Text Bounding Boxes

Extract Text Boxes from PDF

curl --request POST \
  --url https://api.gonitro.dev/extractions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form method=text-bounding-boxes \
  --form 'params={
  "queries": [
    {
      "text": "John Doe",
      "isRegex": false,
      "regexFlags": []
    }
  ]
}' \
  --form 'file=<string>'

import requests

url = "https://api.gonitro.dev/extractions"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('method', 'text-bounding-boxes');
form.append('params', '{
  "queries": [
    {
      "text": "John Doe",
      "isRegex": false,
      "regexFlags": []
    }
  ]
}');
form.append('file', '<string>');

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

options.body = form;

fetch('https://api.gonitro.dev/extractions', 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.gonitro.dev/extractions",
  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=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\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.gonitro.dev/extractions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\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.gonitro.dev/extractions")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.gonitro.dev/extractions")

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=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "result": {
    "textBoxes": [
      {
        "query": {
          "text": "John Doe",
          "isRegex": false,
          "regexFlags": [
            "ignore-case"
          ]
        },
        "matches": [
          {
            "matchedText": "Scope of Services",
            "boxes": [
              {
                "pageIndex": 123,
                "boundingBox": [
                  200,
                  100,
                  100,
                  20
                ],
                "textPiece": "<string>"
              }
            ],
            "groups": [
              {
                "index": 1,
                "text": "<string>",
                "boxes": [
                  {
                    "pageIndex": 123,
                    "boundingBox": [
                      200,
                      100,
                      100,
                      20
                    ],
                    "textPiece": "<string>"
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#400-bad-request",
  "title": "Bad Request",
  "status": 400,
  "detail": "Request validation failed",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#401-unauthorized",
  "title": "Unauthorized",
  "status": 401,
  "detail": "Missing or invalid Authorization header",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#404-not-found",
  "title": "Not Found",
  "status": 404,
  "detail": "Resource not found",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#413-content-too-large",
  "title": "Content too large",
  "status": 413,
  "detail": "Uploaded document exceeds the file size limit",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#422-unprocessable-entity",
  "title": "Unprocessable Entity",
  "status": 422,
  "detail": "The request was well-formed but could not be processed",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#500-internal-server-error",
  "title": "Internal Server Error",
  "status": 500,
  "detail": "An unexpected error occurred",
  "instance": "/platform/extractions"
}

POST

extractions

Extract Text Boxes from PDF

curl --request POST \
  --url https://api.gonitro.dev/extractions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form method=text-bounding-boxes \
  --form 'params={
  "queries": [
    {
      "text": "John Doe",
      "isRegex": false,
      "regexFlags": []
    }
  ]
}' \
  --form 'file=<string>'

import requests

url = "https://api.gonitro.dev/extractions"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('method', 'text-bounding-boxes');
form.append('params', '{
  "queries": [
    {
      "text": "John Doe",
      "isRegex": false,
      "regexFlags": []
    }
  ]
}');
form.append('file', '<string>');

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

options.body = form;

fetch('https://api.gonitro.dev/extractions', 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.gonitro.dev/extractions",
  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=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\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.gonitro.dev/extractions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\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.gonitro.dev/extractions")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.gonitro.dev/extractions")

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=\"method\"\r\n\r\ntext-bounding-boxes\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"params\"\r\n\r\n{\r\n  \"queries\": [\r\n    {\r\n      \"text\": \"John Doe\",\r\n      \"isRegex\": false,\r\n      \"regexFlags\": []\r\n    }\r\n  ]\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "result": {
    "textBoxes": [
      {
        "query": {
          "text": "John Doe",
          "isRegex": false,
          "regexFlags": [
            "ignore-case"
          ]
        },
        "matches": [
          {
            "matchedText": "Scope of Services",
            "boxes": [
              {
                "pageIndex": 123,
                "boundingBox": [
                  200,
                  100,
                  100,
                  20
                ],
                "textPiece": "<string>"
              }
            ],
            "groups": [
              {
                "index": 1,
                "text": "<string>",
                "boxes": [
                  {
                    "pageIndex": 123,
                    "boundingBox": [
                      200,
                      100,
                      100,
                      20
                    ],
                    "textPiece": "<string>"
                  }
                ]
              }
            ]
          }
        ]
      }
    ]
  }
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#400-bad-request",
  "title": "Bad Request",
  "status": 400,
  "detail": "Request validation failed",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#401-unauthorized",
  "title": "Unauthorized",
  "status": 401,
  "detail": "Missing or invalid Authorization header",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#404-not-found",
  "title": "Not Found",
  "status": 404,
  "detail": "Resource not found",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#413-content-too-large",
  "title": "Content too large",
  "status": 413,
  "detail": "Uploaded document exceeds the file size limit",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#422-unprocessable-entity",
  "title": "Unprocessable Entity",
  "status": 422,
  "detail": "The request was well-formed but could not be processed",
  "instance": "/platform/extractions"
}

{
  "type": "https://developers.gonitro.com/docs/build-nitro/errors#500-internal-server-error",
  "title": "Internal Server Error",
  "status": 500,
  "detail": "An unexpected error occurred",
  "instance": "/platform/extractions"
}

The Extract Text Bounding Boxes method of the Extractions endpoint lets you locate text in PDF files and retrieve its position on the page. It takes a list of queries as part of the queries parameter — each query is either literal text or a regular expression — and returns, for each query, the matches found in the PDF file along with their bounding boxes. It is useful to identify specific information in a document and identify locations for applying redactions. Each query accepts: text: The text or regular expression to search for. isRegex: Whether text should be treated as a regular expression. Defaults to false. regexFlags: Optional regex matching flags, only allowed when isRegex is true. Any combination of ignore-case, multiline and dot-all.

Matching is exact and case-sensitive. For case-insensitive matching, use a regex query with the ignore-case flag.

An invalid regular expression, or regexFlags on a non-regex query, is rejected with a 422 error explaining the problem.

The response contains, under textBoxes, one result per query in the same order as the request. Each result echoes the query and lists its matches: matchedText: The full matched text. boxes: The bounding boxes covering the match — one per line, so a match spanning multiple lines yields multiple boxes. Each box has a zero-based pageIndex, a boundingBox as an array of four values (check the Bounding Box Guide) and a textPiece with the text covered by that box. groups: For regex queries, the capture groups of the match, each with its one-based index, captured text and its own boxes.

Example

If you pass the parameters queries: [{"text": "token"}, {"text": "conversions"}] the method would identify the following boxes in the PDF file below:

Location of text boxes

To find every amount of money following the word “Total”, case-insensitively, you could pass:

{
  "queries": [
    { "text": "total:?\\s*\\$(\\d+(?:\\.\\d{2})?)", "isRegex": true, "regexFlags": ["ignore-case"] }
  ]
}

The amount itself is returned as capture group 1 of each match, with its own bounding boxes.

The method value extract-text-bounding-boxes still works for backwards compatibility, but is deprecated in favor of its new name, text-bounding-boxes.

Output File Format

The endpoint can return output either as JSON or as a binary file. The format depends on the Accept header (details below), which defaults to application/json.

Processing

When requesting JSON, you can run the operation synchronously or asynchronously. This is determined by the Prefer header (details below).

In sync mode, the response includes a URL pointing to the processed file.
In async mode, the request creates a Job, and the response contains the Job ID and status so you can track progress.

Binary (octet-stream) responses are only available for synchronous operations.

Custom File Delivery

The endpoint supports custom file-delivery destinations through the optional delivery parameter. You can provide an upload target, such as your own PUT endpoint or a pre-signed S3 URL, and Nitro will upload the resulting file there. This works for both synchronous and asynchronous processing.

Sync delivery
In synchronous calls, the delivery parameter lets you direct Nitro to upload the output file to a custom URL endpoint or a pre-signed URL (e.g S3), by providing an upload url in the uploadResultTo or uploadResultsTo properties.
Custom endpoint

If implementing the upload endpoint by yourself, make sure your code or middleware configuration accepts requests without content-type headers.

S3 delivery
If you are using S3 to manage delivery uploads, follow this AWS documentation to generate a pre-signed PUT URL.
If using the AWS provided Python script, omit the Content-Type in Params to get the pre-signed url. For example:
url = generate_presigned_url( s3_client, "put_object", { "Bucket": args.bucket, "Key": args.key, # Content-Type: "application/octet-stream" => Omit! }, 1000)
Async delivery
In asynchronous flows, you can also provide a custom URL or pre-signed S3 object via uploadResultTo or uploadResultsTo, to upload your file(s) once the Job is done processing.
Callback
For asynchronous processing, you can also include a callback URL within the delivery parameter. This callback is a POST endpoint that Nitro will call once the Job is created and running, providing details about the file-processing job. Example of Nitro’s callback request body:
{ "jobID": "babe2aa7-9b5d-4eb2-a679-5fc12cf0a490", "location": "https://api.gonitro.dev/jobs/babe2aa7-9b5d-4eb2-a679-5fc12cf0a490" }

Response behavior Matrix

This matrix shows the expected response behavior based on content type, sync/async mode, and custom file-delivery settings.

	JSON (`application/json`)	Binary (`application/octet-stream`)
Synchronous	Returns a JSON object with a file(s) URL(s).	Returns the processed file directly as binary.
Asynchronous (`respond-async`)	Returns a JSON object with a Job ID and status.	Async preference ignored, returns sync binary.
Synchronous delivery	File delivered to custom endpoint / Bucket, returns success confirmation.	N/A
Asynchronous delivery	Returns a JSON object with a Job ID and status. The file(s) will be uploaded to the provided PUT endpoint / S3 Bucket at the end of process. If `callback` url is provided, Nitro will notify the endpoint with a JOB ID and location.	N/A

Limits

The Platform API has the following limits:

File size: Maximum of 100 MB per request for direct uploads and synchronous requests; asynchronous requests with remote-file (URL) input allow up to 300 MB. This applies to single-file and multi-file requests (multi-file requests are limited by their combined size). Some operations allow more — Merge accepts up to 1.5 GB for asynchronous remote-file input.
Page count: Maximum of 500 pages per individual document, or 2500 pages for asynchronous requests with remote-file (URL) input. This applies to single-file and multi-file requests. Multiple documents may exceed the page limit in total.
Retention time: Inputs and outputs are deleted approximately 15 minutes after the operation completes.

Request

Authorizations

Authorization

string

header

required

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

Headers

enum<string>

default:*/*

Controls response format and behavior. See endpoint description above for detailed response combinations.

application/json: Returns JSON response with operation result
application/octet-stream: Returns binary file content
*/*: Defaults to JSON response

Available options:

application/json,

application/octet-stream,

*/*

Prefer

enum<string>

Controls synchronous vs asynchronous operation. See endpoint description above for behavior details.

respond-async: Makes request asynchronous, returns job status for polling
No value: Synchronous response

Available options:

respond-async

Body

multipart/form-data

method

enum<string>

default:text-bounding-boxes

required

The Extractions' endpoint method: text-bounding-boxes (previously extract-text-bounding-boxes, which still works during the transition)

Available options:

text-bounding-boxes,

extract-text-bounding-boxes

params

Text Box · object

required

Show child attributes

file

required

The file to process. It can be provided as a binary upload or as a JSON remote file reference.

delivery

object

This endpoint lets you supply your own URL to receive the single-file output. The URL may point to a custom API endpoint or a pre-signed S3 URL.

The HTTP method defaults to PUT, but you can change it based on your implementation needs via the verb parameter. You can also provide custom headers, such as authentication headers or any others required by your endpoint.

Show child attributes

Response

Returns either JSON or binary output depending on the Accept header (defaults to JSON). JSON responses include a file URL for synchronous tasks or a job status for asynchronous tasks.

Sync - Text Box
Async - Job

result

Text Boxes · object

required

Show child attributes

Start Here

PDF Services

Sign API

Reference

Example

Location of text boxes

Output File Format

Processing

Custom File Delivery

Sync delivery

Custom endpoint

S3 delivery

Async delivery

Callback

Response behavior Matrix

Limits

Request

Authorizations

Headers

Body

Response