交给你的 AI 智能体
把这段提示词复制到 Claude Code、Cursor、Codex 或任何编程智能体中。它会告诉智能体文档在哪里,以及如何使用你的 API 密钥。
Use the Lovely Router data tool "搜索 Naver 购物" (id `naver-shopping`, Naver) to get data for me. It returns JSON.
- Docs (read first): https://lovelyrouter.com/docs/tools/run.md and https://lovelyrouter.com/docs/api/tools.md
- Input fields and price: GET https://lovelyrouter.com/v1/tools/naver-shopping (public, no key needed). Price: $0.0057 / product + $0.0075 / call.
- Run: POST https://lovelyrouter.com/v1/tools/naver-shopping/run with a body like `{"input":{"keywords":["노트북"],"maxProductsPerKeyword":5},"max_results":10}`. A 200 has the finished run with `items`; a 202 means it is still running, so poll the `poll` path until `status` is `succeeded`, `failed`, `timed_out` or `stopped`.
- Only delivered results are billed. Keep max_results small on the first run, check the output, then scale up (up to 500 per run).
- If you support MCP, you can instead connect the server https://lovelyrouter.com/mcp (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool with tool "naver-shopping".
- Auth: read my API key from the LOVELY_API_KEY environment variable and send it as `Authorization: Bearer $LOVELY_API_KEY`. Never print or commit the key. If it is not set, ask me to create one at https://lovelyrouter.com/app/keys.
- Billing is prepaid: every call is charged to my balance, so test with a small request before running anything large.
- Every docs page is plain Markdown; the full index is https://lovelyrouter.com/llms.txt.
My task: <describe the data you need, e.g. which places, profiles, keywords or URLs, and the output format>输入
keywordsarraySearch words; Korean terms give the richest results.
productUrlsarrayScrape specific products instead of, or in addition to, searching. Paste any Naver Shopping product link (price-comparison or store page), a category link to collect that category's products, or the link of a Naver Shopping search to collect what it shows. Product ID numbers work too. Search ID from an export? Some ID numbers (for example the productId in a Naver…
sortstringREL, LOW_PRICE, HIGH_PRICE, REVIEW, RECENT or PURCHASE.
REL · LOW_PRICE · HIGH_PRICE · REVIEW · RECENT · PURCHASE
minPriceintegerIn Korean won.
maxPriceintegerIn Korean won.
brandNamestringOnly products from one brand or product line, e.g. 갤럭시북4 (Galaxy Book 4). On Naver a brand is usually narrower than a manufacturer: 삼성전자 is the manufacturer, 갤럭시북4 is the brand.
makerNamestringOnly products from one manufacturer, e.g. 삼성전자 (Samsung Electronics). Pick a suggestion or type any manufacturer name. This is the company that makes the product; for a specific product line use Brand below.
试一试
在代码中调用
了解运行、轮询与计费 →curl https://lovelyrouter.com/v1/tools/naver-shopping/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{"input":{"keywords":["노트북"],"maxProductsPerKeyword":5},"max_results":20}'# MCP (agents): suggest_tools → get_tool → run_tool
run_tool({
"tool": "naver-shopping",
"input": {"keywords":["노트북"],"maxProductsPerKeyword":5},
"max_results": 20
})费用示例
| 结果 | 运行次数(每次最多 500 条) | 成本 |
|---|---|---|
| 100 | 1 | $0.578 |
| 1,000 | 2 | $5.72 |
| 10,000 | 20 | $57.15 |
预付费,无需订阅。返回的结果少于请求数量时费用更低。 价格
适用场景
常见问题
搜索 Naver 购物 API 的价格是多少?
$0.0057 / product + $0.0075 / call。以每次最多 500 条获取 1,000 条结果,费用为 $5.72。无需订阅:从预付费余额中扣除。
一次运行返回多少条结果?
默认 20 条,每次最多 500 条。用 max_results 限制单次数量:只为实际交付的结果付费。
需要 Naver 账号或 API 密钥吗?
不需要。用你的 Lovely Router API 密钥调用工具即可获得 JSON,无需在 Naver 上做任何设置。
AI 智能体可以使用这个工具吗?
可以。把 Claude Code、Cursor 或任何 MCP 客户端连接到 Lovely Router 的 MCP 服务器:智能体用 suggest_tools 找到这个工具,再用 run_tool 和 id naver-shopping 运行它。
运行失败会怎样?
失败或被停止的运行只为已交付的结果付费,不收调用费。运行开始时会冻结最高费用,结算后释放剩余部分。