検索 - Firecrawl Docs

検索し、必要に応じて検索結果をスクレイピングする

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

import requests

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

payload = {
    "query": "<string>",
    "categories": [{ "type": "github" }],
    "country": "US",
    "enterprise": [],
    "excludeDomains": ["<string>"],
    "ignoreInvalidURLs": False,
    "includeDomains": ["<string>"],
    "limit": 10,
    "location": "<string>",
    "scrapeOptions": {},
    "sources": ["web"],
    "tbs": "<string>",
    "threatProtection": {
        "blacklist": ["<string>"],
        "blockedTlds": ["<string>"],
        "riskScoreThreshold": 75,
        "whitelist": ["<string>"]
    },
    "timeout": 60000
}
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: 'github'}],
    country: 'US',
    enterprise: [],
    excludeDomains: ['<string>'],
    ignoreInvalidURLs: false,
    includeDomains: ['<string>'],
    limit: 10,
    location: '<string>',
    scrapeOptions: {},
    sources: ['web'],
    tbs: '<string>',
    threatProtection: {
      blacklist: ['<string>'],
      blockedTlds: ['<string>'],
      riskScoreThreshold: 75,
      whitelist: ['<string>']
    },
    timeout: 60000
  })
};

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' => 'github'
        ]
    ],
    'country' => 'US',
    'enterprise' => [
        
    ],
    'excludeDomains' => [
        '<string>'
    ],
    'ignoreInvalidURLs' => false,
    'includeDomains' => [
        '<string>'
    ],
    'limit' => 10,
    'location' => '<string>',
    'scrapeOptions' => [
        
    ],
    'sources' => [
        'web'
    ],
    'tbs' => '<string>',
    'threatProtection' => [
        'blacklist' => [
                '<string>'
        ],
        'blockedTlds' => [
                '<string>'
        ],
        'riskScoreThreshold' => 75,
        'whitelist' => [
                '<string>'
        ]
    ],
    'timeout' => 60000
  ]),
  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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}")

	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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}")
  .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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}"

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>"
      }
    ],
    "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

検索し、必要に応じて検索結果をスクレイピングする

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

import requests

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

payload = {
    "query": "<string>",
    "categories": [{ "type": "github" }],
    "country": "US",
    "enterprise": [],
    "excludeDomains": ["<string>"],
    "ignoreInvalidURLs": False,
    "includeDomains": ["<string>"],
    "limit": 10,
    "location": "<string>",
    "scrapeOptions": {},
    "sources": ["web"],
    "tbs": "<string>",
    "threatProtection": {
        "blacklist": ["<string>"],
        "blockedTlds": ["<string>"],
        "riskScoreThreshold": 75,
        "whitelist": ["<string>"]
    },
    "timeout": 60000
}
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: 'github'}],
    country: 'US',
    enterprise: [],
    excludeDomains: ['<string>'],
    ignoreInvalidURLs: false,
    includeDomains: ['<string>'],
    limit: 10,
    location: '<string>',
    scrapeOptions: {},
    sources: ['web'],
    tbs: '<string>',
    threatProtection: {
      blacklist: ['<string>'],
      blockedTlds: ['<string>'],
      riskScoreThreshold: 75,
      whitelist: ['<string>']
    },
    timeout: 60000
  })
};

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' => 'github'
        ]
    ],
    'country' => 'US',
    'enterprise' => [
        
    ],
    'excludeDomains' => [
        '<string>'
    ],
    'ignoreInvalidURLs' => false,
    'includeDomains' => [
        '<string>'
    ],
    'limit' => 10,
    'location' => '<string>',
    'scrapeOptions' => [
        
    ],
    'sources' => [
        'web'
    ],
    'tbs' => '<string>',
    'threatProtection' => [
        'blacklist' => [
                '<string>'
        ],
        'blockedTlds' => [
                '<string>'
        ],
        'riskScoreThreshold' => 75,
        'whitelist' => [
                '<string>'
        ]
    ],
    'timeout' => 60000
  ]),
  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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}")

	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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}")
  .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\": \"github\"\n    }\n  ],\n  \"country\": \"US\",\n  \"enterprise\": [],\n  \"excludeDomains\": [\n    \"<string>\"\n  ],\n  \"ignoreInvalidURLs\": false,\n  \"includeDomains\": [\n    \"<string>\"\n  ],\n  \"limit\": 10,\n  \"location\": \"<string>\",\n  \"scrapeOptions\": {},\n  \"sources\": [\n    \"web\"\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}"

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>"
      }
    ],
    "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
}

この search エンドポイントは、Web 検索と Firecrawl のスクレイピング機能を組み合わせることで、あらゆるクエリに対してページ全体のコンテンツを返します。各検索結果の Markdown 形式の完全なコンテンツを取得するには、scrapeOptions に formats: [{"type": "markdown"}] を指定してください。指定しない場合は、結果（url、title、description）がデフォルトで返されます。要約されたコンテンツが必要な場合は、{"type": "summary"} など他のフォーマットも使用できます。

サポートされているクエリ演算子

検索をより的確に絞り込むための各種クエリ演算子をサポートしています。

演算子	機能	例
`""`	テキストを厳密一致で検索する	`"Firecrawl"`
`-`	特定のキーワードを除外、または他の演算子を否定する	`-bad`, `-site:firecrawl.dev`
`site:`	指定したサイトの結果のみを返す	`site:firecrawl.dev`
`filetype:`	特定のファイル拡張子を持つ結果のみを返す	`filetype:pdf`, `-filetype:pdf`
`inurl:`	URL に特定の語を含む結果のみを返す	`inurl:firecrawl`
`allinurl:`	URL に複数の語を含む結果のみを返す	`allinurl:git firecrawl`
`intitle:`	ページタイトルに特定の語を含む結果のみを返す	`intitle:Firecrawl`
`allintitle:`	ページタイトルに複数の語を含む結果のみを返す	`allintitle:firecrawl playground`
`related:`	特定のドメインに関連する結果のみを返す	`related:firecrawl.dev`
`imagesize:`	指定した寸法と完全一致の画像のみを返す	`imagesize:1920x1080`
`larger:`	指定した寸法より大きい画像のみを返す	`larger:1920x1080`

Location パラメータ

location パラメータで地域ターゲットの検索結果を取得します。形式: "string"。例: "Germany"、"San Francisco,California,United States"。利用可能な国と言語の一覧は、サポート対象ロケーションの全リストをご覧ください。

Country パラメータ

country パラメータで、ISO の国コードを用いて検索結果の対象国を指定します。既定値: "US"。例: "US", "DE", "FR", "JP", "UK", "CA"。

{
  "query": "レストラン",
  "country": "DE"
}

Categories パラメータ

categories パラメータで、特定のカテゴリに検索結果を絞り込みます：

github: GitHub のリポジトリ、コード、Issue、ドキュメントを検索
research: 学術系・研究系のウェブサイト（arXiv、Nature、IEEE、PubMed など）を検索
pdf: PDF を検索

使い方の例

{
  "query": "機械学習",
  "categories": ["github", "research"],
  "limit": 10
}

ドメインフィルター

includeDomains を使うと結果を特定のドメインに限定でき、excludeDomains を使うと検索結果から特定のドメインを除外できます。ドメインには、プロトコルやパスを含めず、ホスト名のみを指定してください。 includeDomains と excludeDomains は同時に使用できません。

含めるドメインの例

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

除外ドメインの例

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

カテゴリレスポンス

各結果には、どのソースからのものかを示す category フィールドが含まれます。

{
  "success": true,
  "data": {
    "web": [
      {
        "url": "https://github.com/example/ml-project",
        "title": "Machine Learning Project",
        "description": "Implementation of ML algorithms",
        "category": "github"
      },
      {
        "url": "https://arxiv.org/abs/2024.12345",
        "title": "ML Research Paper",
        "description": "Latest advances in machine learning",
        "category": "research"
      }
    ]
  }
}

時間ベースの検索

tbs パラメータを使用すると、カスタム日付範囲を含む期間で検索結果を時間別に絞り込むことができます。詳細な例とサポートされている形式については、検索機能のドキュメントを参照してください。

Firecrawl API key が必要な AI agent ですか？自動オンボーディング手順については、firecrawl.dev/agent-onboarding/SKILL.mdを参照してください。

承認

Authorization

string

header

必須

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

ボディ

application/json

query

string

必須

検索クエリ

Maximum string length: 500

レスポンス

成功時のレスポンス

creditsUsed

integer

検索で使用されたクレジット数

data

object

検索結果。利用可能な配列は、リクエストで指定したソースに応じて変わります。デフォルトでは web 配列が返されます。

Show child attributes

string

検索ジョブのID

success

boolean

warning

string | null

何らかの問題が発生した場合の警告メッセージ

エラー

検索フィードバック

​サポートされているクエリ演算子

​Location パラメータ

​Country パラメータ

​Categories パラメータ

​使い方の例

​ドメインフィルター

​含めるドメインの例

​除外ドメインの例

​カテゴリレスポンス

​時間ベースの検索

承認

ボディ

レスポンス

サポートされているクエリ演算子

Location パラメータ

Country パラメータ

Categories パラメータ

使い方の例

ドメインフィルター

含めるドメインの例

除外ドメインの例

カテゴリレスポンス

時間ベースの検索