishu.cn/document/uAjLw4CM/ukTMukTMukTM/reference/bitable-v1/app-table-record/create) ## Skill Output: **Output Type(s):** [text, JSON, shell commands, configuration, guidance] **Output Format:** [Plain text or Markdown guidance with shell commands; parser output can be printed text or saved JSON.] **Output Parameters:** [1D] **Other Properties Related to Output:** [Optional Feishu saving requires FEISHU_APP_ID, FEISHU_APP_SECRET, FEISHU_APP_TOKEN, and FEISHU_TABLE_ID.] ## Skill Version(s): 1.0.1 (source: server release metadata and artifact _meta.json) ## 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.
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
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
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!
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/harven-droid/skills/wechat-article-parser",
"sourceUrl": "https://clawhub.ai/harven-droid/skills/wechat-article-parser",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T11:34:11.987Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-harven-droid-wechat-article-parser/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-harven-droid-wechat-article-parser/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-09T11:34:11.987Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "2.8K downloads",
"href": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceUrl": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-09T11:34:11.987Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.0.1",
"href": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceUrl": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-02T10:10:35.631Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-harven-droid-wechat-article-parser/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-harven-droid-wechat-article-parser/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.1",
"description": "- Added metadata file _meta.json to the project. - No changes to user-facing functionality or documentation.",
"href": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceUrl": "https://clawhub.ai/harven-droid/wechat-article-parser",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-02T10:10:35.631Z",
"isPublic": true
}
]
}Record generated Oct 9, 2026.
