Skip to main content
POST
/
extract
Extract structured data from pages using LLMs
curl --request POST \
  --url https://api.firecrawl.dev/v2/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "urls": [
    "<string>"
  ],
  "prompt": "<string>",
  "schema": {},
  "enableWebSearch": false,
  "ignoreSitemap": false,
  "includeSubdomains": true,
  "showSources": false,
  "scrapeOptions": {
    "formats": [
      "markdown"
    ],
    "onlyMainContent": true,
    "onlyCleanContent": false,
    "includeTags": [
      "<string>"
    ],
    "excludeTags": [
      "<string>"
    ],
    "maxAge": 172800000,
    "minAge": 123,
    "headers": {},
    "waitFor": 0,
    "mobile": false,
    "skipTlsVerification": true,
    "timeout": 60000,
    "parsers": [
      "pdf"
    ],
    "actions": [
      {
        "type": "wait",
        "milliseconds": 2
      }
    ],
    "location": {
      "country": "US",
      "languages": [
        "en-US"
      ]
    },
    "removeBase64Images": true,
    "blockAds": true,
    "proxy": "auto",
    "storeInCache": true,
    "lockdown": false,
    "redactPII": false,
    "threatProtection": {
      "riskScoreThreshold": 75,
      "blacklist": [
        "<string>"
      ],
      "whitelist": [
        "<string>"
      ],
      "blockedTlds": [
        "<string>"
      ]
    }
  },
  "ignoreInvalidURLs": true,
  "threatProtection": {
    "riskScoreThreshold": 75,
    "blacklist": [
      "<string>"
    ],
    "whitelist": [
      "<string>"
    ],
    "blockedTlds": [
      "<string>"
    ]
  }
}
'
import requests

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

payload = {
    "urls": ["<string>"],
    "prompt": "<string>",
    "schema": {},
    "enableWebSearch": False,
    "ignoreSitemap": False,
    "includeSubdomains": True,
    "showSources": False,
    "scrapeOptions": {
        "formats": ["markdown"],
        "onlyMainContent": True,
        "onlyCleanContent": False,
        "includeTags": ["<string>"],
        "excludeTags": ["<string>"],
        "maxAge": 172800000,
        "minAge": 123,
        "headers": {},
        "waitFor": 0,
        "mobile": False,
        "skipTlsVerification": True,
        "timeout": 60000,
        "parsers": ["pdf"],
        "actions": [
            {
                "type": "wait",
                "milliseconds": 2
            }
        ],
        "location": {
            "country": "US",
            "languages": ["en-US"]
        },
        "removeBase64Images": True,
        "blockAds": True,
        "proxy": "auto",
        "storeInCache": True,
        "lockdown": False,
        "redactPII": False,
        "threatProtection": {
            "riskScoreThreshold": 75,
            "blacklist": ["<string>"],
            "whitelist": ["<string>"],
            "blockedTlds": ["<string>"]
        }
    },
    "ignoreInvalidURLs": True,
    "threatProtection": {
        "riskScoreThreshold": 75,
        "blacklist": ["<string>"],
        "whitelist": ["<string>"],
        "blockedTlds": ["<string>"]
    }
}
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({
    urls: ['<string>'],
    prompt: '<string>',
    schema: {},
    enableWebSearch: false,
    ignoreSitemap: false,
    includeSubdomains: true,
    showSources: false,
    scrapeOptions: {
      formats: ['markdown'],
      onlyMainContent: true,
      onlyCleanContent: false,
      includeTags: ['<string>'],
      excludeTags: ['<string>'],
      maxAge: 172800000,
      minAge: 123,
      headers: {},
      waitFor: 0,
      mobile: false,
      skipTlsVerification: true,
      timeout: 60000,
      parsers: ['pdf'],
      actions: [{type: 'wait', milliseconds: 2}],
      location: {country: 'US', languages: ['en-US']},
      removeBase64Images: true,
      blockAds: true,
      proxy: 'auto',
      storeInCache: true,
      lockdown: false,
      redactPII: false,
      threatProtection: {
        riskScoreThreshold: 75,
        blacklist: ['<string>'],
        whitelist: ['<string>'],
        blockedTlds: ['<string>']
      }
    },
    ignoreInvalidURLs: true,
    threatProtection: {
      riskScoreThreshold: 75,
      blacklist: ['<string>'],
      whitelist: ['<string>'],
      blockedTlds: ['<string>']
    }
  })
};

fetch('https://api.firecrawl.dev/v2/extract', 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/extract",
  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([
    'urls' => [
        '<string>'
    ],
    'prompt' => '<string>',
    'schema' => [
        
    ],
    'enableWebSearch' => false,
    'ignoreSitemap' => false,
    'includeSubdomains' => true,
    'showSources' => false,
    'scrapeOptions' => [
        'formats' => [
                'markdown'
        ],
        'onlyMainContent' => true,
        'onlyCleanContent' => false,
        'includeTags' => [
                '<string>'
        ],
        'excludeTags' => [
                '<string>'
        ],
        'maxAge' => 172800000,
        'minAge' => 123,
        'headers' => [
                
        ],
        'waitFor' => 0,
        'mobile' => false,
        'skipTlsVerification' => true,
        'timeout' => 60000,
        'parsers' => [
                'pdf'
        ],
        'actions' => [
                [
                                'type' => 'wait',
                                'milliseconds' => 2
                ]
        ],
        'location' => [
                'country' => 'US',
                'languages' => [
                                'en-US'
                ]
        ],
        'removeBase64Images' => true,
        'blockAds' => true,
        'proxy' => 'auto',
        'storeInCache' => true,
        'lockdown' => false,
        'redactPII' => false,
        'threatProtection' => [
                'riskScoreThreshold' => 75,
                'blacklist' => [
                                '<string>'
                ],
                'whitelist' => [
                                '<string>'
                ],
                'blockedTlds' => [
                                '<string>'
                ]
        ]
    ],
    'ignoreInvalidURLs' => true,
    'threatProtection' => [
        'riskScoreThreshold' => 75,
        'blacklist' => [
                '<string>'
        ],
        'whitelist' => [
                '<string>'
        ],
        'blockedTlds' => [
                '<string>'
        ]
    ]
  ]),
  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/extract"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"prompt\": \"<string>\",\n  \"schema\": {},\n  \"enableWebSearch\": false,\n  \"ignoreSitemap\": false,\n  \"includeSubdomains\": true,\n  \"showSources\": false,\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"onlyCleanContent\": false,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"maxAge\": 172800000,\n    \"minAge\": 123,\n    \"headers\": {},\n    \"waitFor\": 0,\n    \"mobile\": false,\n    \"skipTlsVerification\": true,\n    \"timeout\": 60000,\n    \"parsers\": [\n      \"pdf\"\n    ],\n    \"actions\": [\n      {\n        \"type\": \"wait\",\n        \"milliseconds\": 2\n      }\n    ],\n    \"location\": {\n      \"country\": \"US\",\n      \"languages\": [\n        \"en-US\"\n      ]\n    },\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"proxy\": \"auto\",\n    \"storeInCache\": true,\n    \"lockdown\": false,\n    \"redactPII\": false,\n    \"threatProtection\": {\n      \"riskScoreThreshold\": 75,\n      \"blacklist\": [\n        \"<string>\"\n      ],\n      \"whitelist\": [\n        \"<string>\"\n      ],\n      \"blockedTlds\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"ignoreInvalidURLs\": true,\n  \"threatProtection\": {\n    \"riskScoreThreshold\": 75,\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"whitelist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ]\n  }\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/extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"<string>\"\n  ],\n  \"prompt\": \"<string>\",\n  \"schema\": {},\n  \"enableWebSearch\": false,\n  \"ignoreSitemap\": false,\n  \"includeSubdomains\": true,\n  \"showSources\": false,\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"onlyCleanContent\": false,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"maxAge\": 172800000,\n    \"minAge\": 123,\n    \"headers\": {},\n    \"waitFor\": 0,\n    \"mobile\": false,\n    \"skipTlsVerification\": true,\n    \"timeout\": 60000,\n    \"parsers\": [\n      \"pdf\"\n    ],\n    \"actions\": [\n      {\n        \"type\": \"wait\",\n        \"milliseconds\": 2\n      }\n    ],\n    \"location\": {\n      \"country\": \"US\",\n      \"languages\": [\n        \"en-US\"\n      ]\n    },\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"proxy\": \"auto\",\n    \"storeInCache\": true,\n    \"lockdown\": false,\n    \"redactPII\": false,\n    \"threatProtection\": {\n      \"riskScoreThreshold\": 75,\n      \"blacklist\": [\n        \"<string>\"\n      ],\n      \"whitelist\": [\n        \"<string>\"\n      ],\n      \"blockedTlds\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"ignoreInvalidURLs\": true,\n  \"threatProtection\": {\n    \"riskScoreThreshold\": 75,\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"whitelist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ]\n  }\n}")
  .asString();
require 'uri'
require 'net/http'

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

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  \"urls\": [\n    \"<string>\"\n  ],\n  \"prompt\": \"<string>\",\n  \"schema\": {},\n  \"enableWebSearch\": false,\n  \"ignoreSitemap\": false,\n  \"includeSubdomains\": true,\n  \"showSources\": false,\n  \"scrapeOptions\": {\n    \"formats\": [\n      \"markdown\"\n    ],\n    \"onlyMainContent\": true,\n    \"onlyCleanContent\": false,\n    \"includeTags\": [\n      \"<string>\"\n    ],\n    \"excludeTags\": [\n      \"<string>\"\n    ],\n    \"maxAge\": 172800000,\n    \"minAge\": 123,\n    \"headers\": {},\n    \"waitFor\": 0,\n    \"mobile\": false,\n    \"skipTlsVerification\": true,\n    \"timeout\": 60000,\n    \"parsers\": [\n      \"pdf\"\n    ],\n    \"actions\": [\n      {\n        \"type\": \"wait\",\n        \"milliseconds\": 2\n      }\n    ],\n    \"location\": {\n      \"country\": \"US\",\n      \"languages\": [\n        \"en-US\"\n      ]\n    },\n    \"removeBase64Images\": true,\n    \"blockAds\": true,\n    \"proxy\": \"auto\",\n    \"storeInCache\": true,\n    \"lockdown\": false,\n    \"redactPII\": false,\n    \"threatProtection\": {\n      \"riskScoreThreshold\": 75,\n      \"blacklist\": [\n        \"<string>\"\n      ],\n      \"whitelist\": [\n        \"<string>\"\n      ],\n      \"blockedTlds\": [\n        \"<string>\"\n      ]\n    }\n  },\n  \"ignoreInvalidURLs\": true,\n  \"threatProtection\": {\n    \"riskScoreThreshold\": 75,\n    \"blacklist\": [\n      \"<string>\"\n    ],\n    \"whitelist\": [\n      \"<string>\"\n    ],\n    \"blockedTlds\": [\n      \"<string>\"\n    ]\n  }\n}"

response = http.request(request)
puts response.read_body
{
  "success": true,
  "id": "<string>",
  "invalidURLs": [
    "<string>"
  ]
}
{
  "error": "Invalid input data."
}
{
  "error": "An unexpected error occurred on the server."
}
Are you an AI agent that needs a Firecrawl API key? See firecrawl.dev/agent-onboarding/SKILL.md for automated onboarding instructions.

Authorizations

​
Authorization
string
header
required

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

Body

application/json
​
urls
string<uri>[]
required

The URLs to extract data from. URLs should be in glob format.

​
prompt
string

Prompt to guide the extraction process

​
schema
object

Schema to define the structure of the extracted data. Must conform to JSON Schema.

​
enableWebSearch
boolean
default:false

When true, the extraction will use web search to find additional data

​
ignoreSitemap
boolean
default:false

When true, sitemap.xml files will be ignored during website scanning

​
includeSubdomains
boolean
default:true

When true, subdomains of the provided URLs will also be scanned

​
showSources
boolean
default:false

When true, the sources used to extract the data will be included in the response as sources key

​
scrapeOptions
object
​
ignoreInvalidURLs
boolean
default:true

If invalid URLs are specified in the urls array, they will be ignored. Instead of them failing the entire request, an extract using the remaining valid URLs will be performed, and the invalid URLs will be returned in the invalidURLs field of the response.

​
threatProtection
Threat Protection Override · object

Per-request Threat Protection override. Fields you provide replace the corresponding fields of your organization's policy for this request only; omitted fields keep their organization-level values. Requires Threat Protection to be enabled for your team (enterprise feature) — otherwise the request is rejected with a 403. If your organization has disabled request overrides, any request that includes this object is rejected with a 403. If Threat Protection is enforced for your team, mode may not be set to off.

Response

Successful extraction

​
success
boolean
​
id
string
​
invalidURLs
string[] | null

If ignoreInvalidURLs is true, this is an array containing the invalid URLs that were specified in the request. If there were no invalid URLs, this will be an empty array. If ignoreInvalidURLs is false, this field will be undefined.