firecrawl / firecrawl

🔥 Firecrawl: The API to search, scrape, and interact with the web at scale. The web context API to find sources, extract content, and turn it into clean Markdown or structured data your agents can ship with. Open source and available as a hosted service. Pst. Hey, you, join our stargazers :)

🔥 Firecrawl：一个用于大规模搜索、抓取并与网络进行交互的 API。它是获取网络上下文的 API，用于查找来源、提取内容，并将其转换为干净的 Markdown 或结构化数据，供你的 AI Agent 使用。该项目开源并提供托管服务。嘿，快来加入我们的星标用户行列吧 :)

Why Firecrawl?

为什么选择 Firecrawl？

Industry-leading reliability: Covers 96% of the web, including JS-heavy pages — no proxy headaches, just clean data (see benchmarks)
Blazingly fast: P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps
LLM-ready output: Clean markdown, structured JSON, screenshots, and more — spend fewer tokens, build better AI apps
We handle the hard stuff: Rotating proxies, orchestration, rate limits, JS-blocked content, and more — zero configuration
Agent ready: Connect Firecrawl to any AI agent or MCP client with a single command
Media parsing: Parse and extract content from web-hosted PDFs, DOCX, and more
Actions: Click, scroll, write, wait, and press before extracting content
Open source: Developed transparently and collaboratively — join our community
行业领先的可靠性： 覆盖 96% 的网页，包括重度依赖 JS 的页面——无需处理代理难题，直接获取干净数据（查看基准测试）。
极速响应： 在数百万个页面中 P95 延迟仅为 3.4 秒，专为实时 Agent 和动态应用构建。
LLM 就绪的输出： 提供干净的 Markdown、结构化 JSON、截图等——节省 Token，构建更优秀的 AI 应用。
处理复杂难题： 自动处理轮换代理、编排、速率限制、JS 拦截内容等——零配置。
Agent 就绪： 通过单条命令即可将 Firecrawl 连接到任何 AI Agent 或 MCP 客户端。
媒体解析： 解析并提取托管在网页上的 PDF、DOCX 等文件内容。
操作支持： 在提取内容前执行点击、滚动、输入、等待和按键操作。
开源： 透明且协作式开发——欢迎加入我们的社区。

Feature Overview

功能概览

Core Endpoints	Feature Description
Search	Search the web and get full page content from results
Scrape	Convert any URL to markdown, HTML, screenshots, or structured JSON
Interact	Scrape a page, then interact with it using AI prompts or code

核心端点	功能描述
搜索 (Search)	搜索网络并从结果中获取完整页面内容
抓取 (Scrape)	将任何 URL 转换为 Markdown、HTML、截图或结构化 JSON
交互 (Interact)	抓取页面后，使用 AI 提示词或代码与页面进行交互

More	Feature Description
Agent	Automated data gathering, just describe what you need
Crawl	Scrape all URLs of a website with a single request
Map	Discover all URLs on a website instantly
Batch Scrape	Scrape thousands of URLs asynchronously

更多功能	功能描述
Agent	自动化数据收集，只需描述你的需求
爬取 (Crawl)	通过单次请求抓取网站的所有 URL
映射 (Map)	瞬间发现网站上的所有 URL
批量抓取 (Batch Scrape)	异步抓取数千个 URL

Quick Start

快速开始

Sign up at firecrawl.dev to get your API key. Try the playground to test it out. 请在 firecrawl.dev 注册以获取你的 API Key。你可以尝试使用 Playground 进行测试。

Search

搜索

Search the web and get full content from results. 搜索网络并从结果中获取完整内容。

from firecrawl import Firecrawl
app = Firecrawl(api_key="fc-YOUR_API_KEY")
search_result = app.search("firecrawl", limit=5)

Node.js / cURL / CLI

Node.js

import { Firecrawl } from 'firecrawl';
const app = new Firecrawl({apiKey: "fc-YOUR_API_KEY"});
app.search("firecrawl", { limit: 5 })

cURL

curl -X POST 'https://api.firecrawl.dev/v2/search' \
 -H 'Authorization: Bearer fc-YOUR_API_KEY' \
 -H 'Content-Type: application/json' \
 -d '{ "query": "firecrawl", "limit": 5 }'

CLI

firecrawl search "firecrawl" --limit 5

Output:

[
  { "url": "https://firecrawl.dev", "title": "Firecrawl", "markdown": "Turn websites into..." },
  { "url": "https://docs.firecrawl.dev", "title": "Firecrawl Docs", "markdown": "# Getting Started..." }
]

Scrape

抓取

Get LLM-ready data from any website — markdown, JSON, screenshots, and more. 从任何网站获取 LLM 就绪的数据——包括 Markdown、JSON、截图等。

from firecrawl import Firecrawl
app = Firecrawl(api_key="fc-YOUR_API_KEY")
result = app.scrape('firecrawl.dev')

Node.js

import { Firecrawl } from 'firecrawl';
const app = new Firecrawl({ apiKey: "fc-YOUR_API_KEY" });
app.scrape('firecrawl.dev')

cURL

curl -X POST 'https://api.firecrawl.dev/v2/scrape' \
 -H 'Authorization: Bearer fc-YOUR_API_KEY' \
 -H 'Content-Type: application/json' \
 -d '{ "url": "firecrawl.dev" }'

CLI

firecrawl scrape https://firecrawl.dev
firecrawl https://firecrawl.dev --only-main-content

Output:

# Firecrawl
Firecrawl helps AI agents search, scrape, and interact with the web.
## Features
- Search: Find information across the web
- Scrape: Clean data from any page
- Interact: Click, navigate, and operate pages
- Agent: Autonomous data gathering

Interact

交互

Scrape a page, then interact with it using AI prompts or code. 抓取页面，然后使用 AI 提示词或代码与页面进行交互。

from firecrawl import Firecrawl
app = Firecrawl(api_key="fc-YOUR_API_KEY")
result = app.scrape("https://amazon.com")
scrape_id = result.metadata.scrape_id
app.interact(scrape_id, prompt="Search for 'mechanical keyboard'")
app.interact(scrape_id, prompt="Click the first result")

Node.js

import { Firecrawl } from 'firecrawl';
const app = new Firecrawl({apiKey: "fc-YOUR_API_KEY"});
const result = await app.scrape("https://amazon.com");
await app.interact(result.metadata.scrapeId, { prompt: "Search for 'mechanical keyboard'" });
await app.interact(result.metadata.scrapeId, { prompt: "Click the first result" });

cURL

# 1. Scrape the page
curl -X POST 'https://api.firecrawl.dev/v2/scrape' \
 -H 'Authorization: Bearer fc-YOUR_API_KEY' \
 -H 'Content-Type: application/json' \
 -d '{"url": "https://amazon.com"}'

# 2. Interact with the page (use scrapeId from step 1)
curl -X POST 'https://api.firecrawl.dev/v2/scrape/SCRAPE_ID/interact' \
 -H 'Authorization: Bearer fc-YOUR_API_KEY' \
 -H 'Content-Type: application/json' \
 -d '{"prompt": "Search for mechanical keyboard"}'

CLI

firecrawl scrape https://amazon.com
firecrawl interact exec --prompt "Search for 'mechanical keyboard'"
firecrawl interact exec --prompt "Click the first result"

Output:

{
  "success": true,
  "output": "Keyboard available at $100",
  "liveViewUrl": "https://liveview.firecrawl.dev/..."
}

Power Your Agent

为你的 Agent 赋能

Connect Firecrawl to any AI agent or MCP client in minutes. 在几分钟内将 Firecrawl 连接到任何 AI Agent 或 MCP 客户端。

Skill Give your agent easy access to real-time web data with one command. 通过一条命令让你的 Agent 轻松访问实时网络数据。

npx -y firecrawl-cli@latest init --all --browser

Restart your agent after installing. Works with Claude Code, Antigravity, OpenCode, and more. 安装后重启你的 Agent。适用于 Claude Code、Antigravity、OpenCode 等。

MCP Connect any MCP-compatible client to the web in seconds. 在几秒钟内将任何兼容 MCP 的客户端连接到网络。

{
  "mcpServers": {
    "firecrawl-mcp": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "fc-YOUR_API_KEY"
      }
    }
  }
}

Agent Onboarding Are you an AI agent? Fetch this skill to sign up your user, get an API key, and start building with Firecrawl. 你是 AI Agent 吗？获取此技能以注册你的用户、获取 API Key 并开始使用 Firecrawl 进行构建。

curl -s https://firecrawl.dev/agent-onboarding/SKILL.md

See the Skill + CLI documentation for all available commands. For MCP, see firecrawl-mcp-server. 查看 Skill + CLI 文档以获取所有可用命令。关于 MCP，请参阅 firecrawl-mcp-server。

firecrawl / firecrawl

firecrawl / firecrawl

Why Firecrawl?

为什么选择 Firecrawl？

Feature Overview

功能概览

Quick Start

快速开始

Search

搜索

Node.js / cURL / CLI

Node.js / cURL / CLI

Scrape

抓取

Interact

交互

Power Your Agent

为你的 Agent 赋能

More Endpoints

更多端点