据 AlphaMoat 统计,截至 2026-09,Douyin DL 累计下载 1,699 次、获 0 个星标,在全部 5,078 个 AI 技能中排名第 4,642 位,在「数据分析」分类(399 个)中排名第 361 位。

累计安装

110

累计下载

1,699

星标

全站排名

#4,642

全站前 92% · 「数据分析」前 91%

平台	累计安装	累计下载	星标	评论
ClawHub ↗	38	1,373	-	-
SkillHub ↗	110	1,699	-	—

各平台的计数口径不同,统计时间不一致。

这个技能是做什么的

接收视频页、搜索结果、分享短链或笔记链接；通过无头浏览器打开页面并提取媒体源，再用 curl 下载。文档称无需登录，但媒体链接可能临时有效，提取后应尽快保存。

资料发布于 2026-10-29

可以用来做什么

下载抖音视频链接中的媒体
处理搜索页、分享或笔记链接

什么时候用

需要把页面上的抖音视频保存到本地时
已安装 agent-browser 和 curl 时

示例提示词

以下是根据技能文档生成的示例,不代表实际运行结果。

下载这个抖音分享链接中的视频并保存到指定目录

从这个搜索链接提取并下载对应视频

月度数据趋势

累计下载1,699

星标-

2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。

月份	累计下载	环比	星标
2026-09	1,699	—	-
2026-08	1,362	+9.0%	-
2026-07	1,250	—	-
2026-05	914	—	-
2026-03	493	—	-

SKILL.md 原文

以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。

2.0 KB · ClawHub v1.0.0

---
name: douyin-downloader
description: Download Douyin (抖音) short videos from URLs. Supports direct video links, search page links with modal_id, share links (v.douyin.com), and note links. Uses headless browser to bypass anti-scraping and extract video source. Use when asked to "download douyin video", "下载抖音视频", "save douyin clip", or given any douyin.com URL to download.
---

# Douyin Video Downloader

Downloads Douyin videos by opening the page in a headless browser, extracting the `<video>` source URL, and downloading via curl. This bypasses yt-dlp's cookie issues with Douyin's anti-scraping.

## Prerequisites

展开全部(共 56 行)


- `agent-browser` (`npm i -g agent-browser`)
- `curl`

## Usage

```bash
python3 scripts/douyin_download.py <URL> [--output-dir DIR] [--filename NAME]
```

## Supported URL Formats

- `https://www.douyin.com/video/<id>` — direct video page
- `https://www.douyin.com/search/...?modal_id=<id>` — search results with video modal
- `https://v.douyin.com/<code>` — share short links
- `https://www.douyin.com/note/<id>` — note/image posts with video

## Examples

```bash
# Basic download to ~/Downloads
python3 scripts/douyin_download.py 'https://www.douyin.com/video/7577715519366576522'

# Custom output directory and filename
python3 scripts/douyin_download.py 'https://www.douyin.com/video/7577715519366576522' \
  -o ~/Videos -f my_video

# From search page URL
python3 scripts/douyin_download.py 'https://www.douyin.com/search/关键词?modal_id=7577715519366576522'
```

## How It Works

1. Normalize URL → extract video ID, construct direct video page URL
2. Open page in `agent-browser` (headless Chromium)
3. Extract `<video>` element's `currentSrc` (CDN direct link)
4. Close browser
5. Download MP4 via `curl` with proper Referer header

## Notes

- No login required — fresh browser session is sufficient
- Video title auto-detected from page title for filename
- Large videos may take 30-60s to download depending on network
- CDN links are temporary (~2h validity); download promptly after extraction