Quickstart | Firecrawl

欢迎来到 Firecrawl

Firecrawl 是一个 API 服务，它接受一个 URL，进行爬取，并将其转换为干净的 Markdown。我们会爬取所有可访问的子页面，并为您提供每个页面的干净 Markdown。不需要站点地图。

如何使用？

我们提供了易于使用的 API，通过托管版本提供。您可以在这里找到游乐场和文档。如果您愿意，也可以自行托管后端。请查看以下资源以开始使用：

API: 文档
SDKs: Python, Node, Go, Rust
LLM 框架: Langchain (python), Langchain (js), Llama Index, Crew.ai, Composio, PraisonAI, Superinterface, Vectorize
低代码框架: Dify, Langflow, Flowise AI, Cargo, Pipedream
其他: Zapier, Pabbly Connect
需要 SDK 或集成吗？通过打开一个 issue 告诉我们。

自托管: 要进行自托管，请参考指南这里。

API 密钥

要使用 API，您需要在 Firecrawl 上注册并获取一个 API 密钥。

爬取

用于爬取一个 URL 及其所有可访问的子页面。这会提交一个爬取任务并返回一个任务 ID，用于检查爬取状态。

安装

pip install firecrawl-py

npm install @mendable/firecrawl-js

go get github.com/mendableai/firecrawl-go

# add the following to your Cargo.toml

[dependencies]
firecrawl = "^0.1"
tokio = { version = "^1", features = ["full"] }
serde = { version = "^1.0", features = ["derive"] }
serde_json = "^1.0"
uuid = { version = "^1.10", features = ["v4"] }

[build-dependencies]
tokio = { version = "1", features = ["full"] }

使用

from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key="YOUR_API_KEY")

crawl_result = app.crawl_url('docs.firecrawl.dev', {'crawlerOptions': {'excludes': ['blog/*']}})

# Get the markdown
for result in crawl_result:
    print(result['markdown'])

import FirecrawlApp from '@mendable/firecrawl-js';

// Initialize the FirecrawlApp with your API key
const app = new FirecrawlApp({ apiKey: 'YOUR_API_KEY' });

// Crawl a website
const crawlResult = await app.crawlUrl('docs.firecrawl.dev', {
  crawlerOptions: { excludes: ['blog/*'] },
});

// Log the markdown
console.log(crawlResult.map(result => result.markdown));

import (
  "fmt"
  "log"

  "github.com/mendableai/firecrawl-go"
)

func main() {
  // Initialize the FirecrawlApp with your API key
  app, err := firecrawl.NewFirecrawlApp("YOUR_API_KEY")
  if err != nil {
    log.Fatalf("Failed to initialize FirecrawlApp: %v", err)
  }

  // Crawl a website
  params := map[string]any{
    "crawlerOptions": map[string]any{
      "excludes": []string{"blog/*"},
    },
  }
  crawlResult, err := app.CrawlURL("docs.firecrawl.dev", params)
  if err != nil {
    log.Fatalf("Error occurred while crawling: %v", err)
  }

  // Get the markdown
  for _, result := range crawlResult {
    fmt.Println(result.Markdown)
  }
}

use firecrawl::FirecrawlApp;

#[tokio::main]
async fn main() {
  // Initialize the FirecrawlApp with the API key
  let api_key = "YOUR_API_KEY";
  let api_url = "https://api.firecrawl.dev";
  let app = FirecrawlApp::new(api_key, api_url).expect("Failed to initialize FirecrawlApp");

  // Crawl the URL
  let crawl_params = json!({
    "crawlerOptions": {
        "excludes": ["blog/*"]
    }
  });

  let crawl_result = app
      .crawl_url("https://example.com", Some(crawl_params), true, 2, None)
      .await;

  // Print the crawl result
  match crawl_result {
      Ok(data) => println!("Crawl Result:
{}", data),
      Err(e) => eprintln!("Crawl failed: {}", e),
  }
}

curl -X POST https://api.firecrawl.dev/v0/crawl \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://docs.firecrawl.dev"
    }'

如果你不使用 SDK 或更喜欢使用 Webhook 或其他轮询方法，可以将 wait_until_done 设置为 false。这会返回一个 jobId。对于 cURL，/crawl 始终会返回一个 jobId，你可以用它来检查抓取的状态。

{ "jobId": "1234-5678-9101" }

检查抓取作业

用于检查抓取作业的状态并获取其结果。

status = app.check_crawl_status(job_id)

const status = await app.checkCrawlStatus(jobId);

status, err := app.CheckCrawlStatus(jobId)
if err != nil {
  log.Fatalf("Failed to check crawl status: %v", err)
}

let status = match app.check_crawl_status(jobId).await {
    Ok(status) => status,
    Err(e) => panic!("Failed to check crawl status: {:?}", e),
};

println!("Crawl Status: {:?}", status);

curl -X GET https://api.firecrawl.dev/v0/crawl/status/1234-5678-9101 \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY'

响应

{
  "status": "completed",
  "current": 22,
  "total": 22,
  "data": [
    {
      "content": "Raw Content ",
      "markdown": "# Markdown Content",
      "provider": "web-scraper",
      "metadata": {
        "title": "Firecrawl | Scrape the web reliably for your LLMs",
        "description": "AI for CX and Sales",
        "language": null,
        "sourceURL": "https://docs.firecrawl.dev/"
      }
    }
  ]
}

抓取

要抓取单个 URL，请使用 scrape_url 方法。它接受 URL 作为参数，并返回抓取的数据作为字典。

from firecrawl import FirecrawlApp

app = FirecrawlApp(api_key="YOUR_API_KEY")

content = app.scrape_url("https://docs.firecrawl.dev")

import { FirecrawlApp } from 'firecrawl-js';

const app = new FirecrawlApp({ apiKey: 'YOUR_API_KEY' });

const content = await app.scrapeUrl('https://docs.firecrawl.dev');

import (
  "log"

  "github.com/mendableai/firecrawl-go"
)

func main() {
  app, err := firecrawl.NewFirecrawlApp("YOUR_API_KEY")
  if err != nil {
    log.Fatalf("Failed to initialize FirecrawlApp: %v", err)
  }

  content, err := app.ScrapeURL("docs.firecrawl.dev", nil)
  if err != nil {
    log.Fatalf("Failed to scrape URL: %v", err)
  }
}

use firecrawl::FirecrawlApp;

#[tokio::main]
async fn main() {
    // 初始化 FirecrawlApp 实例，使用 API key
    let api_key = "YOUR_API_KEY";
    let api_url = "https://api.firecrawl.dev";
    let app = FirecrawlApp::new(api_key, api_url).expect("Failed to initialize FirecrawlApp");

    // 抓取 URL
    let scrape_result = app.scrape_url("https://example.com", None).await;

    // 打印抓取结果
  match scrape_result {
    Ok(data) => println!("Scrape Result:
{}", data["markdown"]),
    Err(e) => eprintln!("Scrape failed: {}", e),
  }
}

curl -X POST https://api.firecrawl.dev/v0/scrape \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://docs.firecrawl.dev"
    }'

响应

{
  "success": true,
  "data": {
    "markdown": "<string>",
    "content": "<string>",
    "html": "<string>",
    "rawHtml": "<string>",
    "metadata": {
      "title": "<string>",
      "description": "<string>",
      "language": "<string>",
      "sourceURL": "<string>",
      "<any other metadata> ": "<string>",
      "pageStatusCode": 123,
      "pageError": "<string>"
    },
    "llm_extraction": {},
    "warning": "<string>"
  }
}

提取数据

通过 LLM 提取功能，你可以轻松地从任何 URL 中提取结构化数据。我们支持 pydantic 模式，使其更易于使用。以下是如何使用它的示例：

class ArticleSchema(BaseModel):
    title: str
    points: int 
    by: str
    commentsURL: str

class TopArticlesSchema(BaseModel):
top: List[ArticleSchema] = Field(..., max_items=5, description="Top 5 stories")

data = app.scrape_url('https://news.ycombinator.com', {
'extractorOptions': {
'extractionSchema': TopArticlesSchema.model_json_schema(),
'mode': 'llm-extraction'
},
'pageOptions':{
'onlyMainContent': True
}
})
print(data["llm_extraction"])

import FirecrawlApp from "@mendable/firecrawl-js";
import { z } from "zod";

const app = new FirecrawlApp({
  apiKey: "fc-YOUR_API_KEY",
});

// Define schema to extract contents into
const schema = z.object({
  top: z
    .array(
      z.object({
        title: z.string(),
        points: z.number(),
        by: z.string(),
        commentsURL: z.string(),
      })
    )
    .length(5)
    .describe("Top 5 stories on Hacker News"),
});

const scrapeResult = await app.scrapeUrl("https://news.ycombinator.com", {
  extractorOptions: { extractionSchema: schema },
});

console.log(scrapeResult.data["llm_extraction"]);

import (
  "fmt"
  "log"

  "github.com/mendableai/firecrawl-go"
)

app, err := NewFirecrawlApp(TEST_API_KEY, API_URL)
if err != nil {
  log.Fatalf("Failed to initialize FirecrawlApp: %v", err)
}

params := map[string]any{
  "extractorOptions": ExtractorOptions{
    Mode:             "llm-extraction",
    ExtractionPrompt: "Based on the information on the page, find what the company's mission is and whether it supports SSO, and whether it is open source",
    ExtractionSchema: map[string]any{
      "type": "object",
      "properties": map[string]any{
        "company_mission": map[string]string{"type": "string"},
        "supports_sso":    map[string]string{"type": "boolean"},
        "is_open_source":  map[string]string{"type": "boolean"},
      },
      "required": []string{"company_mission", "supports_sso", "is_open_source"},
    },
  },
}

scrapeResult, err := app.ScrapeURL("https://news.ycombinator.com", params)
if err != nil {
  log.Fatalf("Failed to scrape URL: %v", err)
}
fmt.Println(scrapeResult.LLMExtraction)

use firecrawl::FirecrawlApp;

#[tokio::main]
async fn main() {
    // Initialize the FirecrawlApp with the API key
    let api_key = "YOUR_API_KEY";
    let api_url = "https://api.firecrawl.dev";
    let app = FirecrawlApp::new(api_key, api_url).expect("Failed to initialize FirecrawlApp");

    // Define schema to extract contents into
    let json_schema = json!({
        "type": "object",
        "properties": {
            "top": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "title": {"type": "string"},
                        "points": {"type": "number"},
                        "by": {"type": "string"},
                        "commentsURL": {"type": "string"}
                    },
                    "required": ["title", "points", "by", "commentsURL"]
                },
                "minItems": 5,
                "maxItems": 5,
                "description": "Top 5 stories on Hacker News"
            }
        },
        "required": ["top"]
    });

    let llm_extraction_params = json!({
        "extractorOptions": {
            "extractionSchema": json_schema,
            "mode": "llm-extraction"
        },
        "pageOptions": {
            "onlyMainContent": true
        }
    });

    let llm_extraction_result = app
        .scrape_url("https://news.ycombinator.com", Some(llm_extraction_params))
        .await;
    match llm_extraction_result {
        Ok(data) => println!("LLM Extraction Result:\n{}", data["llm_extraction"]),
        Err(e) => eprintln!("LLM Extraction failed: {}", e),
    }
}

curl -X POST https://api.firecrawl.dev/v0/scrape \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer YOUR_API_KEY' \
    -d '{
      "url": "https://docs.firecrawl.dev/",
      "extractorOptions": {
        "mode": "llm-extraction",
        "extractionPrompt": "Based on the information on the page, extract the information from the schema. ",
        "extractionSchema": {
          "type": "object",
          "properties": {
            "company_mission": {
                      "type": "string"
            },
            "supports_sso": {
                      "type": "boolean"
            },
            "is_open_source": {
                      "type": "boolean"
            },
            "is_in_yc": {
                      "type": "boolean"
            }
          },
          "required": [
            "company_mission",
            "supports_sso",
            "is_open_source",
            "is_in_yc"
          ]
        }
      }
    }'

我们欢迎任何形式的贡献！在提交拉取请求之前，请阅读我们的贡献指南。

​欢迎来到 Firecrawl

​如何使用？

​API 密钥

​爬取

​安装

​使用

​检查抓取作业

​响应

​抓取

​响应

​提取数据

欢迎来到 Firecrawl

如何使用？

API 密钥

爬取

安装

使用

检查抓取作业

响应

抓取

响应

提取数据