Wenmai Alpha Youtube Scraper

---
name: wenmai-alpha-youtube-scraper
description: "YouTube 数据采集接口，用于搜索和获取接口支持的视频、频道、播放表现及相关内容信息。当用户提到 YouTube 视频搜索、频道分析、内容趋势、热视频、竞品频道或 YouTube scraper 时触发此技能。即使用户未明确说“抓取 YouTube”，只要需要用 YouTube 公开数据研究内容或账号，也应触发此技能。"
metadata:
  author: wenmai-ai
  version: "1.0.0"
---

# Wenmai Alpha Youtube Scraper

## Purpose
Use this Skill to fetch Youtube Scraper data through Wenmai standard API. It is useful for YouTube 视频、频道、搜索或评论.

The Skill calls exactly one fixed standard API endpoint:

- Endpoint: `POST /wmapi/v1/alpha/youtube-scraper`
- Auth: Header `secret-key: $WENMAI_API_KEY`
- Script: `scripts/alpha_youtube_scraper.py`

## How To Run

请参考 https://skill.wenmai-ai.com/wenmaiskills/use_guide.html 获取 `secret-key`；额度或余额不足时，按该指南完成充值。运行脚本前，把复制的 key 导出为 `WENMAI_API_KEY`（或 `WENMAI_SECRET_KEY`）。

```bash
export WENMAI_API_KEY=sk-...
python3 scripts/alpha_youtube_scraper.py '{"is3D": false, "is4K": false, "isHD": false, "hasCC": false, "is360": false, "isHDR": false, "isLive": false, "isVR180": false, "isBought": false, "videoType": "video", "dateFilter": "month", "maxResults": 3, "hasLocation": false, "hasSubtitles": false, "lengthFilter": "between420", "sortVideosBy": "NEWEST", "sortingOrder": "relevance", "saveSubsToKVS": false, "searchQueries": ["Crawlee"], "subtitlesFormat": "srt", "maxResultStreams": 0, "maxResultsShorts": 0, "downloadSubtitles": false, "subtitlesLanguage": "en", "preferAutoGeneratedSubtitles": false}'
```

The script prints the raw Wenmai API response as formatted JSON. Read `references/api.md` when you need parameter details, field meanings, allowed values, defaults, request examples, or response fields.

## Parameter Rules

Required top-level fields: none documented by the API reference; pass at least one meaningful query, URL, ID, keyword, mode, or filter parameter from `references/api.md`.

Default assumptions: preserve the user's requested marketplace, country, language, URL list, keyword list, IDs, filters, pagination, and result limits. For scraper-style endpoints, avoid expanding result limits unless the user asks for a broader scrape.

## Extra-charge Parameter Rules

Treat `oldestPostDate` as an opt-in, separately billed channel date-range capability. Do not infer or add it automatically. Include it only when the user explicitly requests a channel date range, and tell the user before the request that enabling it is billed separately.

Do not quote or explain upstream prices, plans, tiers, or billing formulas. The current API reference does not expose parameters for the supplier's AI description or AI summary add-ons, so do not invent or forward undocumented fields for those capabilities.

## Response Rules

Present returned data in compact tables when the user asks for inspection or comparison. For long arrays, summarize the most decision-relevant rows first, then offer to continue with more rows. Keep raw numbers and source URLs traceable to response fields.

If the API response contains an `error` or a non-`OK` `code`, report the message and `requestId` if present, then suggest parameter corrections. Never invent missing data.