Pesquisa

Pesquise e, opcionalmente, faça scraping dos resultados de busca

curl --request POST \
  --url https://api.firecrawl.dev/v2/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "categories": [
    {
      "type": "developer"
    }
  ],
  "country": "US",
  "domainTools": true,
  "enterprise": [],
  "excludeDomains": [
    "<string>"
  ],
  "highlights": true,
  "ignoreInvalidURLs": false,
  "includeDomains": [
    "<string>"
  ],
  "limit": 10,
  "location": "<string>",
  "safe": true,
  "scrapeOptions": {},
  "sources": [
    {
      "type": "web"
    }
  ],
  "tbs": "<string>",
  "threatProtection": {
    "blacklist": [
      "<string>"
    ],
    "blockedTlds": [
      "<string>"
    ],
    "riskScoreThreshold": 75,
    "whitelist": [
      "<string>"
    ]
  },
  "timeout": 60000,
  "toolDetail": "compact"
}
'

import requests

url = "https://api.firecrawl.dev/v2/search"

payload = {
    "query": "<string>",
    "categories": [{ "type": "developer" }],
    "country": "US",
    "domainTools": True,
    "enterprise": [],
    "excludeDomains": ["<string>"],
    "highlights": True,
    "ignoreInvalidURLs": False,
    "includeDomains": ["<string>"],
    "limit": 10,
    "location": "<string>",
    "safe": True,
    "scrapeOptions": {},
    "sources": [{ "type": "web" }],
    "tbs": "<string>",
    "threatProtection": {
        "blacklist": ["<string>"],
        "blockedTlds": ["<string>"],
        "riskScoreThreshold": 75,
        "whitelist": ["<string>"]
    },
    "timeout": 60000,
    "toolDetail": "compact"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query: '<string>',
    categories: [{type: 'developer'}],
    country: 'US',
    domainTools: true,
    enterprise: [],
    excludeDomains: ['<string>'],
    highlights: true,
    ignoreInvalidURLs: false,
    includeDomains: ['<string>'],
    limit: 10,
    location: '<string>',
    safe: true,
    scrapeOptions: {},
    sources: [{type: 'web'}],
    tbs: '<string>',
    threatProtection: {
      blacklist: ['<string>'],
      blockedTlds: ['<string>'],
      riskScoreThreshold: 75,
      whitelist: ['<string>']
    },
    timeout: 60000,
    toolDetail: 'compact'
  })
};

fetch('https://api.firecrawl.dev/v2/search', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.firecrawl.dev/v2/search",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query' => '<string>',
    'categories' => [
        [
                'type' => 'developer'
        ]
    ],
    'country' => 'US',
    'domainTools' => true,
    'enterprise' => [
        
    ],
    'excludeDomains' => [
        '<string>'
    ],
    'highlights' => true,
    'ignoreInvalidURLs' => false,
    'includeDomains' => [
        '<string>'
    ],
    'limit' => 10,
    'location' => '<string>',
    'safe' => true,
    'scrapeOptions' => [
        
    ],
    'sources' => [
        [
                'type' => 'web'
        ]
    ],
    'tbs' => '<string>',
    'threatProtection' => [
        'blacklist' => [
                '<string>'
        ],
        'blockedTlds' => [
                '<string>'
        ],
        'riskScoreThreshold' => 75,
        'whitelist' => [
                '<string>'
        ]
    ],
    'timeout' => 60000,
    'toolDetail' => 'compact'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.firecrawl.dev/v2/search"

	payload := strings.NewReader("{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/search")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.firecrawl.dev/v2/search")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}"

response = http.request(request)
puts response.read_body

{
  "creditsUsed": 123,
  "data": {
    "images": [
      {
        "imageHeight": 123,
        "imageUrl": "<string>",
        "imageWidth": 123,
        "position": 123,
        "title": "<string>",
        "url": "<string>"
      }
    ],
    "news": [
      {
        "audio": "<string>",
        "date": "<string>",
        "html": "<string>",
        "imageUrl": "<string>",
        "links": [
          "<string>"
        ],
        "markdown": "<string>",
        "metadata": {
          "description": "<string>",
          "error": "<string>",
          "numPages": 123,
          "sourceURL": "<string>",
          "statusCode": 123,
          "title": "<string>",
          "totalPages": 123,
          "url": "<string>"
        },
        "position": 123,
        "rawHtml": "<string>",
        "screenshot": "<string>",
        "snippet": "<string>",
        "title": "<string>",
        "url": "<string>",
        "video": "<string>"
      }
    ],
    "tools": [
      {
        "capability": "<string>",
        "description": "<string>",
        "provider": "<string>",
        "creditsCost": 1,
        "id": "<string>",
        "matchedBy": [
          "semantic"
        ],
        "matchedUrls": [
          "<string>"
        ],
        "name": "<string>",
        "options": [
          {
            "name": "<string>",
            "type": "<string>"
          }
        ],
        "perRecord": true,
        "response": {
          "about": "<string>",
          "fields": [
            {}
          ],
          "key": "<string>"
        }
      }
    ],
    "web": [
      {
        "audio": "<string>",
        "description": "<string>",
        "html": "<string>",
        "links": [
          "<string>"
        ],
        "markdown": "<string>",
        "metadata": {
          "description": "<string>",
          "error": "<string>",
          "numPages": 123,
          "sourceURL": "<string>",
          "statusCode": 123,
          "title": "<string>",
          "totalPages": 123,
          "url": "<string>"
        },
        "rawHtml": "<string>",
        "screenshot": "<string>",
        "title": "<string>",
        "url": "<string>",
        "video": "<string>"
      }
    ]
  },
  "id": "<string>",
  "success": true,
  "warning": "<string>"
}

{
  "error": "Request timed out",
  "success": false
}

{
  "code": "UNKNOWN_ERROR",
  "error": "An unexpected error occurred on the server.",
  "success": false
}

POST

Pesquise e, opcionalmente, faça scraping dos resultados de busca

curl --request POST \
  --url https://api.firecrawl.dev/v2/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "query": "<string>",
  "categories": [
    {
      "type": "developer"
    }
  ],
  "country": "US",
  "domainTools": true,
  "enterprise": [],
  "excludeDomains": [
    "<string>"
  ],
  "highlights": true,
  "ignoreInvalidURLs": false,
  "includeDomains": [
    "<string>"
  ],
  "limit": 10,
  "location": "<string>",
  "safe": true,
  "scrapeOptions": {},
  "sources": [
    {
      "type": "web"
    }
  ],
  "tbs": "<string>",
  "threatProtection": {
    "blacklist": [
      "<string>"
    ],
    "blockedTlds": [
      "<string>"
    ],
    "riskScoreThreshold": 75,
    "whitelist": [
      "<string>"
    ]
  },
  "timeout": 60000,
  "toolDetail": "compact"
}
'

import requests

url = "https://api.firecrawl.dev/v2/search"

payload = {
    "query": "<string>",
    "categories": [{ "type": "developer" }],
    "country": "US",
    "domainTools": True,
    "enterprise": [],
    "excludeDomains": ["<string>"],
    "highlights": True,
    "ignoreInvalidURLs": False,
    "includeDomains": ["<string>"],
    "limit": 10,
    "location": "<string>",
    "safe": True,
    "scrapeOptions": {},
    "sources": [{ "type": "web" }],
    "tbs": "<string>",
    "threatProtection": {
        "blacklist": ["<string>"],
        "blockedTlds": ["<string>"],
        "riskScoreThreshold": 75,
        "whitelist": ["<string>"]
    },
    "timeout": 60000,
    "toolDetail": "compact"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    query: '<string>',
    categories: [{type: 'developer'}],
    country: 'US',
    domainTools: true,
    enterprise: [],
    excludeDomains: ['<string>'],
    highlights: true,
    ignoreInvalidURLs: false,
    includeDomains: ['<string>'],
    limit: 10,
    location: '<string>',
    safe: true,
    scrapeOptions: {},
    sources: [{type: 'web'}],
    tbs: '<string>',
    threatProtection: {
      blacklist: ['<string>'],
      blockedTlds: ['<string>'],
      riskScoreThreshold: 75,
      whitelist: ['<string>']
    },
    timeout: 60000,
    toolDetail: 'compact'
  })
};

fetch('https://api.firecrawl.dev/v2/search', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.firecrawl.dev/v2/search",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'query' => '<string>',
    'categories' => [
        [
                'type' => 'developer'
        ]
    ],
    'country' => 'US',
    'domainTools' => true,
    'enterprise' => [
        
    ],
    'excludeDomains' => [
        '<string>'
    ],
    'highlights' => true,
    'ignoreInvalidURLs' => false,
    'includeDomains' => [
        '<string>'
    ],
    'limit' => 10,
    'location' => '<string>',
    'safe' => true,
    'scrapeOptions' => [
        
    ],
    'sources' => [
        [
                'type' => 'web'
        ]
    ],
    'tbs' => '<string>',
    'threatProtection' => [
        'blacklist' => [
                '<string>'
        ],
        'blockedTlds' => [
                '<string>'
        ],
        'riskScoreThreshold' => 75,
        'whitelist' => [
                '<string>'
        ]
    ],
    'timeout' => 60000,
    'toolDetail' => 'compact'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.firecrawl.dev/v2/search"

	payload := strings.NewReader("{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/search")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.firecrawl.dev/v2/search")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"query\": \"<string>\",\n  \"categories\": [\n    {\n      \"type\": \"developer\"\n    }\n  ],\n  \"country\": \"US\",\n  \"domainTools\": true,\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"highlights\": true,\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"safe\": true,\n  \"scrapeOptions\": {},\n  \"sources\": [\n    {\n      \"type\": \"web\"\n    }\n  ],\n  \"tbs\": \"<string>\",\n  \"threatProtection\": {\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ],\n    \"riskScoreThreshold\": 75,\n    \"whitelist\": [\n      \"<string>\"\n    ]\n  },\n  \"timeout\": 60000,\n  \"toolDetail\": \"compact\"\n}"

response = http.request(request)
puts response.read_body

{
  "creditsUsed": 123,
  "data": {
    "images": [
      {
        "imageHeight": 123,
        "imageUrl": "<string>",
        "imageWidth": 123,
        "position": 123,
        "title": "<string>",
        "url": "<string>"
      }
    ],
    "news": [
      {
        "audio": "<string>",
        "date": "<string>",
        "html": "<string>",
        "imageUrl": "<string>",
        "links": [
          "<string>"
        ],
        "markdown": "<string>",
        "metadata": {
          "description": "<string>",
          "error": "<string>",
          "numPages": 123,
          "sourceURL": "<string>",
          "statusCode": 123,
          "title": "<string>",
          "totalPages": 123,
          "url": "<string>"
        },
        "position": 123,
        "rawHtml": "<string>",
        "screenshot": "<string>",
        "snippet": "<string>",
        "title": "<string>",
        "url": "<string>",
        "video": "<string>"
      }
    ],
    "tools": [
      {
        "capability": "<string>",
        "description": "<string>",
        "provider": "<string>",
        "creditsCost": 1,
        "id": "<string>",
        "matchedBy": [
          "semantic"
        ],
        "matchedUrls": [
          "<string>"
        ],
        "name": "<string>",
        "options": [
          {
            "name": "<string>",
            "type": "<string>"
          }
        ],
        "perRecord": true,
        "response": {
          "about": "<string>",
          "fields": [
            {}
          ],
          "key": "<string>"
        }
      }
    ],
    "web": [
      {
        "audio": "<string>",
        "description": "<string>",
        "html": "<string>",
        "links": [
          "<string>"
        ],
        "markdown": "<string>",
        "metadata": {
          "description": "<string>",
          "error": "<string>",
          "numPages": 123,
          "sourceURL": "<string>",
          "statusCode": 123,
          "title": "<string>",
          "totalPages": 123,
          "url": "<string>"
        },
        "rawHtml": "<string>",
        "screenshot": "<string>",
        "title": "<string>",
        "url": "<string>",
        "video": "<string>"
      }
    ]
  },
  "id": "<string>",
  "success": true,
  "warning": "<string>"
}

{
  "error": "Request timed out",
  "success": false
}

{
  "code": "UNKNOWN_ERROR",
  "error": "An unexpected error occurred on the server.",
  "success": false
}

O endpoint de pesquisa combina pesquisa na web com as capacidades de scraping do Firecrawl para retornar o conteúdo completo da página para qualquer consulta. Inclua scrapeOptions com formats: [{"type": "markdown"}] para obter o conteúdo completo em markdown para cada resultado de pesquisa; caso contrário, você receberá por padrão apenas os resultados (url, title, description). Você também pode usar outros formatos, como {"type": "summary"} para conteúdo condensado.

Operadores de pesquisa compatíveis

Oferecemos uma variedade de operadores de pesquisa que ajudam você a filtrar melhor seus resultados.

Operador	Funcionalidade	Exemplos
`""`	Faz uma correspondência exata com um trecho de texto	`"Firecrawl"`
`-`	Exclui determinadas palavras-chave ou nega outros operadores	`-bad`, `-site:firecrawl.dev`
`site:`	Retorna apenas resultados de um site específico	`site:firecrawl.dev`
`filetype:`	Retorna apenas resultados com uma extensão de arquivo específica	`filetype:pdf`, `-filetype:pdf`
`inurl:`	Retorna apenas resultados que incluam uma palavra na URL	`inurl:firecrawl`
`allinurl:`	Retorna apenas resultados que incluam várias palavras na URL	`allinurl:git firecrawl`
`intitle:`	Retorna apenas resultados que incluam uma palavra no título da página	`intitle:Firecrawl`
`allintitle:`	Retorna apenas resultados que incluam várias palavras no título da página	`allintitle:firecrawl playground`
`related:`	Retorna apenas resultados relacionados a um domínio específico	`related:firecrawl.dev`
`imagesize:`	Retorna apenas imagens com dimensões exatas	`imagesize:1920x1080`
`larger:`	Retorna apenas imagens maiores que as dimensões especificadas	`larger:1920x1080`

Parâmetro de localização

Use o parâmetro location para obter resultados de pesquisa segmentados por região. Formato: "string". Exemplos: "Germany", "San Francisco,California,United States". Consulte a lista completa de localidades compatíveis para ver todos os países e idiomas disponíveis.

Parâmetro country

Use o parâmetro country para definir o país dos resultados de pesquisa usando códigos de país ISO. Padrão: "US". Exemplos: "US", "DE", "FR", "JP", "UK", "CA".

{
  "query": "restaurantes",
  "country": "DE"
}

Parâmetro Categories

Filtre os resultados de busca por categorias específicas usando o parâmetro categories:

research: Restringe a pesquisa na web a sites acadêmicos e de pesquisa (arxiv.org, nature.com, pubmed.ncbi.nlm.nih.gov e similares). Os resultados são páginas web, retornadas em data.web. Para registros de artigos, use GET /search/research/papers
pdf: Busca por PDFs
developer: Busca no Índice para Desenvolvedores — issues, pull requests mesclados e READMEs de repositórios de código públicos, além de sites de documentação selecionados
gov: Busca no Firecrawl Government Index — leis, regulamentos, códigos, decisões judiciais e outras publicações governamentais. Não pode ser combinada com outras categorias e não aceita filtros; use /search/gov para filtrar

Exemplo de uso

{
  "query": "machine learning",
  "categories": ["research", "pdf"],
  "limit": 10
}

Filtros de domínio

Use includeDomains para restringir os resultados a domínios específicos ou excludeDomains para excluir domínios específicos da busca. Os domínios devem conter apenas nomes de host, sem protocolo ou caminho. includeDomains e excludeDomains são mutuamente excludentes.

Exemplo de inclusão de domínios

{
  "query": "web scraping",
  "includeDomains": ["firecrawl.dev", "docs.firecrawl.dev"],
  "limit": 10
}

Exemplo de exclusão de domínios

{
  "query": "web scraping tools",
  "excludeDomains": ["example.com"],
  "limit": 10
}

Categoria da Resposta

Cada resultado inclui um campo category que indica sua origem:

{
  "success": true,
  "data": {
    "web": [
      {
        "url": "https://arxiv.org/abs/2024.12345",
        "title": "ML Research Paper",
        "description": "Latest advances in machine learning",
        "category": "research"
      },
      {
        "url": "https://example.com/ml-survey.pdf",
        "title": "ML Survey",
        "description": "A survey of machine learning methods",
        "category": "pdf"
      }
    ]
  }
}

Busca por período de tempo

Use o parâmetro tbs para filtrar resultados por períodos de tempo, incluindo intervalos de datas personalizados. Consulte a documentação do recurso de busca para exemplos detalhados e formatos suportados.

Você é um agente de IA que precisa de uma chave de API da Firecrawl? Consulte firecrawl.dev/agent-onboarding/SKILL.md para instruções de onboarding automatizado.

Autorizações

Authorization

string

header

obrigatório

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Corpo

application/json

query

string

obrigatório

A consulta de busca

Maximum string length: 500

Resposta

Resposta bem-sucedida

creditsUsed

integer

O número de créditos utilizados na busca

data

object

Os resultados da pesquisa. Os arrays disponíveis dependerão das fontes que você especificar na requisição. Por padrão, o array web será retornado.

Show child attributes

string

O ID da tarefa de pesquisa

success

boolean

warning

string | null

Mensagem de aviso caso ocorra algum problema. Inclui Some tool discovery results are unavailable. quando a descoberta de ferramentas do Alexandria ou de domínio falha parcialmente.

Usando a API

Endpoints de busca

Endpoints /scrape

Endpoints para interagir / Browser Sandbox

Endpoints do Research Index

Endpoints do índice para desenvolvedores

Endpoints do índice governamental

Endpoints de mapeamento

Endpoints de Parse

Endpoints de rastreamento

Endpoints de monitoramento

Endpoints de agente

Endpoints de feedback

Endpoints de depuração agêntica

Endpoints da conta

Payloads de webhook

Firecrawl for Platforms

Operadores de pesquisa compatíveis

Parâmetro de localização

Parâmetro country

Parâmetro Categories

Exemplo de uso

Filtros de domínio

Exemplo de inclusão de domínios

Exemplo de exclusão de domínios

Categoria da Resposta

Busca por período de tempo

Autorizações

Corpo

Resposta