← Back to Skills Marketplace
colorlessboy

微信读书 AI 阅读助手

by colorlessboy · GitHub ↗ · v1.1.0 · MIT-0
cross-platform ⚠ suspicious
80
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install weread-dl
Description
微信读书 AI 阅读助手 - 扫码登录、阅读进度跟踪、章节内容存档、AI 对话
README (SKILL.md)

微信读书 AI 阅读助手 (weread-dl)

通过 Playwright 实现扫码登录 → 获取阅读进度 → 从浏览器渲染 DOM 提取章节全文 → 存档和 AI 对话。

文件结构

weread-dl/
├── SKILL.md                      # 本文档
├── scripts/
│   ├── login.js                  # 扫码登录
│   └── read-chapter.js           # 打开书籍,获取章节/进度,保存到文件夹
├── profile/
│   └── weread-cookies.json       # 持久化 cookies(自动生成)
└── books/
    └── \x3C书名>/
        ├── metadata.json         # 书籍信息 + 目录 + 阅读进度 + 阅读历史
        ├── chapters/
        │   └── chapter_text.md   # 渲染后的章节全文(从 DOM 提取)
        ├── screenshots/
        │   └── YYYY-MM-DD.png    # 每次阅读的页面截图
        └── chat.md               # 聊天记录

工作原理

章节提取

微信读书网页版使用 CSS 绝对定位打散字符进行版权保护。本工具通过 Playwright 打开书籍阅读页,从渲染后的 DOM 中获取所有 position: absolute 的文本元素,按视觉坐标(top/left)排序重组,重建完整章节文本。

不涉及翻页操作,不影响用户阅读进度。

阅读进度

从页面目录元素自动提取当前章节和百分比进度,记录在 metadata.json 中。

使用

登录

cd ~/.openclaw/workspace/skills/weread-dl
NODE_PATH=/home/peng/.npm-global/lib/node_modules node scripts/login.js

生成二维码 → 微信扫一扫 → 自动保存 cookies

读一本书

NODE_PATH=/home/peng/.npm-global/lib/node_modules node scripts/read-chapter.js \x3CbookId>

可选 --chat 参数记录聊天:

node scripts/read-chapter.js \x3CbookId> --chat "讨论内容"

AI 对话功能

  1. 运行 read-chapter.js 打开指定书籍
  2. 获取当前章节(第X章,进度Y%)和相关上下文
  3. 基于目录结构和历史阅读记录与用户讨论
  4. 聊天记录自动保存到 books/\x3C书名>/chat.md

注意事项

  • ⚠️ 使用工具有封号风险,建议小号
  • 加密章节数据需配合解密端使用
Usage Guidance
Install only if you are comfortable granting the skill access to your WeRead session and saving book content, screenshots, reading history, and chats on disk. Review or patch the login.js curl/execSync code before running it, and protect or delete the saved cookie file when finished.
Capability Tags
requires-oauth-tokenrequires-sensitive-credentials
Capability Assessment
Purpose & Capability
The stated purpose is coherent with the artifacts: Playwright-based WeRead login, reading progress, chapter extraction/archive, and local chat notes. Users should notice that it deliberately extracts and stores protected book content and warns about account-ban risk.
Instruction Scope
The skill advertises Bash(node:*) usage, but the login script invokes child_process/curl internally with a page-derived URL, expanding execution beyond a simple Node workflow and creating an avoidable shell-injection risk.
Install Mechanism
There is no install spec; package.json/package-lock declare Playwright and the README gives user-directed setup commands. The login script also relies on curl even though no required binary is declared.
Credentials
Use of WeRead cookies, browser pages, bookshelf data, chapters, screenshots, and reading history is purpose-aligned, but these are sensitive account and reading-data flows.
Persistence & Privilege
The skill persists cookies and local reading archives under its own directories. No background daemon, self-propagation, or hidden exfiltration endpoint is shown.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install weread-dl
  3. After installation, invoke the skill by name or use /weread-dl
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
改用 DOM 渲染文本提取代替 API 解码,解决章节内容乱码问题;不翻页不影响阅读进度
v1.0.0
首次发布:扫码登录、章节解码、书架管理、阅读存档
Metadata
Slug weread-dl
Version 1.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is 微信读书 AI 阅读助手?

微信读书 AI 阅读助手 - 扫码登录、阅读进度跟踪、章节内容存档、AI 对话. It is an AI Agent Skill for Claude Code / OpenClaw, with 80 downloads so far.

How do I install 微信读书 AI 阅读助手?

Run "/install weread-dl" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 微信读书 AI 阅读助手 free?

Yes, 微信读书 AI 阅读助手 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 微信读书 AI 阅读助手 support?

微信读书 AI 阅读助手 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 微信读书 AI 阅读助手?

It is built and maintained by colorlessboy (@colorlessboy); the current version is v1.1.0.

💬 Comments