Skip to content
Skills Library
Marketing & content · Conversion & formats

wechat-article-browseruse

/wechat-article-browseruse

使用 BrowserUse 云浏览器 + Playwright CDP 抓取微信公众号文章,并可直接发布到飞书原生文档。

Licence
MIT
Last repository change
17.09.2026

Assessment and security

96/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability21 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
12
Scripts
6
HTML comments
0
URLs in SKILL.md
4
Deprecation

No signals detected. Repository changed on 17.09.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 6 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/fetch_wechat_article.py, scripts/publish_wechat_article_to_feishu.py, scripts/run.py, scripts/smoke-test.sh, tests/test_fetch_wechat_article.py, tests/test_publish_wechat_article_to_feishu.py

What it does and when to use it

使用 BrowserUse 云浏览器 + Playwright CDP 抓取微信公众号文章,并可直接发布到飞书原生文档。

Original author description

使用 BrowserUse 云浏览器 + Playwright CDP 抓取微信公众号文章,并可直接发布到飞书原生文档。

How it works

  1. 当前目录提供什么
  2. 前提条件
  3. 最常用用法
  4. 参数说明
  5. 输出字段
  6. 一句话总结
Original SKILL.md headings · 115 lines, 191 words
SKILL.md preview
---
name: wechat-article-browseruse
description: 使用 BrowserUse 云浏览器 + Playwright CDP 抓取微信公众号文章,并可直接发布到飞书原生文档。
version: 0.2.0
author: Hermes Agent
license: MIT
metadata:
  hermes:
    tags: [wechat, mp.weixin.qq.com, browseruse, browser-use, playwright, extraction, markdown, json]
---

# WeChat Article Extraction via BrowserUse

当你要抓取 **微信公众号文章链接**(`mp.weixin.qq.com/s/...`)并且想试一条不依赖本机 CamoFox 服务的新链路时,用这个 skill。

## 当前目录提供什么

- `scripts/run.py`:统一入口
- `scripts/fetch_wechat_article.py`:抓取并输出 Markdown / JSON
- `scripts/publish_wechat_article_to_feishu.py`:抓取并发布到飞书原生文档
- `scripts/smoke-test.sh`:基础环境检查
- `tests/`:回归测试

## 前提条件

### 1)准备 BrowserUse API key

支持两个环境变量名,任选其一:

```bash
export BROWSER_USE_API_KEY=...
# 或
export BROWSERUSE_API_KEY=...
```

### 2)安装依赖

```bash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
playwright install chromium
```

### 3)如果要发布到飞书

请先安装并登录 `lark-cli`,并确保当前用户身份具备文档导入/读取权限。

## 最常用用法

### 抓取为 Markdown

```bash
python3 scripts/run.py fetch \
  "https://mp.weixin.qq.com/s/xxxxxxxxxxxxxxxx"
```

### 抓取为 JSON

```bash
python3 scripts/run.py fetch \
  "https://mp.weixin.qq.com/s/xxxxxxxxxxxxxxxx" \
  --format json \
  --include-images
```

### 发布为飞书原生文档

```bash
python3 scripts/run.py publish-feishu \
  "https://mp.weixin.qq.com/s/xxxxxxxxxxxxxxxx"
```

### 发布到指定飞书文件夹

```bash
python3 scripts/run.py publish-feishu \
  "https://mp.weixin.qq.com/s/xxxxxxxxxxxxxxxx" \
  --folder-token <folder_token>
```

## 参数说明

### `fetch`

- `--format markdown|json`
- `--include-images`
- `--save PATH`
- `--proxy-country hk`
- `--timeout-seconds 240`
- `--wait-ms 8000`

### `publish-feishu`

- `--folder-token <token>`
- `--json`
- `--proxy-country hk`
- `--timeout-seconds 240`
- `--wait-ms 8000`

## 输出字段

JSON 输出包含:

- `url`
- `title`
- `author`
- `published_at`
- `content_markdown`
- `images`
- `source`

发布结果包含:

- `title`
- `doc_id`
- `doc_url`
- `source_url`
- `validated`
- `doc_preview`

## 一句话总结

**这套 skill 用 BrowserUse 提供远端浏览器,用 Playwright CDP 做稳定 DOM 提取,并可把结果一键发布成飞书原生文档。**
Files in this package (12)
  • .env.example 1 KB
  • .gitignore 1 KB
  • README.md 5 KB
  • SKILL.md 3 KB
  • requirements.txt 1 KB
  • assets/workflow-preview-v2.svg 4 KB
  • scripts/fetch_wechat_article.py 11 KB
  • scripts/publish_wechat_article_to_feishu.py 9 KB
  • scripts/run.py 4 KB
  • scripts/smoke-test.sh 1 KB
  • tests/test_fetch_wechat_article.py 3 KB
  • tests/test_publish_wechat_article_to_feishu.py 6 KB

Versions

The database has no other skills named wechat-article-browseruse.

Database snapshot: 13.11.2026 · package version c7b5ca006122 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95wechat-article
    生成可直接发布的微信公众号软文。当用户要求写公众号推文、软文、绩效文章(如"写本月公众号推文""写一篇XX主题的软文")时使用。覆盖账号建档、选题对齐、场景化写作、严谨性审查、文风去 AI 化、配图、标题打磨的完整七阶段流程,产出可直接排版发布的 .md 文件与配图。
  • 100wechat-article-compose
    把一个已确认的选题写成微信公众号长文。锁定复刻锚与用户价值、写出 article.md / wechat.yml / _review.md,并通过公众号通用合规检查和人工预览前自检。准备、改写或核验公众号文章时使用;不负责发布,也不产出小红书卡片。
  • 100wechat-publishing-workflow
    Use when extracting WeChat articles, rendering Markdown for official-account drafts, generating covers, or publishing Feishu/Markdown content into WeChat workflows.
  • 96wechat-article-generator
    交互式生成公众号文章。当用户需要创作公众号推文时调用,通过步骤化引导收集文章要素,生成符合公众号风格的文章。
  • 91wechat-article-maker
    智能创作并发布微信公众号文章。支持AI文章生成、链接发布、Markdown转换、图片清洗、样式处理和一键发布。当用户提到"创作公众号文章"、"发布文章链接"、"生成微信文章"、"推送到微信公众号"、"发布到微信公众号"时使用。
  • 90wechat-article
    Retrieve, inspect, summarize, or analyze a WeChat Official Account article from its original URL or indexed identifier while preserving metadata and provenance. Use when a user provides a WeChat article link, asks for full text or metadata, wants a summary or comparison, or…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.