解析 - Firecrawl Docs

上传并解析文件

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

上传并解析文件

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
}

上传本地或非公开文档，并将其转换为整洁、可供 LLM 使用的数据。/parse 通过 multipart/form-data 接收文件二进制内容，并返回 Markdown、JSON、HTML、链接、图像或摘要——同时保留阅读顺序和表格。

将 PDF、DOCX、XLSX、HTML 等转换为 Markdown 或结构化 JSON
借助基于 Rust 的引擎，解析速度最高可提升 5 倍
单次请求最多支持 50 MB 的文件
支持零数据保留

何时使用 `/parse`

当源文档是本地文件或无法通过公开 URL 访问时，请使用 /parse。如果你有一个指向文档的公开 URL，建议优先使用 /scrape——它会根据扩展名或内容类型自动识别文件类型，并以相同方式解析。

来源	端点
指向文档的公开 URL (例如 `https://example.com/report.pdf`)	`POST /scrape`
本地文件或非公开字节流 (PDF、DOCX、XLSX、HTML 等)	`POST /parse` (此端点)

通过 MCP 使用 Firecrawl？ 对于本地文件，请使用 firecrawl_parse。配置了 FIRECRAWL_API_URL 时，本地 MCP 可以直接读取文件。远程托管的 MCP 会先返回一个短期有效的上传命令，然后再解析返回的 uploadRef。公开文档 URL 仍应使用 /scrape。

授权

Authorization

string

header

必填

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

请求体

multipart/form-data

file

必填

要解析的文件字节。支持的扩展名：.html、.htm、.pdf、.docx、.doc、.odt、.rtf、.xlsx、.xls。

options

object

可选的解析选项，以 JSON 形式通过 multipart 的 options 字段传递。

Show child attributes

响应

成功响应

data

object

Show child attributes

success

boolean

Map（映射）

抓取

使用 API

搜索端点

抓取端点

交互端点

研究索引端点

映射端点

解析端点

爬取端点

监控端点

反馈端点

Agentic Debugging 端点

账户端点

Webhook 载荷

合作伙伴集成

解析

何时使用 `/parse`

授权

请求体

响应

​何时使用 /parse

授权

请求体

响应

何时使用 `/parse`