Démarrage rapide

pip install firecrawl-py

npm install firecrawl

go get github.com/mendableai/firecrawl-go

# ajoutez ce qui suit à votre 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"] }

from firecrawl import Firecrawl

app = Firecrawl(api_key="YOUR_API_KEY")

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

# Récupérer le markdown
for result in crawl_result:
    print(result['markdown'])

import { Firecrawl } from "firecrawl";

// Initialiser Firecrawl avec votre clé API
const app = new Firecrawl({ apiKey: "YOUR_API_KEY" });

// Crawler un site web
const crawlResult = await app.crawlUrl("docs.firecrawl.dev", {
  crawlerOptions: { excludes: ["blog/*"] },
});

// Afficher le markdown
console.log(crawlResult.map((result) => result.markdown));

import (
  "fmt"
  "log"

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

func main() {
  // Initialiser Firecrawl avec votre clé API
  app, err := firecrawl.NewFirecrawlApp("YOUR_API_KEY")
  if err != nil {
    log.Fatalf("Échec de l'initialisation de Firecrawl : %v", err)
  }

  // Crawler un site web
  params := map[string]any{
    "crawlerOptions": map[string]any{
      "excludes": []string{"blog/*"},
    },
  }
  crawlResult, err := app.CrawlURL("docs.firecrawl.dev", params)
  if err != nil {
    log.Fatalf("Erreur lors du crawl : %v", err)
  }

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

use firecrawl::Firecrawl;

#[tokio::main]
async fn main() {
  // Initialiser Firecrawl avec la clé API
  let api_key = "YOUR_API_KEY";
  let api_url = "https://api.firecrawl.dev";
  let app = Firecrawl::new(api_key, api_url).expect("Échec de l'initialisation de Firecrawl");

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

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

  // Afficher le résultat du crawl
  match crawl_result {
      Ok(data) => println!("Résultat du crawl:\n{}", data),
      Err(e) => eprintln!("Échec du crawl : {}", 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"
    }'

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'

from firecrawl import Firecrawl

app = Firecrawl(api_key="YOUR_API_KEY")

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

import { Firecrawl } from 'firecrawl-js';

const app = new Firecrawl({ 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 Firecrawl: %v", err)
  }

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

use firecrawl::Firecrawl;

#[tokio::main]
async fn main() {
    // Initialiser Firecrawl avec la clé API
    let api_key = "YOUR_API_KEY";
    let api_url = "https://api.firecrawl.dev";
    let app = Firecrawl::new(api_key, api_url).expect("Failed to initialize Firecrawl");

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

    // Afficher le résultat du scraping
  match scrape_result {
    Ok(data) => println!("Scrape Result:\n{}", 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"
    }'

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 { Firecrawl } from "firecrawl";
import { z } from "zod";

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

// Définir le schéma dans lequel extraire le contenu
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("Échec de l'initialisation de Firecrawl : %v", err)
}

params := map[string]any{
  "extractorOptions": ExtractorOptions{
    Mode:             "llm-extraction",
    ExtractionPrompt: "D'après les informations de la page, identifiez la mission de l'entreprise, précisez si elle prend en charge le SSO et si elle est 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("Échec du scraping de l'URL : %v", err)
}
fmt.Println(scrapeResult.LLMExtraction)

use firecrawl::Firecrawl;

#[tokio::main]
async fn main() {
    // Initialiser Firecrawl avec la clé d'API
    let api_key = "YOUR_API_KEY";
    let api_url = "https://api.firecrawl.dev";
    let app = Firecrawl::new(api_key, api_url).expect("Échec de l'initialisation de Firecrawl");

    // Définir le schéma d'extraction du contenu
    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!("Résultat de l'extraction LLM :\n{}", data["llm_extraction"]),
        Err(e) => eprintln!("Échec de l'extraction LLM : {}", 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"
          ]
        }
      }
    }'