music-search

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Music Search Skill

Music Search Skill

搜索音乐资源(歌曲、专辑、无损音乐),通过实时爬虫深度抓取资源页面,从各网盘平台获取公开分享的资源链接。
Search for music resources (songs, albums, lossless music), crawl resource pages deeply through real-time crawlers, and obtain publicly shared resource links from various cloud drive platforms.

前置条件

Prerequisites

  • web-search skill(必需,用于搜索发现资源页面)
  • Python 3(必需,用于 cloudscraper 深度页面抓取。依赖首次运行时自动安装到
    .venv
  • web-search skill (required, used to search and discover resource pages)
  • Python 3 (required, used for deep page crawling with cloudscraper. Dependencies are automatically installed to
    .venv
    on first run)

命令

Commands

搜索资源

Search Resources

bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "关键词" [选项]
选项:
参数说明默认值
--pan <type>
筛选网盘类型:
quark
,
baidu
,
aliyun
,
uc
,
all
all
--format <f>
筛选音频格式:
flac
,
ape
,
wav
,
dsd
,
hires
,
mp3
,
aac
,
all
all
--limit <n>
每个平台最大结果数
5
--engine <e>
搜索引擎:
deep
,
web
deep
引擎说明:
  • deep
    (默认,推荐)— web-search 搜索发现资源页面 + cloudscraper 深度抓取提取网盘链接和提取码,结果最准确
  • web
    — 仅从 web-search 搜索引擎摘要中提取链接(速度快,但准确率较低,不做深度抓取)
示例:
bash
undefined
bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "关键词" [选项]
Options:
ParameterDescriptionDefault Value
--pan <type>
Filter cloud drive type:
quark
,
baidu
,
aliyun
,
uc
,
all
all
--format <f>
Filter audio format:
flac
,
ape
,
wav
,
dsd
,
hires
,
mp3
,
aac
,
all
all
--limit <n>
Maximum number of results per platform
5
--engine <e>
Search engine:
deep
,
web
deep
Engine Description:
  • deep
    (default, recommended) — web-search to discover resource pages + cloudscraper deep crawling to extract cloud drive links and access codes, most accurate results
  • web
    — Extract links only from web-search engine snippets (fast, but lower accuracy, no deep crawling)
Examples:
bash
undefined

搜索所有平台的音乐资源(默认使用深度搜索)

搜索所有平台的音乐资源(默认使用深度搜索)

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西"
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西"

只搜夸克网盘 FLAC 资源

只搜夸克网盘 FLAC 资源

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西" --pan quark --format flac
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "周杰伦 范特西" --pan quark --format flac

搜索 Hi-Res 高解析音乐

搜索 Hi-Res 高解析音乐

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "邓紫棋 光年之外" --format hires
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "邓紫棋 光年之外" --format hires

限制结果数量

限制结果数量

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "林俊杰 她说" --limit 10
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "林俊杰 她说" --limit 10

使用浅层搜索(不深度抓取页面)

使用浅层搜索(不深度抓取页面)

bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "陈奕迅 十年" --engine web

Windows 系统使用 PowerShell 脚本:
```powershell
powershell -File "$SKILLS_ROOT/music-search/scripts/music-search.ps1" search "周杰伦 范特西" --pan quark
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" search "陈奕迅 十年" --engine web

For Windows systems, use the PowerShell script:
```powershell
powershell -File "$SKILLS_ROOT/music-search/scripts/music-search.ps1" search "周杰伦 范特西" --pan quark

热门推荐

Hot Recommendations

bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" hot "2025年热门专辑"
本质上是以推荐类关键词调用搜索,返回相关网盘资源。
bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" hot "2025年热门专辑"
It essentially calls the search with recommendation keywords and returns relevant cloud drive resources.

解析跳转链接

Parse Redirect Links

bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" resolve "https://example.com/goto/xxx"
当搜索结果中的链接需要二次跳转时,用此命令解析出真实网盘地址。
bash
bash "$SKILLS_ROOT/music-search/scripts/music-search.sh" resolve "https://example.com/goto/xxx"
Use this command to parse the real cloud drive address when the link in the search results requires secondary redirection.

Agent 使用流程

Agent Usage Process

  1. 用户说「帮我找 XXX 的音乐」→ 执行
    search "XXX"
  2. 解析返回的 JSON,提取网盘链接
  3. 按网盘类型和音频格式分组呈现给用户
  4. 如果结果中有提取码 (
    extractCode
    ),一并展示给用户
  5. 如果结果中有
    pageUrl
    但没有直接
    url
    ,用
    resolve
    命令获取真实地址
示例对话:
用户:帮我找一下周杰伦范特西专辑的无损资源,要FLAC格式
Agent:
  1. 执行
    search "周杰伦 范特西" --format flac
  2. 从 JSON 结果中取出匹配项
  3. 返回:标题 + 格式 + 网盘链接 + 提取码(如有)
  1. User says "Help me find XXX's music" → Execute
    search "XXX"
  2. Parse the returned JSON and extract cloud drive links
  3. Group and present to users by cloud drive type and audio format
  4. If there is an access code (
    extractCode
    ) in the result, display it to the user together
  5. If there is a
    pageUrl
    but no direct
    url
    in the result, use the
    resolve
    command to get the real address
Sample Conversation:
User: Help me find the lossless resources of Jay Chou's Fantasy album, in FLAC format
Agent:
  1. Execute
    search "周杰伦 范特西" --format flac
  2. Extract matching items from JSON results
  3. Return: Title + Format + Cloud drive link + Access code (if any)

输出格式

Output Format

所有命令输出 JSON,结构如下:
json
{
  "success": true,
  "data": {
    "query": "周杰伦 范特西",
    "total": 5,
    "results": [
      {
        "title": "资源标题",
        "pan": "quark",
        "url": "https://pan.quark.cn/s/xxx",
        "format": "FLAC",
        "extractCode": "ab12",
        "source": "deep-search",
        "pageUrl": "https://example.com/resource/123"
      }
    ]
  }
}
字段说明:
  • pan
    : 网盘类型 —
    quark
    (夸克),
    baidu
    (百度),
    aliyun
    (阿里),
    uc
    (UC),
    magnet
    (磁力)
  • format
    : 检测到的音频格式 —
    FLAC
    ,
    APE
    ,
    WAV
    ,
    DSD
    ,
    Hi-Res
    ,
    AIFF
    ,
    MP3
    ,
    AAC
    ,
    OGG
    , 空字符串表示未检测到
  • source
    : 结果来源 —
    deep-search
    (深度抓取),
    web-search
    (搜索摘要)
  • url
    : 网盘分享链接(可直接访问)
  • extractCode
    : 提取码/密码(如果检测到)
  • pageUrl
    : 结果来源页面 URL
All commands output JSON with the following structure:
json
{
  "success": true,
  "data": {
    "query": "周杰伦 范特西",
    "total": 5,
    "results": [
      {
        "title": "资源标题",
        "pan": "quark",
        "url": "https://pan.quark.cn/s/xxx",
        "format": "FLAC",
        "extractCode": "ab12",
        "source": "deep-search",
        "pageUrl": "https://example.com/resource/123"
      }
    ]
  }
}
Field Description:
  • pan
    : Cloud drive type —
    quark
    (Quark),
    baidu
    (Baidu),
    aliyun
    (Alibaba),
    uc
    (UC),
    magnet
    (Magnet)
  • format
    : Detected audio format —
    FLAC
    ,
    APE
    ,
    WAV
    ,
    DSD
    ,
    Hi-Res
    ,
    AIFF
    ,
    MP3
    ,
    AAC
    ,
    OGG
    , empty string means not detected
  • source
    : Result source —
    deep-search
    (Deep crawling),
    web-search
    (Search snippet)
  • url
    : Cloud drive sharing link (directly accessible)
  • extractCode
    : Access code/password (if detected)
  • pageUrl
    : Result source page URL

配置

Configuration

编辑
music-search/.env
可自定义偏好:
bash
undefined
Edit
music-search/.env
to customize preferences:
bash
undefined

偏好的网盘类型(逗号分隔,排在前面的优先展示)

偏好的网盘类型(逗号分隔,排在前面的优先展示)

MUSIC_SEARCH_PREFERRED_PAN=quark,aliyun,baidu,uc
MUSIC_SEARCH_PREFERRED_PAN=quark,aliyun,baidu,uc

深度搜索开关(推荐开启)

深度搜索开关(推荐开启)

MUSIC_SEARCH_DEEP_ENABLED=true
MUSIC_SEARCH_DEEP_ENABLED=true

每次搜索最多访问的结果页面数

每次搜索最多访问的结果页面数

MUSIC_SEARCH_DEEP_MAX_PAGES=6
MUSIC_SEARCH_DEEP_MAX_PAGES=6

并发抓取页面数

并发抓取页面数

MUSIC_SEARCH_DEEP_CONCURRENCY=4
undefined
MUSIC_SEARCH_DEEP_CONCURRENCY=4
undefined

注意事项

Notes

  • 搜索建议使用中文歌手名+专辑名或歌曲名,效果最好
  • 深度搜索(
    --engine deep
    )比浅层搜索多 2-3 秒,但结果准确得多
  • 首次使用时会自动安装 Python cloudscraper 到
    .venv
    (需要 Python 3)
  • 深度搜索需要 web-search skill 启用,首次搜索可能需要等待浏览器启动
  • 网盘分享链接可能随时失效,建议尽快使用
  • It is recommended to use Chinese singer name + album name or song name for search, which gives the best results
  • Deep search (
    --engine deep
    ) takes 2-3 seconds more than shallow search, but the results are much more accurate
  • Python cloudscraper will be automatically installed to
    .venv
    on first use (Python 3 required)
  • Deep search requires web-search skill to be enabled, first search may need to wait for browser startup
  • Cloud drive sharing links may expire at any time, it is recommended to use them as soon as possible

免责声明

Disclaimer

本工具仅供个人学习和研究使用。不托管、不分发、不提供任何版权内容,仅聚合搜索引擎上公开可访问的链接。请遵守所在地区的法律法规。
This tool is for personal learning and research use only. It does not host, distribute, or provide any copyrighted content, only aggregates publicly accessible links on search engines. Please comply with the laws and regulations of your region.