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 "Booking.com 酒店评论" (id `booking-reviews`, Booking.com) 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/booking-reviews (public, no key needed). Price: $0.00285 / review.
- Run: POST https://lovelyrouter.com/v1/tools/booking-reviews/run with a body like `{"input":{"startUrls":[{"url":"https://www.booking.com/hotel/cz/jeromehouse.en-gb.html"}],"maxReviewsPerHotel":3},"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 "booking-reviews".
- 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
startUrlsarray必填URLs of hotels to scrape reviews from. If you add any userData, it will be included in each review for the given hotel under the key `customData`
maxReviewsPerHotelintegerMaximum number of reviews to scrape per hotel
sortReviewsBystringReview attribute by which the reviews will be ordered
f_relevance · f_recent_desc · f_recent_asc · f_score_desc · f_score_asc
reviewScoresstring[]Filter reviews by their score, as shown on Booking.com
试一试
在代码中调用
了解运行、轮询与计费 →curl https://lovelyrouter.com/v1/tools/booking-reviews/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{"input":{"startUrls":[{"url":"https://www.booking.com/hotel/cz/jeromehouse.en-gb.html"}],"maxReviewsPerHotel":3},"max_results":20}'# MCP (agents): suggest_tools → get_tool → run_tool
run_tool({
"tool": "booking-reviews",
"input": {"startUrls":[{"url":"https://www.booking.com/hotel/cz/jeromehouse.en-gb.html"}],"maxReviewsPerHotel":3},
"max_results": 20
})费用示例
| 结果 | 运行次数（每次最多 500 条） | 成本 |
|---|---|---|
| 100 | 1 | $0.285 |
| 1,000 | 2 | $2.85 |
| 10,000 | 20 | $28.50 |
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
Booking.com 酒店评论 API 的价格是多少？
$0.00285 / review。以每次最多 500 条获取 1,000 条结果，费用为 $2.85。无需订阅：从预付费余额中扣除。
这是Booking 酒店评论爬虫吗？
是的。如果你在搜索Booking 酒店评论爬虫、酒店评论 API或Booking.com 评论抓取，这就是：Booking.com 酒店的住客评论：评分、好评、差评、旅客类型、日期。
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 Booking.com 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 Booking.com 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 booking-reviews 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。