Envie e analise um arquivo
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,
"checkPromptInjection": false,
"excludeTags": [
"<string>"
],
"formats": [
{
"type": "markdown"
}
],
"headers": {},
"includeTags": [
"<string>"
],
"integration": "<string>",
"onlyMainContent": true,
"origin": "api",
"parsers": [
{
"type": "pdf"
}
],
"redactPII": false,
"removeBase64Images": true,
"skipTlsVerification": true,
"timeout": 30000,
"zeroDataRetention": false
};type=application/json'import requests
url = "https://api.firecrawl.dev/v2/parse"
files = { "file": ("example-file", open("example-file", "rb")) }
files["options"] = (None, "{\n \"blockAds\": true,\n \"checkPromptInjection\": false,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n {\n \"type\": \"markdown\"\n }\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"integration\": \"<string>\",\n \"onlyMainContent\": true,\n \"origin\": \"api\",\n \"parsers\": [\n {\n \"type\": \"pdf\"\n }\n ],\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"timeout\": 30000,\n \"zeroDataRetention\": false\n}", "application/json")
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('options', '{
"blockAds": true,
"checkPromptInjection": false,
"excludeTags": [
"<string>"
],
"formats": [
{
"type": "markdown"
}
],
"headers": {},
"includeTags": [
"<string>"
],
"integration": "<string>",
"onlyMainContent": true,
"origin": "api",
"parsers": [
{
"type": "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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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>",
"attributes": [
{
"attribute": "<string>",
"selector": "<string>",
"values": [
"<string>"
]
}
],
"audio": "<string>",
"blocks": [
{
"height": 123,
"items": [
{
"bbox": [
123
],
"confidence": {
"layout": 123,
"ocr": 123
},
"content": "<string>",
"id": "<string>",
"label": "<string>",
"markdownSpan": [
123
],
"readingOrder": 123,
"source": "<string>",
"type": "<string>"
}
],
"pageNumber": 123,
"status": "<string>",
"width": 123
}
],
"branding": {
"animations": {},
"colorScheme": "light",
"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": {
"changeStatus": "new",
"diff": "<string>",
"json": {},
"previousScrapeAt": "2023-11-07T05:31:56Z",
"visibility": "visible"
},
"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>"
],
"provider": {
"creditsCost": 123,
"id": "<string>",
"steps": [
{
"creditsCost": 123,
"provider": "<string>",
"status": "matched"
}
]
},
"sourceURL": "<string>",
"statusCode": 123,
"title": "<string>",
"totalPages": 123,
"url": "<string>"
},
"pages": [
{
"markdown": "<string>",
"pageNumber": 123
}
],
"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>"
},
"rawBase64": "<string>",
"rawHtml": "<string>",
"screenshot": "<string>",
"summary": "<string>",
"tools": [
{
"capability": "<string>",
"description": "<string>",
"provider": "<string>",
"creditsCost": 1,
"id": "<string>",
"matchedBy": [
"semantic"
],
"matchedUrls": [
"<string>"
],
"name": "<string>",
"options": [
{
"name": "<string>",
"type": "<string>"
}
],
"perRecord": true,
"response": {
"about": "<string>",
"fields": [
{}
],
"key": "<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
}Endpoints de Parse
Parse
POST
/
parse
Envie e analise um arquivo
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,
"checkPromptInjection": false,
"excludeTags": [
"<string>"
],
"formats": [
{
"type": "markdown"
}
],
"headers": {},
"includeTags": [
"<string>"
],
"integration": "<string>",
"onlyMainContent": true,
"origin": "api",
"parsers": [
{
"type": "pdf"
}
],
"redactPII": false,
"removeBase64Images": true,
"skipTlsVerification": true,
"timeout": 30000,
"zeroDataRetention": false
};type=application/json'import requests
url = "https://api.firecrawl.dev/v2/parse"
files = { "file": ("example-file", open("example-file", "rb")) }
files["options"] = (None, "{\n \"blockAds\": true,\n \"checkPromptInjection\": false,\n \"excludeTags\": [\n \"<string>\"\n ],\n \"formats\": [\n {\n \"type\": \"markdown\"\n }\n ],\n \"headers\": {},\n \"includeTags\": [\n \"<string>\"\n ],\n \"integration\": \"<string>\",\n \"onlyMainContent\": true,\n \"origin\": \"api\",\n \"parsers\": [\n {\n \"type\": \"pdf\"\n }\n ],\n \"redactPII\": false,\n \"removeBase64Images\": true,\n \"skipTlsVerification\": true,\n \"timeout\": 30000,\n \"zeroDataRetention\": false\n}", "application/json")
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('options', '{
"blockAds": true,
"checkPromptInjection": false,
"excludeTags": [
"<string>"
],
"formats": [
{
"type": "markdown"
}
],
"headers": {},
"includeTags": [
"<string>"
],
"integration": "<string>",
"onlyMainContent": true,
"origin": "api",
"parsers": [
{
"type": "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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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\nContent-Type: application/json\r\n\r\n{\r\n \"blockAds\": true,\r\n \"checkPromptInjection\": false,\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"formats\": [\r\n {\r\n \"type\": \"markdown\"\r\n }\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 {\r\n \"type\": \"pdf\"\r\n }\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>",
"attributes": [
{
"attribute": "<string>",
"selector": "<string>",
"values": [
"<string>"
]
}
],
"audio": "<string>",
"blocks": [
{
"height": 123,
"items": [
{
"bbox": [
123
],
"confidence": {
"layout": 123,
"ocr": 123
},
"content": "<string>",
"id": "<string>",
"label": "<string>",
"markdownSpan": [
123
],
"readingOrder": 123,
"source": "<string>",
"type": "<string>"
}
],
"pageNumber": 123,
"status": "<string>",
"width": 123
}
],
"branding": {
"animations": {},
"colorScheme": "light",
"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": {
"changeStatus": "new",
"diff": "<string>",
"json": {},
"previousScrapeAt": "2023-11-07T05:31:56Z",
"visibility": "visible"
},
"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>"
],
"provider": {
"creditsCost": 123,
"id": "<string>",
"steps": [
{
"creditsCost": 123,
"provider": "<string>",
"status": "matched"
}
]
},
"sourceURL": "<string>",
"statusCode": 123,
"title": "<string>",
"totalPages": 123,
"url": "<string>"
},
"pages": [
{
"markdown": "<string>",
"pageNumber": 123
}
],
"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>"
},
"rawBase64": "<string>",
"rawHtml": "<string>",
"screenshot": "<string>",
"summary": "<string>",
"tools": [
{
"capability": "<string>",
"description": "<string>",
"provider": "<string>",
"creditsCost": 1,
"id": "<string>",
"matchedBy": [
"semantic"
],
"matchedUrls": [
"<string>"
],
"name": "<string>",
"options": [
{
"name": "<string>",
"type": "<string>"
}
],
"perRecord": true,
"response": {
"about": "<string>",
"fields": [
{}
],
"key": "<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
}Envie um documento local ou não público e converta-o em contexto limpo, pronto para LLM. O Quando usar
Use
/parse aceita os bytes do arquivo via multipart/form-data e retorna Markdown, JSON, HTML, links, imagens ou um resumo — com a ordem de leitura e as tabelas preservadas.
- Converta PDF, Word, Excel, PowerPoint, OpenDocument, EPUB, CSV, HTML e outros formatos em Markdown ou JSON estruturado
- Análise até 5x mais rápida com um mecanismo baseado em Rust
- Arquivos de até 50 MB por solicitação
- Suporte a Zero Data Retention
Quando usar /parse
Use /parse quando o documento de origem for um arquivo local ou não estiver acessível publicamente por URL. Se você tiver uma URL pública que aponte para um documento, prefira /scrape — ele detecta automaticamente o tipo de arquivo pela extensão ou pelo tipo de conteúdo e faz o parsing da mesma forma.
| Origem | Endpoint |
|---|---|
URL pública para um documento (por exemplo, https://example.com/report.pdf) | POST /scrape |
| Arquivo local ou bytes não públicos (PDF, DOCX, XLSX, HTML, …) | POST /parse (este endpoint) |
Usando o Firecrawl via MCP? Use
firecrawl_parse para arquivos locais. O MCP local pode ler o arquivo diretamente quando configurado com FIRECRAWL_API_URL. O MCP remoto hospedado primeiro retorna um comando de upload temporário e, em seguida, faz o parsing do uploadRef retornado. URLs públicas de documentos ainda devem usar /scrape.Autorizações
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Corpo
multipart/form-data
Os bytes do arquivo a serem analisados. Extensões compatíveis: .html, .htm, .xhtml, .pdf, .docx, .doc, .docm, .odt, .ods, .odp, .rtf, .xlsx, .xls, .xlsm, .xlsb, .pptx, .ppt, .pptm, .epub, .csv.
Opções opcionais de análise enviadas como JSON no campo multipart options.
Show child attributes
Show child attributes