← Back to Skills Marketplace
terrycarter1985

Podcast Automation

by terrycarter1985 · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
60
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install podcast-automation
Description
播客自动化全流程技能——支持播客抓取、Whisper转录、Sonos播放、飞书Wiki归档。Use when you need to scrape podcast episodes, transcribe audio, play on Sonos speakers, or archive to Feishu Wiki.
README (SKILL.md)

Podcast Automation

播客自动化全流程技能,覆盖从抓取到归档的完整链路。

工作流

抓取最新播客 → 下载音频 → Whisper转录 → Sonos播放 → 飞书Wiki归档

前置依赖

  • Python 3.9+,已安装 requests, beautifulsoup4, openai-whisper, python-dotenv, pyyaml
  • FFmpeg(Whisper转录需要)
  • Sonos CLI(sonos 命令,可选)
  • 飞书应用凭证(可选,用于Wiki归档)

环境变量

变量 必填 说明
FEISHU_APP_ID Wiki归档时必填 飞书应用 App ID
FEISHU_APP_SECRET Wiki归档时必填 飞书应用 App Secret
FEISHU_WIKI_SPACE_ID Wiki归档时必填 目标Wiki空间ID
WHISPER_MODEL 否,默认 base Whisper模型名称
WHISPER_LANGUAGE 否,默认 zh 转录语言
SONOS_DEFAULT_ROOM 否,默认 客厅 Sonos播放房间

配置文件

references/podcast_scraper.yaml 复制到项目 config/ 目录,按目标站点修改选择器:

site_name: "我的播客"
base_url: "https://example.com"
list_page:
  url_pattern: "https://example.com/episodes/page/{page}/"
  item_selector: "article.episode-card"
  link_selector: "a.episode-permalink"
detail_page:
  fields:
    title:
      selector: "h1.episode-title"
      extract: "text"
      required: true
    audio_url:
      selector: "audio source"
      extract: "src"
      required: true

使用方式

完整工作流

python3 scripts/podcast_automation.py --full

单步执行

# 仅抓取
python3 scripts/podcast_automation.py --scrape

# 仅转录
python3 scripts/podcast_automation.py --transcribe

# 仅Wiki归档
python3 scripts/podcast_automation.py --sync-wiki

# 仅Sonos播放
python3 scripts/podcast_automation.py --play

作为 OpenClaw 技能调用

在对话中提及播客相关需求即可触发,例如:

  • "抓取最新一期播客"
  • "转录这期播客并归档到Wiki"
  • "在Sonos上播放最新播客"

输出

  • data/latest_episode.json — 最新一期元数据
  • data/transcript_*.txt — 转录文本
  • data/podcast_episodes.json — 历史抓取记录
  • 飞书Wiki节点 — 归档页面
Usage Guidance
Before installing, make sure you trust the code and manual dependencies, scope the Feishu app to only the intended Wiki space, and avoid running --full until you are ready for it to create a Wiki page and play audio on Sonos. Treat generated transcripts as content that will be stored locally and may be uploaded to Feishu.
Capability Analysis
Type: OpenClaw Skill Name: podcast-automation Version: 1.0.1 The podcast-automation skill performs legitimate tasks including web scraping, audio transcription using OpenAI Whisper, and data synchronization with Feishu Wiki. The Python script (podcast_automation.py) follows security best practices by using yaml.safe_load() for configuration and subprocess.run() with argument lists to prevent shell injection when calling the Sonos CLI. No evidence of data exfiltration, malicious prompt injection, or unauthorized access was found.
Capability Assessment
Purpose & Capability
Scraping, transcription, Sonos playback, and Feishu Wiki archiving are coherent with the stated purpose, but the skill includes high-impact account mutation and device-control capabilities rather than only passive podcast processing.
Instruction Scope
The full/wiki workflow directly creates and writes Feishu Wiki content, and the play workflow controls a Sonos device, with no documented preview, confirmation, or rollback step before those actions.
Install Mechanism
There is no install spec, while SKILL.md asks the user to have several unpinned Python packages plus FFmpeg and optional Sonos CLI installed manually.
Credentials
Registry metadata says no required env vars or primary credential, but the script reads Feishu app credentials and requests a Feishu token during initialization, even before checking whether Wiki sync was requested.
Persistence & Privilege
The skill stores local transcript/episode files and can write the full transcript into a Feishu Wiki space using an app token; users should ensure the app is tightly scoped.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install podcast-automation
  3. After installation, invoke the skill by name or use /podcast-automation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
支持播客抓取、转录、Sonos播放、飞书归档全流程
v1.0.0
支持播客抓取、转录、Sonos播放、飞书归档全流程
Metadata
Slug podcast-automation
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Podcast Automation?

播客自动化全流程技能——支持播客抓取、Whisper转录、Sonos播放、飞书Wiki归档。Use when you need to scrape podcast episodes, transcribe audio, play on Sonos speakers, or archive to Feishu Wiki. It is an AI Agent Skill for Claude Code / OpenClaw, with 60 downloads so far.

How do I install Podcast Automation?

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

Is Podcast Automation free?

Yes, Podcast Automation is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Podcast Automation support?

Podcast Automation is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Podcast Automation?

It is built and maintained by terrycarter1985 (@terrycarter1985); the current version is v1.0.1.

💬 Comments