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 "企业官网招聘职位" (id `career-site-jobs`, Career sites) 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/career-site-jobs (public, no key needed). Price: $0.018 / job.
- Run: POST https://lovelyrouter.com/v1/tools/career-site-jobs/run with a body like `{"input":{"titleSearch":["data engineer"],"locationSearch":["United States"],"limit":10},"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 100 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 "career-site-jobs".
- 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
titleSearcharrayArray of job titles to search for. Use :* for prefix matching (e.g., 'Soft:*' will match 'Software', 'Softball', etc.)
locationSearcharrayArray of locations to search for. Location search uses phrase matching, so you must use the exact 'City, State/Region, Country' format. All locations use English names (e.g., 'Munich' not 'München', 'Bavaria' not 'Bayern'). For the UK, use the constituent country as the state (e.g., 'London, England, United Kingdom', 'Edinburgh, Scotland, United Kingdom'). For the US, use the full state name…
organizationSearcharrayArray of organization names to search for. Use :* for prefix matching (e.g., 'Google:*' will match 'Google', 'Google Cloud', etc.) Getting several companies with the same name? Use the liOrganizationSlugFilter to filter by LinkedIn organization slugs.
descriptionSearcharrayWarning, this search might be too intenstive for the 6m backfill API. Please be very specific, limit your searches to a handful of keywords, and combine with one of the other searches, preferably titleSearch. Array of terms to search in job title & description. Use :* for prefix matching (e.g., 'Python:*' will match 'Python', 'Pythonic', etc.)
timeRangestringSelect the time range for job listings. You can choose between hourly (1h), daily (24h), weekly (7d), or backfill of all active jobs (great to get started, 6m). We strongly recommend running the tool at the same time every hour/day/week to ensure that you get all jobs withou duplicates
1h · 24h · 7d · 6m
试一试
在代码中调用
了解运行、轮询与计费 →curl https://lovelyrouter.com/v1/tools/career-site-jobs/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{"input":{"titleSearch":["data engineer"],"locationSearch":["United States"],"limit":10},"max_results":10}'# MCP (agents): suggest_tools → get_tool → run_tool
run_tool({
"tool": "career-site-jobs",
"input": {"titleSearch":["data engineer"],"locationSearch":["United States"],"limit":10},
"max_results": 10
})费用示例
| 结果 | 运行次数（每次最多 100 条） | 成本 |
|---|---|---|
| 100 | 1 | $1.80 |
| 1,000 | 10 | $18.00 |
| 10,000 | 100 | $180.00 |
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
企业官网招聘职位 API 的价格是多少？
$0.018 / job。以每次最多 100 条获取 1,000 条结果，费用为 $18.00。无需订阅：从预付费余额中扣除。
这是企业招聘官网爬虫吗？
是的。如果你在搜索企业招聘官网爬虫、职位数据 API或ATS 职位抓取，这就是：直接来自企业招聘官网和 ATS（Greenhouse、Lever、Workday 等）的最新职位，可按职位、地点和公司搜索。
一次运行返回多少条结果？
默认 10 条，每次最多 100 条。用 max_results 限制单次数量：只为实际交付的结果付费。
需要 Career sites 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 Career sites 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 career-site-jobs 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。