Xpersona
agentCLAWHUBUnverified

微信公众号文章读取器

抓取微信公众号文章、搜索公众号、文章列表、爆款查询与分析。触发场景：mp.weixin.qq.com 链接、微信公众号文章、公众号文章分析。 Skill: 微信公众号文章读取器 Owner: one2agi Summary: 抓取微信公众号文章、搜索公众号、文章列表、爆款查询与分析。触发场景：mp.weixin.qq.com 链接、微信公众号文章、公众号文章分析。 Tags: latest:1.0.3 Version history: v1.0.3 | 2026-08-13T13:12:14.674Z | user 新增搜狗关键词全文搜索功能 sogou_keyword_fulltext.py v1.0.2 | 2026-07-01T16:38:15.552Z | user 修复 stats 无声失败：当 trends 无匹配时显示尝试过的关键词和建议 v1.0.1 | 2026-07-01T16:28:54.034Z | user SKILL.md 重构降级链路表格：分3层/2层/单路径三类展示，更清晰地反映各命令实际可用路径数 v1.0.0 | 2026-07-0

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

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 11, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 11, 2026
Adoption signal
1.1K downloadsadoption · observed Oct 11, 2026
Latest release
1.0.3release · observed Aug 13, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17af6d0s919355pqydwf8trph842fmk:wechat-article-grab
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. 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-one2agi-wechat-article-grab/snapshot"

Documentation

CLAWHUB

65,598 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: wechat-article-reader
description: "抓取微信公众号文章、搜索公众号、文章列表、爆款查询与分析。触发场景：mp.weixin.qq.com 链接、微信公众号文章、公众号文章分析。"
metadata:
  allowed-tools: ["exec", "read", "write", "edit"]
---

# 微信公众号文章读取器

## 入口
```bash
cd ~/.openclaw/agents/xingchen/workspace/skills/wechat-article-reader
python3 scripts/gzh_article.py <command> [args]
```

## 环境变量配置

详见 `env-guide.md`（MPTEXT_API_KEY 和 Cookie 的获取与配置说明）。

## 命令（12个）

### 常用命令
| 命令 | 说明 |
|------|------|
| `fetch "<url>"` | 抓取单篇文章全文（标题+正文），curl 优先，不需要公众号名 |
| `full "公众号名" [数量]` | 列出某公众号文章+每篇预览前800字，不含阅读量 |
| `list "公众号名" [数量]` | 列出文章标题+摘要digest，不含正文 |
| `mpsearch "<关键字>"` | 按名称搜索公众号，返回名称和fakeid |
| `stats "<url>"` | 拿文章标题搜 trends API，返回相似爆款文章的互动数据（新文章可能无结果） |
| `trends "<关键词>"` | 查某关键词下的爆款文章列表，含阅读/点赞/评论数据 |
| `compare --accounts "名1,名2" [--count N]` | 对比多个公众号的文章列表 |
| `compare --urls "url1,url2"` | 对比多个链接对应的公众号文章列表 |
| `compare "<关键词>"` | 按关键词查爆款文章（不是对比，是搜索） |
| `resolve "<标题>"` | 根据标题搜索并匹配文章链接 |

### 专用命令
| 命令 | 说明 |
|------|------|
| `mparticles "<fakeid>" [数量]` | 从 fakeid 查文章列表 |
| `mparticles_by_url "<url>" [数量]` | 从 URL 提取 biz 再查文章列表（URL 需含 `__biz`） |
| `mpinfo "<fakeid>"` | 查公众号主体信息（公司名、是否认证、原创文章数） |
| `mpdownload "<url>" [格式]` | 下载文章正文（mptext 方式，不含标题） |

## 自动降级链路

### 3 层路径
| 命令 | P1 | P2 | P3 |
|------|----|----|-----|
| fetch | curl（免费） | mptext | Cookie |
| compare --urls | biz→mptext | 正文识别账号名→mptext | Cookie |
| mparticles_by_url | biz→mptext | 正文识别账号名→mptext | Cookie |

### 2 层路径
| 命令 | P1 | P2 |
|------|----|----|
| list | mptext | Cookie |
| full | mptext | Cookie |
| compare --accounts | mptext | Cookie |
| resolve | mptext | Cookie |
| mpsearch | mptext | Cookie |
| mparticles | mptext | Cookie |
| mpdownload | mptext | curl |

### 单路径
| 命令 | 唯一路径 |
|------|----------|
| stats | trends API |
| trends | trends API |
| mpinfo | mptext |

## 已知局限
- **fetch 内容截断**：JS验证拦截的文章只能拿 ~800 字，换 P2 可能完整
- **mparticles_by_url**：URL 不含 `__biz` 时走正文识别公众号名路径，无需 biz
- **stats**：仅对爆款文章有效，新文章无结果时提示"所有关键词查询均失败"
- **历史列表不全**：原生 API 最多约 436 篇

详细说明见 `references/priority.md`

_meta.json

{
  "ownerId": "kn70ps8raw9bhs1czcvkg53z31842jqm",
  "slug": "wechat-article-grab",
  "version": "1.0.3",
  "publishedAt": 1786626734674
}

references/priority.md

# 微信公众号文章读取器 - 优先级与降级

## fetch 抓取正文

| 优先级 | 方法 | 依赖 | 成功率 |
|--------|------|------|--------|
| P1 | curl 多 UA（免费） | 无 | ~80% |
| P2 | mptext API（开源项目，需 API key） | API key | ~70% |
| P3 | requests + Cookie | Cookie | ~60% |

- P1 优先，不需要 Cookie，一次网络请求拿到标题+正文
- P2 为 mptext 开源项目，内容完整但不带标题（需 curl 补标题）
- P3 是最后兜底，需要 Cookie

### 局限性
- **内容被截断**：部分文章（含 JS 验证）只能拿到开头 ~800 字，换 P2 可能拿到完整版

---

## list 公众号文章列表

| 优先级 | 方法 | 依赖 | 成功率 |
|--------|------|------|--------|
| P1 | mptext API（开源项目，需 API key） | API key | ~80% |
| P2 | 原生 API | Cookie | ~90% |

### 局限性
- **历史文章不全**：原生 API 最多约 436 篇，更早历史无法翻到

---

## full 列表 + 每篇摘要

同 list 优先级，先 P1 mptext，失败则 P2 Cookie。

---

## compare / resolve / mpsearch / mparticles / mparticles_by_url

同 list，先 mptext API，失败则 Cookie。

### 局限性
- **resolve**：标题过于泛化可能导致匹配失败



## stats

| 优先级 | 方法 | 依赖 | 成功率 |
|--------|------|------|--------|
| P1 | trends API | 无 | ~60% |

### 局限性
- 仅对爆款文章有效，新文章直接用 fetch 分析正文

---

## Cookie 失效表现

- token 获取返回 ret≠0
- 搜索返回空列表
- 修复见 `../env-guide.md`

## 浏览器兜底

所有 API 失效时：mavis-browser 截图 + 图像理解

env-guide.md

# 环境变量配置说明

配置文件：`scripts/skill.env`，每行格式 `KEY=VALUE`，无需引号。

---

## MPTEXT_API_KEY（mptext API 密钥）

### 获取地址
```
https://wechat.faiz-world.com/dashboard/api
```
注册后可在 API 页面生成密钥，有效期 4 天（会话级）。

> ⚠️ 注意：部分第三方镜像站（如 down.mptext.top）可能使用不同的 key 体系，请从 API 所属域名获取。

### 配置方式
```
MPTEXT_API_KEY=你的密钥
```

### 用途
mptext API 的所有接口均需此 key：
- `search_account` — 搜索公众号
- `get_articles` — 获取文章列表
- `download_article` — 下载文章正文
- `get_author_info` — 查询公众号主体信息

---

## Cookie（微信公众平台 Cookie）

> Cookie 方案为备用方案，大部分场景用 mptext API 即可覆盖。

### 获取方式（推荐：Cookie-Editor 插件）

1. 安装浏览器插件 **Cookie-Editor**（Chrome/Edge 扩展商店有）
2. 登录微信公众平台 `https://mp.weixin.qq.com/`
3. 点击 Cookie-Editor 插件图标 → **Export** → 导出为 JSON
4. 将 JSON 内容发给 agent，说明写入 `scripts/skill.env`

> agent 会将 JSON 转为 `cookie=***` 格式写入配置文件。

### 配置方式

```
cookie=你的cookie值
token=你的token值
```

### 用途
- 公众号文章列表（原生 API）
- 按 biz 查询公众号信息
- 获取文章互动数据（阅读/点赞/评论）

### Cookie 失效表现
- token 获取返回 ret≠0
- 搜索返回空列表
- 修复：重新登录微信公众平台，重新获取 Cookie

skill-card.md

## Description:

抓取微信公众号文章、搜索公众号、文章列表、爆款查询与分析。触发场景：mp.weixin.qq.com 链接、微信公众号文章、公众号文章分析。

This skill is ready for commercial/non-commercial use.

## Publisher:

[one2agi](https://clawhub.ai/user/one2agi)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers can use this skill to fetch WeChat Official Account article text, search accounts and article lists, compare accounts or URLs, and inspect trending article metrics.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill may require sensitive WeChat session cookies for fallback paths.

Mitigation: Prefer the mptext API path with a fresh, low-privilege, short-lived API key; avoid pasting full browser cookie exports into an agent or storing them in the skill directory unless the session exposure is acceptable.

Risk: A packaged API key is present in the artifact configuration file.

Mitigation: Remove the packaged key before use and replace it with a user-controlled short-lived key.

Risk: Unsafe network handling could expose credentials or reach unintended hosts.

Mitigation: Restrict fetches to trusted WeChat-related hosts and avoid the trends path until TLS verification is fixed.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/one2agi/skills/wechat-article-grab)
- [Environment guide](env-guide.md)
- [Priority and fallback reference](references/priority.md)
- [mptext API dashboard](https://wechat.faiz-world.com/dashboard/api)
- [WeChat Official Accounts Platform](https://mp.weixin.qq.com/)
- [Sogou WeChat search](https://weixin.sogou.com/)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Plain text or Markdown command output, with article content, account metadata, article lists, comparisons, and trend summaries.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May use API keys or WeChat cookies and may return partial article text when upstream anti-crawling or validation limits extraction.]

## Skill Version(s):

1.0.3 (source: server release evidence)

## 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.

Related agents

Same protocol, similar job.

Github ReposUpdated 2d agoRank 70

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!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

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

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

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/one2agi/skills/wechat-article-grab",
      "sourceUrl": "https://clawhub.ai/one2agi/skills/wechat-article-grab",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:40:04.672Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-one2agi-wechat-article-grab/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-one2agi-wechat-article-grab/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:40:04.672Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.1K downloads",
      "href": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceUrl": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T09:40:04.672Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.3",
      "href": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceUrl": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-13T13:12:14.674Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-one2agi-wechat-article-grab/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-one2agi-wechat-article-grab/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.3",
      "description": "新增搜狗关键词全文搜索功能 sogou_keyword_fulltext.py",
      "href": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceUrl": "https://clawhub.ai/one2agi/wechat-article-grab",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-13T13:12:14.674Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 11, 2026.

Sponsored

Ads related to 微信公众号文章读取器 and adjacent AI workflows.