Dedao Dl logo

Dedao Dl

Community
yann0917
dedao-dl

dedao-dl 命令行工具的全量用法与排障:登录得到账号、搜索/浏览课程·听书·电子书、下载 MP3/PDF/Markdown/EPUB/读书笔记、学习圈、最近学习、多账号切换。凡用户提到 dedao-dl、"得到"下载或导出、贴出 dedao.cn 链接想下载内容、询问某条命令参数写法、或 dedao-dl 命令报错时都应触发——即使用户没有明确说"dedao-dl"这个词。

Overview

Publisheryann0917
Repositorydedao-dl
Skill namededao-dl
Stars
898
Forks
193
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yann0917 on GitHub. Read the source before you install it.

Installation

Install the Dedao Dl AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yann0917/dedao-dl/tree/main/skills/dedao-dl
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yann0917/dedao-dl.git /tmp/dedao-dl
mkdir -p .claude/skills
cp -r /tmp/dedao-dl/skills/dedao-dl .claude/skills/dedao-dl
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dedao Dl in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dedao Dl on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dedao Dl is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

dedao-dl 使用助手

dedao-dl 是得到(dedao.cn)的命令行下载器:下载已购课程(MP3/PDF/Markdown)、每天听本书(MP3/PDF/Markdown)、电子书(HTML/PDF/EPUB/读书笔记)。产物默认写在当前目录 output/ 下,缓存位于 .cache/。

前置依赖

  • PDF 导出需要 wkhtmltopdf 在 PATH 中
  • 音频处理需要 ffmpeg 可执行
  • Docker 容器内不含 wkhtmltopdf,PDF 下载不可用

核心工作流

bash
# 1) 登录(二选一)
dedao-dl login -q                 # 扫码登录
dedao-dl login -c "<cookie>"      # cookie 来自 https://www.dedao.cn

# 2) 验证登录
dedao-dl who

# 3) 浏览 / 搜索,拿到 ID
dedao-dl course                   # 已购课程
dedao-dl odob                     # 听书书架
dedao-dl ebook                    # 电子书架
dedao-dl search --query "基层中国的运行逻辑" --type 0
dedao-dl free                     # 免费专区

# 4) 下载
dedao-dl dl  <courseID|courseEnid> -t 1     # 课程
dedao-dl dlo <odobID|topic_id_str> -t 1     # 听书
dedao-dl dle <ebookID|ebookEnid>   -t 1     # 电子书

Agent 使用规则

  • 面向 agent / 脚本处理时,所有命令加全局 --json:dedao-dl --json <command> ...
  • 不确定参数时先执行 dedao-dl <command> -h 自查
  • ID 有两类,别混用:
    • 数字 ID(courseID/ebookID…):必须先拉列表建立映射——课程 course、电子书 ebook、听书 odob
    • 字符串 enid:可直接用,来自 URL 的 id 参数
  • search 结果继续操作时,enid 取 list[].list[].extra.enid,不要用 id/goods_id;再按类型分发:
    • track_name=ebook 或 goods_type=2 → dle <extra.enid>
    • track_name=storytell 或 goods_type=13 → dlo <extra.enid>
    • goods_type=66(课程类)→ dl <extra.enid>
  • URL 自动识别(用户提供 dedao.cn 链接时提取 id 参数):
    • /course/detail?id=<课程enid> → dl <课程enid>
    • /course/article?id=<文章enid> → 不能直接 dl <文章enid>(实测报 104000 服务异常:文章 enid 不是课程 enid)。需先取所属课程 enid 与文章数字 ID,再 dl <课程enid> <文章数字ID>:
      bash
      # POST /pc/bauhinia/pc/article/info   body: {"detail_id":"<文章enid>"}
      # → c.article_info.class_enid(课程 enid)、c.article_info.id(文章数字 ID)
      dedao-dl dl <class_enid> -t 1 <article_info.id>
      注意:article --articleEnID 只输出正文,不含 class_enid,无法用它反推所属课程
    • /audioBook/detail?id=<id> → dlo <id>
    • /ebook/reader?id=<id> 或 /ebook/detail?id=<id> → dle <id>
  • 下载格式 -t:
    • dl / dlo:1=mp3(默认) 2=PDF 3=markdown
    • dle:1=html(默认) 2=PDF 3=epub 4=markdown 笔记
  • dl 专属:-m 合并章节文稿、-c 下载热门留言(仅 markdown)、-o 文件名加序号前缀;dl 还可追加第 2 个位置参数只下载单篇文章:dl <课程enid> <articleID>
    • articleID 是课程文章列表里的数字 id(如 115529),不是 URL 里的 enid,也不是文章详情里的 dd_article_id 雪花值(如 1880700885751824556)。用 dedao-dl --json article -c <课程enid> 列出
    • 传错不会退化成整课程下载:过滤条件会命中 0 篇,结果为空
  • 列表分页:course/odob/ebook 的 --page 与 --limit 必须同时传;都不传则自动拉全量。--order 仅 course 支持 study|buy,odob/ebook 仅 study

命令地图

意图命令
登录/账号login -q、login -c <cookie>、who、user、users、su <uid>
搜索/浏览search -q <关键词>、cat(分类)、course、odob、ebook、free、ace(锦囊)、topic
详情course -i <id>、ebook -i <id>、article --id <courseID>、article --articleEnID <enid>、free <enid>
下载dl(课程)、dlo(听书)、dle(电子书)
笔记ebook notes -i <ebookID>、dle <id> -t 4
学习圈channel info、homepage、vip --id <channelID>
学习记录/VIPrecent、vip-ebook、vip-odob
维护clean output、clean cache、web(Web UI,默认 127.0.0.1:17878)

完整参考

注意事项

  • 排查前先复述用户目标(看列表/详情/下载/笔记/报错),再给最短可执行命令,之后才补可选参数
  • PDF 批量转换可能触发频率限制(如 496),降低并发重试
  • 部分内容需要购买或 VIP 权限,报权限类错误先确认账号资产
  • web 命令会常驻进程(默认 127.0.0.1:17878,--open=false 不自动开浏览器);在无人值守/用户无终端的环境里,用完要主动结束该进程

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dedao Dl AI skill do?

dedao-dl 命令行工具的全量用法与排障:登录得到账号、搜索/浏览课程·听书·电子书、下载 MP3/PDF/Markdown/EPUB/读书笔记、学习圈、最近学习、多账号切换。凡用户提到 dedao-dl、"得到"下载或导出、贴出 dedao.cn 链接想下载内容、询问某条命令参数写法、或 dedao-dl 命令报错时都应触发——即使用户没有明确说"dedao-dl"这个词。

Why use Dedao Dl on TypingMind?

Because you install it once and use it with any model. Dedao Dl is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dedao Dl in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yann0917/dedao-dl/tree/main/skills/dedao-dl. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dedao Dl?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dedao Dl?

As many as you like. As long as a model supports skills, you can use Dedao Dl with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dedao Dl AI skill free?

Yes. It is published on GitHub by yann0917 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇