Extrair

Extraia dados estruturados de páginas da web usando LLMs

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

import requests

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

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

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

{
  "id": "<string>",
  "invalidURLs": [
    "<string>"
  ],
  "success": true
}

{
  "error": "Invalid input data."
}

{
  "error": "An unexpected error occurred on the server."
}

POST

extract

Extraia dados estruturados de páginas da web usando LLMs

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

import requests

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

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

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

{
  "id": "<string>",
  "invalidURLs": [
    "<string>"
  ],
  "success": true
}

{
  "error": "Invalid input data."
}

{
  "error": "An unexpected error occurred on the server."
}

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

Autorizações

Authorization

string

header

obrigatório

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

Corpo

application/json

urls

string<uri>[]

obrigatório

As URLs das quais os dados serão extraídos. As URLs devem estar no formato glob.

enableWebSearch

boolean

padrão:false

Quando definido como true, a extração usará busca na web para encontrar dados adicionais

ignoreInvalidURLs

boolean

padrão:true

Se URLs inválidas forem especificadas no array urls, elas serão ignoradas. Em vez de fazer com que a requisição inteira falhe, será feita uma extração usando as URLs válidas restantes, e as URLs inválidas serão retornadas no campo invalidURLs da resposta.

ignoreSitemap

boolean

padrão:false

Quando definido como true, arquivos sitemap.xml serão ignorados durante a varredura do site

includeSubdomains

boolean

padrão:true

Quando definido como true, os subdomínios das URLs fornecidas também serão rastreados

prompt

string

Prompt para guiar o processo de extração

schema

object

Esquema que define a estrutura dos dados extraídos. Deve estar em conformidade com o JSON Schema.

scrapeOptions

object

Show child attributes

showSources

boolean

padrão:false

Quando definido como true, as fontes usadas para extrair os dados serão incluídas na resposta sob a chave sources

threatProtection

Threat Protection Override · object

Substituição por solicitação da Proteção contra ameaças. Os campos fornecidos substituem os campos correspondentes da política da sua organização apenas nesta solicitação; os campos omitidos mantêm os valores definidos no nível da organização. Exige que a Proteção contra ameaças esteja habilitada para sua equipe (recurso enterprise) — caso contrário, a solicitação será rejeitada com 403. Se sua organização tiver desativado substituições por solicitação, qualquer solicitação que inclua este objeto será rejeitada com 403. Se a Proteção contra ameaças for imposta à sua equipe, mode não poderá ser definido como off.

Show child attributes

Resposta

Extração bem-sucedida

string

invalidURLs

string[] | null

Se ignoreInvalidURLs for true, este será um array contendo as URLs inválidas especificadas na requisição. Se não houver URLs inválidas, será um array vazio. Se ignoreInvalidURLs for false, este campo será undefined.

success

boolean

Usando a API

Endpoints de busca

Endpoints de scraping

Endpoints de interação

Endpoints do Research Index

Endpoints de mapeamento

Endpoints de processamento

Endpoints de rastreamento

Endpoints de monitoramento

Endpoints de feedback

Endpoints de depuração agêntica

Endpoints da conta

Payloads de webhook

Integração de parceiro

Autorizações

Corpo

Resposta