Procesar

Sube y procesa un archivo

curl --request POST \
  --url https://api.firecrawl.dev/v2/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'options={
  "blockAds": true,
  "excludeTags": [
    "<string>"
  ],
  "formats": [
    "markdown"
  ],
  "headers": {},
  "includeTags": [
    "<string>"
  ],
  "integration": "<string>",
  "onlyMainContent": true,
  "origin": "api",
  "parsers": [
    "pdf"
  ],
  "redactPII": false,
  "removeBase64Images": true,
  "skipTlsVerification": true,
  "timeout": 30000,
  "zeroDataRetention": false
}'

import requests

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

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "options": "{
  \"blockAds\": true,
  \"excludeTags\": [
    \"<string>\"
  ],
  \"formats\": [
    \"markdown\"
  ],
  \"headers\": {},
  \"includeTags\": [
    \"<string>\"
  ],
  \"integration\": \"<string>\",
  \"onlyMainContent\": true,
  \"origin\": \"api\",
  \"parsers\": [
    \"pdf\"
  ],
  \"redactPII\": false,
  \"removeBase64Images\": true,
  \"skipTlsVerification\": true,
  \"timeout\": 30000,
  \"zeroDataRetention\": false
}" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('options', '{
  "blockAds": true,
  "excludeTags": [
    "<string>"
  ],
  "formats": [
    "markdown"
  ],
  "headers": {},
  "includeTags": [
    "<string>"
  ],
  "integration": "<string>",
  "onlyMainContent": true,
  "origin": "api",
  "parsers": [
    "pdf"
  ],
  "redactPII": false,
  "removeBase64Images": true,
  "skipTlsVerification": true,
  "timeout": 30000,
  "zeroDataRetention": false
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.firecrawl.dev/v2/parse', 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/parse",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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/parse"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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/parse")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--"

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

{
  "data": {
    "actions": {
      "javascriptReturns": [
        {
          "type": "<string>",
          "value": "<unknown>"
        }
      ],
      "pdfs": [
        "<string>"
      ],
      "scrapes": [
        {
          "html": "<string>",
          "url": "<string>"
        }
      ],
      "screenshots": [
        "<string>"
      ]
    },
    "answer": "<string>",
    "audio": "<string>",
    "branding": {
      "animations": {},
      "colors": {
        "accent": "<string>",
        "background": "<string>",
        "error": "<string>",
        "link": "<string>",
        "primary": "<string>",
        "secondary": "<string>",
        "success": "<string>",
        "textPrimary": "<string>",
        "textSecondary": "<string>",
        "warning": "<string>"
      },
      "components": {
        "buttonPrimary": {
          "background": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "buttonSecondary": {
          "background": "<string>",
          "borderColor": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "input": {}
      },
      "fonts": [
        {
          "family": "<string>"
        }
      ],
      "icons": {},
      "images": {
        "favicon": "<string>",
        "logo": "<string>",
        "ogImage": "<string>"
      },
      "layout": {},
      "logo": "<string>",
      "personality": {},
      "spacing": {
        "baseUnit": 123,
        "borderRadius": "<string>",
        "margins": {},
        "padding": {}
      },
      "typography": {
        "fontFamilies": {
          "code": "<string>",
          "heading": "<string>",
          "primary": "<string>"
        },
        "fontSizes": {
          "body": "<string>",
          "h1": "<string>",
          "h2": "<string>",
          "h3": "<string>"
        },
        "fontWeights": {
          "bold": 123,
          "light": 123,
          "medium": 123,
          "regular": 123
        },
        "lineHeights": {
          "body": "<string>",
          "heading": "<string>"
        }
      }
    },
    "changeTracking": {
      "diff": "<string>",
      "json": {},
      "previousScrapeAt": "2023-11-07T05:31:56Z"
    },
    "highlights": "<string>",
    "html": "<string>",
    "links": [
      "<string>"
    ],
    "markdown": "<string>",
    "menu": {
      "isMenu": true,
      "sections": [
        {
          "items": [
            {
              "name": "<string>",
              "availability": {
                "inStock": true,
                "text": "<string>"
              },
              "calories": 123,
              "description": "<string>",
              "dietary": [
                "<string>"
              ],
              "id": "<string>",
              "identifiers": {
                "merchantItemId": "<string>"
              },
              "images": [
                {
                  "url": "<string>",
                  "alt": "<string>"
                }
              ],
              "optionGroups": [
                {}
              ],
              "price": {
                "amount": 123,
                "currency": "<string>",
                "formatted": "<string>"
              },
              "sourceUrl": "<string>",
              "url": "<string>"
            }
          ],
          "name": "<string>",
          "description": "<string>",
          "id": "<string>"
        }
      ],
      "confidence": 123,
      "currency": "<string>",
      "merchant": {
        "name": "<string>",
        "type": "<string>"
      },
      "sourceUrl": "<string>"
    },
    "metadata": {
      "<any other metadata> ": "<string>",
      "concurrencyLimited": true,
      "concurrencyQueueDurationMs": 123,
      "contentType": "<string>",
      "description": "<string>",
      "error": "<string>",
      "keywords": "<string>",
      "language": "<string>",
      "numPages": 123,
      "ogLocaleAlternate": [
        "<string>"
      ],
      "sourceURL": "<string>",
      "statusCode": 123,
      "title": "<string>",
      "totalPages": 123,
      "url": "<string>"
    },
    "product": {
      "title": "<string>",
      "url": "<string>",
      "variants": [
        {
          "availability": {
            "inStock": true,
            "text": "<string>"
          },
          "id": "<string>",
          "images": [
            {
              "url": "<string>",
              "alt": "<string>"
            }
          ],
          "price": {
            "amount": 123,
            "currency": "<string>",
            "formatted": "<string>"
          },
          "sale": {
            "originalPrice": {
              "amount": 123,
              "currency": "<string>",
              "formatted": "<string>"
            }
          },
          "sku": "<string>",
          "title": "<string>",
          "values": {}
        }
      ],
      "brand": "<string>",
      "category": "<string>",
      "description": "<string>"
    },
    "rawHtml": "<string>",
    "screenshot": "<string>",
    "summary": "<string>",
    "video": "<string>",
    "warning": "<string>"
  },
  "success": true
}

{
  "code": "BAD_REQUEST",
  "error": "Invalid multipart form-data request.",
  "success": false
}

{
  "error": "Payment required to access this resource."
}

{
  "error": "Request rate limit exceeded. Please wait and try again later."
}

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

POST

parse

Sube y procesa un archivo

curl --request POST \
  --url https://api.firecrawl.dev/v2/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'options={
  "blockAds": true,
  "excludeTags": [
    "<string>"
  ],
  "formats": [
    "markdown"
  ],
  "headers": {},
  "includeTags": [
    "<string>"
  ],
  "integration": "<string>",
  "onlyMainContent": true,
  "origin": "api",
  "parsers": [
    "pdf"
  ],
  "redactPII": false,
  "removeBase64Images": true,
  "skipTlsVerification": true,
  "timeout": 30000,
  "zeroDataRetention": false
}'

import requests

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

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "options": "{
  \"blockAds\": true,
  \"excludeTags\": [
    \"<string>\"
  ],
  \"formats\": [
    \"markdown\"
  ],
  \"headers\": {},
  \"includeTags\": [
    \"<string>\"
  ],
  \"integration\": \"<string>\",
  \"onlyMainContent\": true,
  \"origin\": \"api\",
  \"parsers\": [
    \"pdf\"
  ],
  \"redactPII\": false,
  \"removeBase64Images\": true,
  \"skipTlsVerification\": true,
  \"timeout\": 30000,
  \"zeroDataRetention\": false
}" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('options', '{
  "blockAds": true,
  "excludeTags": [
    "<string>"
  ],
  "formats": [
    "markdown"
  ],
  "headers": {},
  "includeTags": [
    "<string>"
  ],
  "integration": "<string>",
  "onlyMainContent": true,
  "origin": "api",
  "parsers": [
    "pdf"
  ],
  "redactPII": false,
  "removeBase64Images": true,
  "skipTlsVerification": true,
  "timeout": 30000,
  "zeroDataRetention": false
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.firecrawl.dev/v2/parse', 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/parse",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

$response = curl_exec($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/parse"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "Bearer <token>")

	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/parse")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n  \"blockAds\": true,\r\n  \"excludeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"formats\": [\r\n    \"markdown\"\r\n  ],\r\n  \"headers\": {},\r\n  \"includeTags\": [\r\n    \"<string>\"\r\n  ],\r\n  \"integration\": \"<string>\",\r\n  \"onlyMainContent\": true,\r\n  \"origin\": \"api\",\r\n  \"parsers\": [\r\n    \"pdf\"\r\n  ],\r\n  \"redactPII\": false,\r\n  \"removeBase64Images\": true,\r\n  \"skipTlsVerification\": true,\r\n  \"timeout\": 30000,\r\n  \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--"

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

{
  "data": {
    "actions": {
      "javascriptReturns": [
        {
          "type": "<string>",
          "value": "<unknown>"
        }
      ],
      "pdfs": [
        "<string>"
      ],
      "scrapes": [
        {
          "html": "<string>",
          "url": "<string>"
        }
      ],
      "screenshots": [
        "<string>"
      ]
    },
    "answer": "<string>",
    "audio": "<string>",
    "branding": {
      "animations": {},
      "colors": {
        "accent": "<string>",
        "background": "<string>",
        "error": "<string>",
        "link": "<string>",
        "primary": "<string>",
        "secondary": "<string>",
        "success": "<string>",
        "textPrimary": "<string>",
        "textSecondary": "<string>",
        "warning": "<string>"
      },
      "components": {
        "buttonPrimary": {
          "background": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "buttonSecondary": {
          "background": "<string>",
          "borderColor": "<string>",
          "borderRadius": "<string>",
          "textColor": "<string>"
        },
        "input": {}
      },
      "fonts": [
        {
          "family": "<string>"
        }
      ],
      "icons": {},
      "images": {
        "favicon": "<string>",
        "logo": "<string>",
        "ogImage": "<string>"
      },
      "layout": {},
      "logo": "<string>",
      "personality": {},
      "spacing": {
        "baseUnit": 123,
        "borderRadius": "<string>",
        "margins": {},
        "padding": {}
      },
      "typography": {
        "fontFamilies": {
          "code": "<string>",
          "heading": "<string>",
          "primary": "<string>"
        },
        "fontSizes": {
          "body": "<string>",
          "h1": "<string>",
          "h2": "<string>",
          "h3": "<string>"
        },
        "fontWeights": {
          "bold": 123,
          "light": 123,
          "medium": 123,
          "regular": 123
        },
        "lineHeights": {
          "body": "<string>",
          "heading": "<string>"
        }
      }
    },
    "changeTracking": {
      "diff": "<string>",
      "json": {},
      "previousScrapeAt": "2023-11-07T05:31:56Z"
    },
    "highlights": "<string>",
    "html": "<string>",
    "links": [
      "<string>"
    ],
    "markdown": "<string>",
    "menu": {
      "isMenu": true,
      "sections": [
        {
          "items": [
            {
              "name": "<string>",
              "availability": {
                "inStock": true,
                "text": "<string>"
              },
              "calories": 123,
              "description": "<string>",
              "dietary": [
                "<string>"
              ],
              "id": "<string>",
              "identifiers": {
                "merchantItemId": "<string>"
              },
              "images": [
                {
                  "url": "<string>",
                  "alt": "<string>"
                }
              ],
              "optionGroups": [
                {}
              ],
              "price": {
                "amount": 123,
                "currency": "<string>",
                "formatted": "<string>"
              },
              "sourceUrl": "<string>",
              "url": "<string>"
            }
          ],
          "name": "<string>",
          "description": "<string>",
          "id": "<string>"
        }
      ],
      "confidence": 123,
      "currency": "<string>",
      "merchant": {
        "name": "<string>",
        "type": "<string>"
      },
      "sourceUrl": "<string>"
    },
    "metadata": {
      "<any other metadata> ": "<string>",
      "concurrencyLimited": true,
      "concurrencyQueueDurationMs": 123,
      "contentType": "<string>",
      "description": "<string>",
      "error": "<string>",
      "keywords": "<string>",
      "language": "<string>",
      "numPages": 123,
      "ogLocaleAlternate": [
        "<string>"
      ],
      "sourceURL": "<string>",
      "statusCode": 123,
      "title": "<string>",
      "totalPages": 123,
      "url": "<string>"
    },
    "product": {
      "title": "<string>",
      "url": "<string>",
      "variants": [
        {
          "availability": {
            "inStock": true,
            "text": "<string>"
          },
          "id": "<string>",
          "images": [
            {
              "url": "<string>",
              "alt": "<string>"
            }
          ],
          "price": {
            "amount": 123,
            "currency": "<string>",
            "formatted": "<string>"
          },
          "sale": {
            "originalPrice": {
              "amount": 123,
              "currency": "<string>",
              "formatted": "<string>"
            }
          },
          "sku": "<string>",
          "title": "<string>",
          "values": {}
        }
      ],
      "brand": "<string>",
      "category": "<string>",
      "description": "<string>"
    },
    "rawHtml": "<string>",
    "screenshot": "<string>",
    "summary": "<string>",
    "video": "<string>",
    "warning": "<string>"
  },
  "success": true
}

{
  "code": "BAD_REQUEST",
  "error": "Invalid multipart form-data request.",
  "success": false
}

{
  "error": "Payment required to access this resource."
}

{
  "error": "Request rate limit exceeded. Please wait and try again later."
}

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

Sube un documento local o privado y conviértelo en datos limpios, listos para LLM. /parse acepta los bytes del archivo mediante multipart/form-data y devuelve Markdown, JSON, HTML, enlaces, imágenes o un resumen, conservando el orden de lectura y las tablas.

Convierte PDF, DOCX, XLSX, HTML y más en Markdown o JSON estructurado
Procesamiento hasta 5x más rápido con un motor basado en Rust
Archivos de hasta 50 MB por solicitud
Compatibilidad con retención de datos cero

Cuándo usar `/parse`

Usa /parse cuando el documento de origen sea un archivo local o no sea accesible públicamente mediante una URL. Si tienes una URL pública que apunta a un documento, es preferible usar /scrape: detecta automáticamente el tipo de archivo a partir de la extensión o del tipo de contenido y lo procesa de la misma forma.

Origen	Endpoint
URL pública de un documento (p. ej. `https://example.com/report.pdf`)	`POST /scrape`
Archivo local o bytes no públicos (PDF, DOCX, XLSX, HTML, …)	`POST /parse` (este endpoint)

¿Usas Firecrawl a través de MCP? Usa firecrawl_parse para archivos locales. El MCP local puede leer el archivo directamente cuando está configurado con FIRECRAWL_API_URL. El MCP remoto alojado primero devuelve un comando de carga temporal y luego procesa el uploadRef devuelto. Las URL públicas de documentos deben seguir usando /scrape.

Autorizaciones

Authorization

string

header

requerido

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

Cuerpo

multipart/form-data

file

requerido

Los bytes del archivo que se van a procesar. Extensiones compatibles: .html, .htm, .pdf, .docx, .doc, .odt, .rtf, .xlsx, .xls.

options

object

Opciones opcionales para procesar enviadas como JSON en el campo multipart options.

Show child attributes

Respuesta

Respuesta correcta

data

object

Show child attributes

success

boolean

Mapear

Crawl

Uso de la API

Endpoints de búsqueda

Endpoints de scraping

Endpoints de interacción

Endpoints de Research Index

Endpoints de mapeo

Endpoints de procesamiento

Endpoints de rastreo

Endpoints de supervisión

Endpoints de feedback

Endpoints de depuración con agentes

Endpoints de la cuenta

Cargas útiles de webhook

Integración de socios

Cuándo usar `/parse`

Autorizaciones

Cuerpo

Respuesta

​Cuándo usar /parse

Autorizaciones

Cuerpo

Respuesta

Cuándo usar `/parse`