What makes Silas WeChat Article Search notable?

985 downloads. Trust evidence available

How should Silas WeChat Article Search be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Silas WeChat Article Search

微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Skill: Silas WeChat Article Search Owner: langhuachuanshi Summary: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。 Tags: latest:2.0.0 Version history: v2.0.0 | 2026-04-18T14:19:47.091Z | user v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底 v1.1.0 | 2026-04-18T12:40:16.086Z | user 去掉Node脚本和cheerio依赖，纯agent工具实现，零依赖 v1.0.0 | 2026-04-18T12:31:50.444Z | user Initial release: 微信公众号文章搜索，

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

985

Updated

Oct 11, 2026

Version

2.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 985 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: 985 downloadsadoption · observed Oct 11, 2026
Latest release: 2.0.0release · observed Apr 18, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 2.0.0release
v2.0: 合并parser+search双技能，Python解析全文(iPhone UA绕验证)，段落去重，零Node依赖，Serper转载兜底
Observed Apr 18, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s172yjpf05bfj3wjfrwx88v8sx83hf31:silas-wechat-article-search

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-langhuachuanshi-silas-wechat-article-search/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

10,386 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: silas_wechat_article_search
description: 微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。
metadata:
  openclaw:
    os: linux
---

# 微信公众号文章搜索与解析 v2.0

搜索微信公众号文章 → 解析全文 → 评分 → 入库知识库。

## 搜索源（按优先级）

### 源1：搜狗微信（主力，零依赖）
```bash
curl -s "https://weixin.sogou.com/weixin?type=2&query=关键词" \
  -H "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
```
用 Python 正则提取标题和链接，返回搜狗中间链接列表。

### 源2：新榜（补充）
```bash
curl -s "https://google.serper.dev/search" \
  -H "X-API-KEY: $SERPER_API_KEY" \
  -d '{"q":"site:newrank.cn 关键词","num":10}'
```

### 源3：Serper 转载兜底
当微信原文无法解析时，搜索转载版：
```bash
curl -s "https://google.serper.dev/search" \
  -H "X-API-KEY: $SERPER_API_KEY" \
  -d '{"q":"文章标题","num":5}'
```
优先选新浪/搜狐/网易等全文转载。

## 内容解析（Python 脚本）

**核心脚本**：`scripts/parse_article.py`

### 依赖
```bash
pip3 install requests beautifulsoup4
```

### 用法
```bash
python3 scripts/parse_article.py "https://mp.weixin.qq.com/s/xxxxx"
python3 scripts/parse_article.py "URL" --save
python3 scripts/parse_article.py "URL" --save --output article.json
```

### 输出 JSON
```json
{
  "title": "文章标题",
  "author": "公众号名称",
  "publish_time": "2026-04-18",
  "content": "正文全文...",
  "word_count": 5594,
  "images_count": 21,
  "images": ["url1", "url2", ...],
  "url": "原始链接",
  "parsed_at": "2026-04-18 22:00:00"
}
```

### 原理
- **iPhone UA** 绕过微信验证（关键！）
- **BeautifulSoup** 解析 `rich_media_content` 提取正文
- **段落结构保留**，过滤 <10 字的噪声
- **图片提取**：`data-src` 属性（微信防盗链图）

### 微信原文解析失败时
1. Serper 搜转载版（新浪/搜狐/网易）
2. web_fetch 抓转载全文
3. browser-search 兜底

## 入库流程

### 1. 搜索
```
选词（从 web-keywords.json）→ 搜狗搜索 → 新榜补充 → 合并去重
```

### 2. 解析
```
对每篇目标文章：
a. 先用 Python 脚本解析微信原文
b. 失败 → Serper 搜转载 → web_fetch 抓全文
c. 提取：标题、作者、正文、图片
```

### 3. 评分
```
5 维度评分（同 web-search 技能标准）：
- 数据密度 30%、实操性 25%、时效性 20%、相关性 15%、来源权威 10%
- < 5.0 不入库
- ≥ 8.5 通知管理员
```

### 4. 去重
```
a. feishu_search_doc_wiki 搜索知识库标题
b. memory/collect-log.json 查历史
c. URL + 标题去重
```

### 5. 入库
```
a. 读 wiki-directory-manager 技能匹配目录
b. feishu_create_doc 创建文档（标题不带评分）
c. 正文格式：
   > 来源：URL
   > 发布日期：YYYY-MM-DD
   > 采集日期：YYYY-MM-DD
   > 评分：X.X 🟢/🟡/🟠/🔴
   
   正文内容...
d. 有信息量图片 → 保存本地 → feishu_doc_media insert
e. 写多维表格索引（目录必须和实际一致）
```

## 图片处理

- **保存标准**：数据图表/流程图/对比截图/产品截图
- **跳过**：装饰图/广告/头像/logo
- 每篇最多 10 张，单张 <20MB
- 保存路径：`/tmp/openclaw/images/`

## 踩坑指南

- **微信验证码**：iPhone UA 可绕过，Desktop UA 会被拦截
- **搜狗中间链接**：不能直接 web_fetch，需先解析跳转或用 Python 脚本
- **微信图片防盗链**：`data-src` 是真实地址，但直接访问需要 Referer
- **频繁请求被封**：搜狗搜索间隔 3-5 秒
- **转载版内容可能有删减**：优先用微信原文，转载版做兜底
- **不要用 Node.js**：Python 脚本足够，避免 cheerio 依赖
- **save_to_feishu.py 不用**：飞书写入用 agent 原生工具（feishu_create_doc）

## 频率

Cron：每小时第22分钟（ID: de3ee2d3）
每次 1 个关键词，搜索 → 解析 → 评分 → 入库

_meta.json

{
  "ownerId": "kn78r3ca13npsxrn5f905res8n821ssm",
  "slug": "silas-wechat-article-search",
  "version": "2.0.0",
  "publishedAt": 1776521987091
}

references/example-output.json

{
  "query": "AI 一人公司 创业",
  "total": 5,
  "articles": [
    {
      "title": "AI时代一人公司怎么赚钱？",
      "url": "https://weixin.sogou.com/link?url=xxx",
      "summary": "随着AI工具的普及，越来越多的人开始尝试一人公司模式...",
      "datetime": "2026-04-15 10:30:00",
      "date_text": "2026年04月15日",
      "date_description": "3天前",
      "source": "AI创业笔记"
    }
  ]
}

skill-card.md

## Description:

微信公众号文章搜索与解析。搜狗微信+新榜双源搜索，Python脚本解析全文（零Node依赖），Serper转载兜底。

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

## Publisher:

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

### License/Terms of Use:

MIT-0

## Use Case:

Developers and content operations agents use this skill to search WeChat public-account articles, parse article text and images, score and de-duplicate results, and publish selected content to a knowledge base.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Search terms and article metadata may be sent to Sogou, Serper, and article-source sites.

Mitigation: Use the skill only where those external requests are acceptable, and review search terms before execution.

Risk: Collected content can be written persistently to Feishu knowledge-base destinations.

Mitigation: Require explicit confirmation before Feishu writes and verify the target directory before publishing.

Risk: The workflow can fetch user- or agent-selected article URLs without a stated allowlist.

Mitigation: Add URL allowlisting for approved search and article domains before unattended use.

Risk: Runtime Python dependencies are not pinned in the artifact.

Mitigation: Pin and review dependency versions before deployment.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/langhuachuanshi/skills/silas-wechat-article-search)
- [Example search output](references/example-output.json)
- [Sogou WeChat search endpoint](https://weixin.sogou.com/weixin?type=2&query=%E5%85%B3%E9%94%AE%E8%AF%8D)
- [Serper search endpoint](https://google.serper.dev/search)

## Skill Output:

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

**Output Format:** [Markdown instructions with bash examples, Python parser usage, and JSON article records.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires SERPER_API_KEY for Serper fallback; parser output can be printed or saved as JSON.]

## Skill Version(s):

2.0.0 (source: server release metadata)

## 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.

Github ReposUpdated 3d 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