films-search

Films Search Skill

Search for film and television resources (movies, TV series, anime), deeply crawl resource pages through real-time scraping, and obtain publicly shared resource links from various cloud storage platforms.

Prerequisites

• web-search skill (required, used to search and discover resource pages)

Commands

Search resources

bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "关键词" [选项]

Options:

Parameter	Description	Default value
--pan <type>	Filter cloud storage type: quark, baidu, aliyun, uc, all	all
--quality <q>	Filter quality: 4k, 1080p, 720p, 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 searches and discovers resource pages + JavaScript deep scraping extracts cloud storage links and access codes, most accurate results
• web — only extracts links from web-search engine summaries (fast, but lower accuracy, no deep scraping)

Examples:

# 搜索所有平台的资源（默认使用深度搜索）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2"

# 只搜夸克网盘 4K 资源
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --pan quark --quality 4k

# 限制结果数量
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --limit 10

# 使用浅层搜索（不深度抓取页面）
bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" search "流浪地球2" --engine web

On Windows systems, use the PowerShell script:

powershell -File "$SKILLS_ROOT/films-search/scripts/film-search.ps1" search "流浪地球2" --pan quark

Popular recommendations

bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" hot "2025年热门电影"

Essentially, it calls search with recommendation-type keywords and returns related cloud storage resources.

Resolve redirect links

bash "$SKILLS_ROOT/films-search/scripts/film-search.sh" resolve "https://example.com/goto/xxx"

When links in search results require a second redirect, use this command to resolve the real cloud storage address.

Agent usage flow

1. User says "Help me find the movie XXX" → execute search "XXX"
2. Parse the returned JSON and extract cloud storage links
3. Present them to the user grouped by cloud storage type and quality
4. If the results contain an access code (extractCode), display it to the user as well
5. If the results contain pageUrl but no direct url, use the resolve command to obtain the real address

Example dialogue:

User: Help me find Quark cloud storage resources for The Wandering Earth 2, I want 4K

Agent：

1. Execute search "流浪地球2" --pan quark --quality 4k
2. Extract matching items from the JSON results
3. Return: title + quality + Quark cloud storage link + access code (if any)

Output format

All commands output JSON, with the following structure:

{
  "success": true,
  "data": {
    "query": "流浪地球2",
    "total": 5,
    "results": [
      {
        "title": "资源标题",
        "pan": "quark",
        "url": "https://pan.quark.cn/s/xxx",
        "quality": "4K",
        "extractCode": "ab12",
        "source": "deep-search",
        "pageUrl": "https://example.com/resource/123"
      }
    ]
  }
}

Field descriptions:

• pan: cloud storage type — quark(Quark), baidu(Baidu), aliyun(Ali), uc(UC), magnet(Magnet)
• quality: detected quality — 4K, 1080P, 720P, an empty string means not detected
• source: result source — deep-search(deep scraping), web-search(search summary)
• url: cloud storage share link (directly accessible)
• extractCode: access code/password (if detected)
• pageUrl: URL of the source page of the result

Configuration

Edit films-search/.env to customize preferences:

# 偏好的网盘类型（逗号分隔，排在前面的优先展示）
FILM_SEARCH_PREFERRED_PAN=quark,aliyun,baidu,uc

# 深度搜索开关（推荐开启）
FILM_SEARCH_DEEP_ENABLED=true

# 每次搜索最多访问的结果页面数
FILM_SEARCH_DEEP_MAX_PAGES=6

# 并发抓取页面数
FILM_SEARCH_DEEP_CONCURRENCY=4

Notes

• For searches, it is recommended to useChinese titles, which works best
• Deep search (--engine deep) takes 2-3 seconds longer than shallow search, but the results are much more accurate
• Deep search requires the web-search skill to be enabled; the first search may need to wait for the browser to start
• Cloud storage share links may become invalid at any time, so it is recommended to use them as soon as possible

Disclaimer

This tool is for personal learning and research use only. It does not host, distribute, or provide any copyrighted content, and only aggregates publicly accessible links on search engines. Please comply with the laws and regulations of your region.