Pular para o conteúdo principal

Documentation Index

Fetch the complete documentation index at: https://firecrawl-mog-search-exclude-include-domains.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

​
Pré-requisitos

​
Fazer uma busca na web

O Firecrawl funciona com PHP por meio da API REST com cURL. 
<?php
$apiKey = getenv('FIRECRAWL_API_KEY');

$ch = curl_init('https://api.firecrawl.dev/v2/search');
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . $apiKey,
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'query' => 'firecrawl web scraping',
        'limit' => 5,
    ]),
]);

$response = curl_exec($ch);
curl_close($ch);

$results = json_decode($response, true);
foreach ($results['data']['web'] as $result) {
    echo $result['title'] . ' - ' . $result['url'] . "\n";
}

{
  "success": true,
  "data": {
    "web": [
      {
        "url": "https://docs.firecrawl.dev",
        "title": "Firecrawl Documentation",
        "markdown": "# Firecrawl\n\nFirecrawl is a web scraping API..."
      }
    ]
  }
}

​
Fazer scraping de uma página

<?php
$ch = curl_init('https://api.firecrawl.dev/v2/scrape');
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . $apiKey,
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'url' => 'https://example.com',
    ]),
]);

$response = curl_exec($ch);
curl_close($ch);

$data = json_decode($response, true);
echo $data['data']['markdown'];

{
  "success": true,
  "data": {
    "markdown": "# Example Domain\n\nThis domain is for use in illustrative examples...",
    "metadata": {
      "title": "Example Domain",
      "sourceURL": "https://example.com"
    }
  }
}

​
Interaja com uma página

Inicie uma sessão no navegador, interaja com a página usando prompts em linguagem natural e, em seguida, encerre a sessão.

​
Etapa 1 — Faça scraping para iniciar uma sessão

<?php
$ch = curl_init('https://api.firecrawl.dev/v2/scrape');
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . $apiKey,
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => json_encode([
        'url' => 'https://www.amazon.com',
        'formats' => ['markdown'],
    ]),
]);

$response = curl_exec($ch);
curl_close($ch);

$scrapeResult = json_decode($response, true);
$scrapeId = $scrapeResult['data']['metadata']['scrapeId'];
echo "scrapeId: $scrapeId\n";

​
Etapa 2 — Enviar as interações

<?php
$interactUrl = "https://api.firecrawl.dev/v2/scrape/$scrapeId/interact";
$headers = [
    'Authorization: Bearer ' . $apiKey,
    'Content-Type: application/json',
];

// Buscar um produto
$ch = curl_init($interactUrl);
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => $headers,
    CURLOPT_POSTFIELDS => json_encode([
        'prompt' => 'Search for iPhone 16 Pro Max',
    ]),
]);

$response = curl_exec($ch);
curl_close($ch);
echo $response . "\n";

// Clicar no primeiro resultado
$ch = curl_init($interactUrl);
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => $headers,
    CURLOPT_POSTFIELDS => json_encode([
        'prompt' => 'Click on the first result and tell me the price',
    ]),
]);

$response = curl_exec($ch);
curl_close($ch);
echo $response . "\n";

​
Etapa 3 — Encerre a sessão

<?php
$ch = curl_init($interactUrl);
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_CUSTOMREQUEST => 'DELETE',
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . $apiKey,
    ],
]);

curl_exec($ch);
curl_close($ch);

echo "Sessão encerrada\n";

​
Classe auxiliar reutilizável

Para reutilização, encapsule a API em uma classe: 
<?php
class Firecrawl
{
    private string $apiKey;
    private string $baseUrl = 'https://api.firecrawl.dev/v2';

    public function __construct(string $apiKey)
    {
        $this->apiKey = $apiKey;
    }

    private function post(string $endpoint, array $payload): array
    {
        $ch = curl_init($this->baseUrl . $endpoint);
        curl_setopt_array($ch, [
            CURLOPT_RETURNTRANSFER => true,
            CURLOPT_POST => true,
            CURLOPT_HTTPHEADER => [
                'Authorization: Bearer ' . $this->apiKey,
                'Content-Type: application/json',
            ],
            CURLOPT_POSTFIELDS => json_encode($payload),
        ]);

        $response = curl_exec($ch);
        $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
        curl_close($ch);

        if ($httpCode >= 400) {
            throw new \RuntimeException("Firecrawl API error: HTTP $httpCode");
        }

        return json_decode($response, true);
    }

    public function scrape(string $url, array $options = []): array
    {
        return $this->post('/scrape', array_merge(['url' => $url], $options));
    }

    public function search(string $query, int $limit = 5): array
    {
        return $this->post('/search', ['query' => $query, 'limit' => $limit]);
    }
}

// Uso
$app = new Firecrawl(getenv('FIRECRAWL_API_KEY'));
$result = $app->scrape('https://example.com');
echo $result['data']['markdown'];

​
Próximos passos

Docs do Search

Faça uma busca na web e obtenha o conteúdo completo da página

Docs do scraping

Todas as opções de scraping, incluindo formatos, ações e proxies

Docs do interagir

Clique, preencha formulários e extraia conteúdo dinâmico

Referência da API

Documentação completa da API REST