SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsaccount-video-downloader

account-video-downloader

Design & creation

View repository

Updated 10-16 05:44

About this skill

Multi-platform account homepage video extractor

Enter platform + account → Pull work list → Parse download links → One-click download to local

Introduction

A batch download tool for videos from multi-platform account homepages. Supports Douyin, Kuaishou, Bilibili, YouTube four major platforms. Just provide the platform name and account identifier, and it will automatically pull the account's recent work list, parse the direct download links for videos/images one by one, and support one-click batch download to local.

Features

Feature Description
📋 Work Pulling Get recent works from the homepage via account (title, engagement data, work link)
🔗 Link Parsing Call the parsing API one by one to obtain direct download links for videos/images
📥 Batch Download One-click download all works (videos + images) to local output/ directory
📊 Data Display Markdown table / JSON dual-format output, including complete engagement data
📄 Pagination Supports pagination to view more works
📅 Date Filtering Can filter by work publish time
🌐 Multi-platform One tool covers four major platforms: Douyin/Kuaishou/Bilibili/YouTube

Supported Platforms

--platform Platform Account Identifier Description
douyin Douyin Douyin ID e.g. Fish688688
kuaishou Kuaishou Kuaishou ID e.g. Fish688688
bilibili Bilibili Homepage link (accountUrl) e.g. https://space.bilibili.com/123456
youtube YouTube Channel URL (channel) e.g. https://www.youtube.com/@channel

API Description

This Skill calls the redfox.hk API, with two steps for each platform:

Step API Path Description
1. Pull Works POST /story/api/{platform}/... Get the work list based on the account identifier
2. Parse Download POST /story/api/parseWork/videoDownload/{platform} Get the direct download link based on the work link

Authentication

Go to Redfox Hub to get an API Key, and set it as an environment variable:

# macOS / Linux
export REDFOX_API_KEY=ak_你的密钥

# Windows PowerShell
$env:REDFOX_API_KEY="ak_你的密钥"

Usage

CLI Command Line

# 抖音：基础用法
python3 "$SKILL_PATH/scripts/main.py" --platform douyin --account "Fish688688"

# 快手：基础用法
python3 "$SKILL_PATH/scripts/main.py" --platform kuaishou --account "kwaiId"

# B站：拉取作品并解析下载链接（不下载文件）
python3 "$SKILL_PATH/scripts/main.py" --platform bilibili --account "https://space.bilibili.com/123456"

# YouTube：下载视频到本地
python3 "$SKILL_PATH/scripts/main.py" --platform youtube --account "https://www.youtube.com/@channel" --download

# YouTube：指定下载目录
python3 "$SKILL_PATH/scripts/main.py" --platform youtube --account "https://www.youtube.com/@channel" --download --output-dir ./my_videos

# 指定作品数量（默认10，最多50）
python3 "$SKILL_PATH/scripts/main.py" --platform bilibili --account "MID" --count 20 --download

# 翻页查看更多作品
python3 "$SKILL_PATH/scripts/main.py" --platform kuaishou --account "用户ID" --page 2

# 按日期范围筛选作品
python3 "$SKILL_PATH/scripts/main.py" --platform bilibili --account "MID" --date-start 2026-07-01 --date-end 2026-07-31

# 多账号（逗号分隔）
python3 "$SKILL_PATH/scripts/main.py" --platform bilibili --accounts "MID1,MID2" --download

# 组合使用：第2页 + 日期过滤 + 下载
python3 "$SKILL_PATH/scripts/main.py" --platform bilibili --account "MID" --page 2 --count 20 --date-start 2026-06-01 --download

Parameter Description

Parameter Description
--platform Target platform (required, see table above)
--account Single account identifier
--accounts Multiple account identifiers, comma-separated
--count Number of works to pull (default 10, max 50)
--page Page number (default 1)
--date-start Start date YYYY-MM-DD
--date-end End date YYYY-MM-DD
--download Download video files to local
--output-dir Download directory (default output/）
--json JSON format output
--rate-limit Request interval in seconds (default 1.0)

Dependencies

Dependency Install command
requests pip3 install requests

Account identifier requirements

Different platforms have different requirements for account identifiers,the unique identifier for each platform must be provided：

Platform Requirement URL support How to obtain
Bilibili Profile link (accountUrl) ✅ Supported Directly copy the personal space page URL
YouTube Channel URL (channel) ✅ Supported Directly copy the channel page URL
Douyin Douyin ID (uniqueName) ❌ Not supported Douyin APP → target profile → the "Douyin ID: xxx" field below the avatar
Kuaishou Account ID (kwaiId) ❌ Not supported Kuaishou APP → target profile → the ID displayed below the nickname

⚠️ Douyin and Kuaishou do not support profile links! If the user pastes a URL, you must prompt the user to provide the above unique identifier.

Important: If the user only enters an account name without providing a unique identifier, you must prompt the user to provide the accurate unique identifier.

📸 How to obtain the Douyin ID: Open the Douyin APP → go to the target user's profile → below the avatar and below the follower data, you can see the "Douyin ID: xxx" field. If the user is unsure where the Douyin ID is, you can show an illustrative screenshot (with a red box marking the "Douyin ID" location) to help the user locate it.

Agent Integration Guide

Trigger words

  • Profile video download / batch video download / account video extraction
  • Douyin download / Douyin video extraction / download Douyin works
  • Bilibili video extraction / Bilibili video download / Bilibili video download
  • YouTube channel download / YouTube video extraction
  • Help me download the profile videos of xxx

Agent execution flow

Step 1: 确认用户意图、平台与账号标识
  - 从用户输入中识别目标平台（抖音/快手/B站/YouTube）
  - 若用户未明确平台，询问：「你想下载哪个平台的视频？」
  - 确认账号标识格式正确，若用户提供的是中文昵称，提示提供唯一 ID

Step 2: 识别用户输入的时间范围（如有）
  - 若用户提到了作品时间范围，自动识别并转换为 --date-start / --date-end：
    - "7.1~7.20" → --date-start 2026-07-01 --date-end 2026-07-20
    - "7月1日到7月20日" → --date-start 2026-07-01 --date-end 2026-07-20
    - "最近一周" → 当前日期往前推 7 天
    - "上个月" → 上个月 1 日到上个月最后一天
    - "7月份的作品" → --date-start 2026-07-01 --date-end 2026-07-31
  - 日期格式固定为 YYYY-MM-DD，年份默认为当前年份
  - 若用户要求"继续"/"下一页"，添加 --page N

Step 3: 调用脚本拉取作品 + 解析下载链接
  python3 "$SKILL_PATH/scripts/main.py" --platform <platform> --account "<id>"

Step 4: 展示结果 + 询问翻页
  - 展示 Markdown 表格，含可点击的作品链接和下载链接
  - 若有失败：提示「可能是用户已删除该视频，如需数据核查可联系工作人员邮箱 redfoxdata@proton.me 处理」
  - 若可翻页：告诉用户「还有更多作品，是否需要翻看下一页？」，输入下一页翻页
  - 提示用户支持按时间范围提取作品

Step 5: 询问用户是否需要批量下载
  - 使用 AskUserQuestion：「是否需要将能下载的视频批量下载到本地？」
  - 选项：「下载到本地」/「只看链接即可」

Step 6: 用户确认后执行下载
  python3 "$SKILL_PATH/scripts/main.py" --platform <platform> --account "<id>" --download
  - 告知用户文件保存路径

Agent output specification

After parsing is complete, output in the following format (natural language style, aimed at ordinary users).

⛔ Mandatory rule: simplified output is prohibited

The Agent must display the complete table returned by the script as-is; the following actions are prohibited:

  • ❌ Do not delete or merge any columns (publish time, work, likes, comments, favorites, shares, resource download — none may be missing)
  • ❌ Do not omit the pagination prompt line
  • ❌ Do not omit the time range filter prompt ("💡 Supports entering the desired work time range to extract…")
  • ❌ Do not omit the download inquiry prompt ("💾 Do you need to batch download these X works locally?")
  • ❌ Do not use "..." or a summary to replace the complete table content
  • ✅ Must display the complete information of all works line by line (including resource download links)

Output template

## 📥 {平台}视频下载 — @账号名（粉丝: X）

当前是**第 1 页**，共 10 条作品 | 还有更多作品，输入 `--page 2` 翻看下一页

| #   | 发布时间 | 作品              | 赞   | 评论 | 收藏 | 分享 | 资源下载                                      |
| --- | -------- | ----------------- | ---- | ---- | ---- | ---- | --------------------------------------------- |
| 1   | 07-28    | [作品标题](链接)  | 5.2k | 67   | 689  | 5.8k | [🎬视频](...) · [🖼封面](...) · [🎵音频](...) |
| 2   | 07-24    | [作品标题2](链接) | 3.1k | 22   | 136  | 865  | [🖼封面](...)                                 |
| 3   | …        | …                 | …    | …    | …    | …    | …                                             |

**合计：** 10 条作品，8 条可下载，2 条下载失败

> ⚠️ 下载失败的视频可能是用户已删除该视频，如需数据核查可联系工作人员邮箱 **redfoxdata@proton.me** 处理。

> 💡 需要提取特定时间范围的作品？直接告诉我时间范围即可，如「7.1~7.20」「最近一周」

> 💾 需要将这 X 条作品批量下载到本地吗？直接告诉我即可。

The platform name will be automatically replaced according to the actual platform (Kuaishou / Bilibili / YouTube).

FAQ

Q: How do I get an API Key? A: Go to redfox.hk to register and obtain one.

Q: Do the downloaded videos have watermarks? A: No watermark. The direct video/image links returned by the API have had platform watermarks removed.

Q: Can image-text works be downloaded? A: Yes. Image-text works (slideshows, album types) will automatically download the first image, in JPG/PNG/WebP format.

Q: Why does it prompt "call frequency exceeded"? A: When the API returns code=3108, it means requests were too fast and triggered rate limiting. You can increase --rate-limit 2.0 to extend the interval.

Q: Which platforms are supported? A: Four major platforms: Douyin, Kuaishou, Bilibili, and YouTube.

Q: Where can I get the account identifier for each platform? A: Douyin requires the Douyin ID (e.g., JCLjiangchenglan), Kuaishou requires the account ID / kwaiId (below the account name), Bilibili requires the homepage link, and YouTube requires the channel URL.