网页提取 API · Lovely Router

读取网页

把任意公开网页读取为干净的 Markdown：标题和正文，不含导航和广告。适用于已知 URL 的单个页面。

Browser agent

Give it a goal and a start page; an AI agent drives a real browser to do it: navigate, fill forms, log in with saved secrets, ask you for codes, hand over for CAPTCHAs, wait for your approval before purchases, and return structured JSON in your schema. For tasks that need interaction; to just read a page, use Read a web page (web-fetch). $0.006 per step in fast mode, $0.012 in accurate mode (looks at screenshots when unsure, can run read-only code to read data). Each step includes 1 minute; time beyond that (e.g. waiting for your approval) costs $0.005/min. Full API: /v1/browser.

$0.006 / step详情 →

爬取整个网站并转为 Markdown

Web

爬取整个网站（或其中一部分），把每个页面转成干净、可直接给 LLM 使用的 Markdown。适合 RAG 和文档站点。

$0.01 / page + $0.01 / call详情 →

网页截图

Web

网页的整页截图（PNG 或 PDF），返回图片链接。

$0.00275 / screenshot详情 →

识别图片中的文字（OCR）

Google Lens

用 Google Lens 识别图片中的文字：全文，或带位置的段落、行和单词；可选翻译。

$0.0068 / image + $0.003 / call详情 →

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 Web extraction data tools to get data for me. They return JSON and are billed per result.

- Docs (read first): https://lovelyrouter.com/docs/tools.md and https://lovelyrouter.com/docs/tools/run.md and https://lovelyrouter.com/docs/api/tools.md
- Tools for this:
  - `web-fetch`: 读取网页 ($0.0009 / page)
  - `browser-agent`: Browser agent ($0.006 / step)
  - `website-crawl`: 爬取整个网站并转为 Markdown ($0.01 / page + $0.01 / call)
  - `website-screenshot`: 网页截图 ($0.00275 / screenshot)
  - `image-ocr`: 识别图片中的文字（OCR） ($0.0068 / image + $0.003 / call)
- Run: POST https://lovelyrouter.com/v1/tools/<id>/run with `{"input": {...}, "max_results": N}`. 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`.
- Each tool takes its own input fields: read them with GET https://lovelyrouter.com/v1/tools/<id> (public, no key needed) before the first 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.
- 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 and the output format>

用代码运行

了解运行、轮询与计费 →

curl https://lovelyrouter.com/v1/tools/web-fetch/run \
  -H "Authorization: Bearer $LOVELY_API_KEY" \
  -H "content-type: application/json" \
  -d '{"input":{"url":"https://en.wikipedia.org/wiki/Cloudflare"},"max_results":1}'

每个工具页面都列出了输入字段和示例输入。智能体可以通过 MCP 使用所有工具： MCP 服务器

常见问题

这个类别有哪些工具？

5 个工具：读取网页, Browser agent, 爬取整个网站并转为 Markdown, 网页截图, 识别图片中的文字（OCR）。每个都返回 JSON，并有独立页面列出输入字段和价格。

这是网页提取 API吗？

是的。如果你在搜索网页提取 API、网页截图 API或网站联系方式提取，这就是：读取任意网页、把网站爬取为 Markdown、截图、查找联系方式，或让浏览器智能体代为点击操作。

这些工具如何计价？

每个工具按结果单独计价，最低 $0.0009。只为交付的结果付费，从预付费余额扣除，无需订阅。

AI 智能体可以使用这些工具吗？

可以。把 Claude Code、Cursor 或任何 MCP 客户端连接到 Lovely Router 的 MCP 服务器，智能体会用 suggest_tools 选择合适的工具，并用 run_tool 运行。

数据可以随意使用吗？

你需要合法使用数据，结果包含个人数据时还需遵守隐私法规。参见可接受使用政策。

可接受使用政策 · 使用场景 · 价格