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 "查找网站上的邮箱和联系方式" (id `website-contacts`, Web) 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/website-contacts (public, no key needed). Price: $0.015 / website + $0.0015 / call.
- Run: POST https://lovelyrouter.com/v1/tools/website-contacts/run with a body like `{"input":{"startUrls":[{"url":"https://www.cloudflare.com"}],"maxDepth":1},"max_results":1}`. 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 50 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 "website-contacts".
- 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The list of web pages from which the scraper will start crawling.You can also pass Linktree (linktr.ee) link-in-bio pages. The tool reads every link on the profile and scrapes those linked sites for contact details, even with Stay within domain enabled.
maxDepthintegerThe maximum number of links away from the Start URLs that the tool will crawl. If 0, the scraper will not follow any links. If empty or null, the scraper will follow links to an arbitrary depth.
sameDomainbooleanIf set, the scraper will only follow links within the same domain as the referring page.Links found on a Linktree (linktr.ee) page are an exception - they are always followed, even when this is enabled.
试一试
在代码中调用
了解运行、轮询与计费 →curl https://lovelyrouter.com/v1/tools/website-contacts/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{"input":{"startUrls":[{"url":"https://www.cloudflare.com"}],"maxDepth":1},"max_results":1}'# MCP (agents): suggest_tools → get_tool → run_tool
run_tool({
"tool": "website-contacts",
"input": {"startUrls":[{"url":"https://www.cloudflare.com"}],"maxDepth":1},
"max_results": 1
})费用示例
| 结果 | 运行次数（每次最多 50 条） | 成本 |
|---|---|---|
| 100 | 2 | $1.50 |
| 1,000 | 20 | $15.03 |
| 10,000 | 200 | $150.30 |
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
查找网站上的邮箱和联系方式 API 的价格是多少？
$0.015 / website + $0.0015 / call。以每次最多 50 条获取 1,000 条结果，费用为 $15.03。无需订阅：从预付费余额中扣除。
这是网站邮箱提取吗？
是的。如果你在搜索网站邮箱提取、网站邮箱抓取或网站联系方式采集，这就是：爬取网站，提取邮箱、电话号码和社交主页链接。
一次运行返回多少条结果？
默认 1 条，每次最多 50 条。用 max_results 限制单次数量：只为实际交付的结果付费。
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 website-contacts 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。