An AI agent skill for automated Douyin video and audio extraction using browser automation and DASH stream merging.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install douyin-fetcher
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install douyin-fetcher using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Douyin Fetcher?
Douyin Fetcher is a technical solution designed to automate the process of downloading media from Douyin. By leveraging the framework provided by Openclaw Skills, this module handles the complex lifecycle of link resolution, video ID extraction, and resource discovery. It is specifically built to handle modern web streaming standards, including standard MP4 files and split DASH streams where audio and video must be retrieved separately.
This skill operates by simulating a real browser environment to bypass basic protections and extract direct media URLs from the browser's performance logs. It is a vital tool for developers who need to integrate Chinese short-video content into their automated pipelines, such as AI-driven transcription or sentiment analysis workflows.
Douyin Fetcher Use Cases
- Automating the collection of social media video assets for archival purposes.
- Extracting clean audio tracks for Whisper-based speech-to-text processing.
- Batch downloading high-definition tutorials for offline analysis.
- Researching content trends by programmatic access to raw media files.
How Douyin Fetcher Works
- The skill takes a short Douyin URL and resolves it to a full canonical video link via a curl request.
- It extracts the unique Video ID from the resolved URL.
- An automated browser instance is launched to navigate to the specific video page.
- After a configurable delay to allow resources to load, a JavaScript payload is executed to scrape media URLs from the performance entries.
- The system identifies if the video is a unified MP4 or separate DASH streams (media-video and media-audio).
- Direct downloads are initiated using curl with the appropriate Referer headers to prevent 403 errors.
- If DASH streams are detected, the skill optionally merges them using ffmpeg into a single high-quality video file.
Douyin Fetcher Setup
Ensure that your environment has curl and ffmpeg installed and available in your system path. You must also have a configured browser profile named 'openclaw'.
# Verify dependencies
curl --version
ffmpeg -version
The skill relies on the Openclaw Skills environment to manage browser interactions and file system access.
Douyin Fetcher Data Schema & Taxonomy
The skill organizes downloaded media in a temporary directory structure before moving them to final storage:
| File Type | Default Path | Purpose |
|---|---|---|
| Temporary Video | /temp/douyin/video.mp4 |
Primary video stream (no audio in DASH) |
| Temporary Audio | /temp/douyin/audio.mp4 |
Extracted audio stream |
| Final Output | /temp/douyin/merged.mp4 |
Combined file after ffmpeg merging |
| Knowledge Base | /knowledge/transcripts/ |
Final location for Markdown transcripts |
| Video Archive | /videos/tutorials/ |
Permanent storage for requested videos |
Douyin Fetcher Advanced Features
- Automatic DASH detection: Intelligently identifies and downloads separate audio/video streams.
- Seamless ffmpeg integration: Merges split streams with professional-grade encoding settings.
- Resource Management: Automatically stops browser instances after extraction to free up system memory.
- Whisper ASR Readiness: Optimized for directly passing extracted audio to transcription engines without full video merging.
- Custom JS Injection: Uses advanced evaluation logic to find URLs within the browser's resource timing buffer.
SKILL.md
Loading
Related Openclaw Skills
HTML to Text
A powerful utility that converts complex HTML and web pages into clean, readable text or structured JSON using the MinerU engine.
Douyin Content Analyzer
An AI-driven content analysis module that transforms raw Whisper transcriptions into structured, professional reports with key point extraction.
Douyin Orchestrator
An automated workflow engine that downloads, transcribes, and analyzes Douyin videos and notes into structured knowledge.
Ocr Pro
A high-performance OCR and document extraction tool utilizing Vision Language Models for complex layouts.
Corpus Search
A high-performance semantic search and metadata filtering tool designed for querying structured text databases and literary corpora.
Anson
Anson is a sophisticated bootstrap wizard designed to give AI assistants a rich, bespoke identity, soul, and deep user awareness.
Featured*
