Link Search Menu Expand Document
PDF.co API

PDF Split

Split PDF into multiple PDF files.

Available methods

[POST] /pdf/split (split by page index)

  • url required. URL to the source file. Supports links from Google Drive, Dropbox and from built-in PDF.co files storage. For uploading files via API please check Files Upload section. If you are randomly getting Too Many Requests or Access Denied error for your input url, please try to add cache: to enable built-in url caching.
  • pages (optional, default is all pages) - comma-separated indices of pages (or page ranges) that you want to use. The first page indice is always 1. For example, if you have a 7 page document that you want split into 3 separate PDFs but different number of pages it would go like this: 1, 2, 3- or 1, 2, 3-7 which will result in 1 PDF with page one, 1 PDF with page two and one PDF with the rest of the pages. You can also use inverted page numbers adding ‘!’ before the number. E.g. “!1” means “the last page”, “2-!2” means “from the second to the penultimate page”, “!2-“ - last two pages”. Also, you can use a single asterisk (“*”) character as the range to split the document into separate pages. SPECIAL CASES: You can use a single asterisk * symbol to split the document into separate pages. Parameter must be a String.
  • encrypt optional. Enable encryption for output file. Must be one of: true, false.
  • async optional. Runs processing asynchronously. Returns Use JobId that you may use with /job/check to check state of the processing (possible states: working, failed, aborted and success). Must be one of: true, false.
  • name optional. name of the output file.
  • profiles optional. Must be a String. You can set additional and extra options using this parameter that allows you to set custom configuration. See profiles samples for examples.

Description

  • Method: POST
  • URL: /v1/pdf/split

Query parameters

No query parameters accepted.

Body payload

{
    "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
    "pages": "1-2,3-",
    "name": "result.pdf"
}

Example responses

/pdf/split
{
    "urls": [
        "https://pdf-temp-files.s3.amazonaws.com/1e9a7f2c46834160903276716424382b/result_page1-2.pdf",
        "https://pdf-temp-files.s3.amazonaws.com/c976b9f89a2e460786a3d5c0deeeef67/result_page3-4.pdf"
    ],
    "pageCount": 4,
    "error": false,
    "status": 200,
    "name": "result.pdf",
    "remainingCredits": 98441
}

Code Snippets

CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/split' \
--header 'Content-Type: application/json' \
--header 'x-api-key: ' \
--data-raw '{
    "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
    "pages": "1-2,3-",
    "name": "result.pdf"
}'
JavaScript
var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");
myHeaders.append("x-api-key", "");

var raw = JSON.stringify({
 "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
 "pages": "1-2,3-",
 "name": "result.pdf"
});

var requestOptions = {
	method: 'POST',
	headers: myHeaders,
	body: raw,
	redirect: 'follow'
};

fetch("https://api.pdf.co/v1/pdf/split", requestOptions)
	.then(response => response.text())
	.then(result => console.log(result))
	.catch(error => console.log('error', error));
NodeJs
var request = require('request');
var options = {
	'method': 'POST',
	'url': 'https://api.pdf.co/v1/pdf/split',
	'headers': {
		'Content-Type': 'application/json',
		'x-api-key': ''
	},
	body: JSON.stringify({
	 "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
	 "pages": "1-2,3-",
	 "name": "result.pdf"
	})

};
request(options, function (error, response) {
	if (error) throw new Error(error);
	console.log(response.body);
});
PHP
<?php

$curl = curl_init();

curl_setopt_array($curl, array(
	CURLOPT_URL => 'https://api.pdf.co/v1/pdf/split',
	CURLOPT_RETURNTRANSFER => true,
	CURLOPT_ENCODING => '',
	CURLOPT_MAXREDIRS => 10,
	CURLOPT_TIMEOUT => 0,
	CURLOPT_FOLLOWLOCATION => true,
	CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
	CURLOPT_CUSTOMREQUEST => 'POST',
	CURLOPT_POSTFIELDS =>'{
    "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
    "pages": "1-2,3-",
    "name": "result.pdf"
}',
	CURLOPT_HTTPHEADER => array(
		'Content-Type: application/json',
		'x-api-key: '
	),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;
Java
import java.io.*;
import okhttp3.*;
public class main {
	public static void main(String []args) throws IOException{
		OkHttpClient client = new OkHttpClient().newBuilder()
			.build();
		MediaType mediaType = MediaType.parse("application/json");
		RequestBody body = RequestBody.create(mediaType, "{\n    \"url\": \"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf\",\n    \"pages\": \"1-2,3-\",\n    \"name\": \"result.pdf\"\n}");
		Request request = new Request.Builder()
			.url("https://api.pdf.co/v1/pdf/split")
			.method("POST", body)
			.addHeader("Content-Type", "application/json")
			.addHeader("x-api-key", "")
			.build();
		Response response = client.newCall(request).execute();
		System.out.println(response.body().string());
	}
}
C#
using System;
using RestSharp;
namespace HelloWorldApplication {
	class HelloWorld {
		static void Main(string[] args) {
			var client = new RestClient("https://api.pdf.co/v1/pdf/split");
			client.Timeout = -1;
			var request = new RestRequest(Method.POST);
			request.AddHeader("Content-Type", "application/json");
			request.AddHeader("x-api-key", "");
			var body = @"{" + "\n" +
			@"    ""url"": ""https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf""," + "\n" +
			@"    ""pages"": ""1-2,3-""," + "\n" +
			@"    ""name"": ""result.pdf""" + "\n" +
			@"}";
			request.AddParameter("application/json", body,  ParameterType.RequestBody);
			IRestResponse response = client.Execute(request);
			Console.WriteLine(response.Content);
		}
	}
}
Python
import requests
import json

url = "https://api.pdf.co/v1/pdf/split"

payload = json.dumps({
 "url": "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf",
 "pages": "1-2,3-",
 "name": "result.pdf"
})
headers = {
	'Content-Type': 'application/json',
	'x-api-key': ''
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)
Powershell
$headers = New-Object "System.Collections.Generic.Dictionary[[String],[String]]"
$headers.Add("Content-Type", "application/json")
$headers.Add("x-api-key", "")

$body = "{`n    `"url`": `"https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-split/sample.pdf`",`n    `"pages`": `"1-2,3-`",`n    `"name`": `"result.pdf`"`n}"

$response = Invoke-RestMethod 'https://api.pdf.co/v1/pdf/split' -Method 'POST' -Headers $headers -Body $body
$response | ConvertTo-Json

[POST] /pdf/split2 (split by text search)

  • url required. URL to the source file. Supports links from Google Drive, Dropbox and from built-in PDF.co files storage. For uploading files via API please check Files Upload section. If you are randomly getting Too Many Requests or Access Denied error for your input url, please try to add cache: to enable built-in url caching.
  • searchString (required). Text to search for on pages. Must be a String.
  • excludeKeyPages (optional). Set to true if you want to exclude pages where text was found. false by default.
  • regexSearch (optional). Set to true to enable regular expressions for search string. false by default.
  • caseSensitive (optional). Set to true to enable case sensitive search. false by default.
  • lang optional. eng by default. Sets OCR (image to text extraction) language to be used for scanned PDF when scanned document is detected or input is PNG, JPG images. Default is eng. Supported values: eng, spa, deu, fra, jpn, chi_sim, chi_tra, kor. You can also specify two languages to be used on the same page, for example: eng+deu, jpn+kor or other combinations. For more languages please contact our customer support.
  • encrypt optional. Enable encryption for output file. Must be one of: true, false.
  • async optional. Runs processing asynchronously. Returns Use JobId that you may use with /job/check to check state of the processing (possible states: working, failed, aborted and success). Must be one of: true, false.
  • name optional. name of the output file.
  • profiles optional. Must be a String. You can set additional and extra options using this parameter that allows you to set custom configuration. See profiles samples for examples.

Description

  • Method: POST
  • URL: /v1/pdf/split2

Query parameters

No query parameters accepted.

Body payload

{
    "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
    "searchString": "invoice number",
    "excludeKeyPages": false,
    "regexSearch": false,
    "caseSensitive": false,
    "name": "invoice-extracted"
}

Example responses

/pdf/split2
{
    "urls": [
        "https://pdf-temp-files.s3.amazonaws.com/1e9a7f2c46834160903276716424382b/invoice-extracted_page1.pdf",
        "https://pdf-temp-files.s3.amazonaws.com/c976b9f89a2e460786a3d5c0deeeef67/invoice-extracted_page2.pdf",
        "https://pdf-temp-files.s3.amazonaws.com/c976b9f89a2e460786a3d5c0deeeef67/invoice-extracted_page3.pdf"
    ],
    "pageCount": 3,
    "error": false,
    "status": 200,
    "name": "invoice-extracted.pdf",
    "remainingCredits": 98441
}

Code Snippets

CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/split2' \
--header 'Content-Type: application/json' \
--header 'x-api-key: ' \
--data-raw '{
    "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
    "searchString": "invoice number",
    "excludeKeyPages": false,
    "regexSearch": false,
    "caseSensitive": false,
    "name": "invoice-extracted"
}'
JavaScript
var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");
myHeaders.append("x-api-key", "");

var raw = JSON.stringify({
 "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
 "searchString": "invoice number",
 "excludeKeyPages": false,
 "regexSearch": false,
 "caseSensitive": false,
 "name": "invoice-extracted"
});

var requestOptions = {
	method: 'POST',
	headers: myHeaders,
	body: raw,
	redirect: 'follow'
};

fetch("https://api.pdf.co/v1/pdf/split2", requestOptions)
	.then(response => response.text())
	.then(result => console.log(result))
	.catch(error => console.log('error', error));
NodeJs
var request = require('request');
var options = {
	'method': 'POST',
	'url': 'https://api.pdf.co/v1/pdf/split2',
	'headers': {
		'Content-Type': 'application/json',
		'x-api-key': ''
	},
	body: JSON.stringify({
	 "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
	 "searchString": "invoice number",
	 "excludeKeyPages": false,
	 "regexSearch": false,
	 "caseSensitive": false,
	 "name": "invoice-extracted"
	})

};
request(options, function (error, response) {
	if (error) throw new Error(error);
	console.log(response.body);
});
PHP
<?php

$curl = curl_init();

curl_setopt_array($curl, array(
	CURLOPT_URL => 'https://api.pdf.co/v1/pdf/split2',
	CURLOPT_RETURNTRANSFER => true,
	CURLOPT_ENCODING => '',
	CURLOPT_MAXREDIRS => 10,
	CURLOPT_TIMEOUT => 0,
	CURLOPT_FOLLOWLOCATION => true,
	CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
	CURLOPT_CUSTOMREQUEST => 'POST',
	CURLOPT_POSTFIELDS =>'{
    "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
    "searchString": "invoice number",
    "excludeKeyPages": false,
    "regexSearch": false,
    "caseSensitive": false,
    "name": "invoice-extracted"
}',
	CURLOPT_HTTPHEADER => array(
		'Content-Type: application/json',
		'x-api-key: '
	),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;
Java
import java.io.*;
import okhttp3.*;
public class main {
	public static void main(String []args) throws IOException{
		OkHttpClient client = new OkHttpClient().newBuilder()
			.build();
		MediaType mediaType = MediaType.parse("application/json");
		RequestBody body = RequestBody.create(mediaType, "{\n    \"url\": \"https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf\",\n    \"searchString\": \"invoice number\",\n    \"excludeKeyPages\": false,\n    \"regexSearch\": false,\n    \"caseSensitive\": false,\n    \"name\": \"invoice-extracted\"\n}");
		Request request = new Request.Builder()
			.url("https://api.pdf.co/v1/pdf/split2")
			.method("POST", body)
			.addHeader("Content-Type", "application/json")
			.addHeader("x-api-key", "")
			.build();
		Response response = client.newCall(request).execute();
		System.out.println(response.body().string());
	}
}
C#
using System;
using RestSharp;
namespace HelloWorldApplication {
	class HelloWorld {
		static void Main(string[] args) {
			var client = new RestClient("https://api.pdf.co/v1/pdf/split2");
			client.Timeout = -1;
			var request = new RestRequest(Method.POST);
			request.AddHeader("Content-Type", "application/json");
			request.AddHeader("x-api-key", "");
			var body = @"{" + "\n" +
			@"    ""url"": ""https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf""," + "\n" +
			@"    ""searchString"": ""invoice number""," + "\n" +
			@"    ""excludeKeyPages"": false," + "\n" +
			@"    ""regexSearch"": false," + "\n" +
			@"    ""caseSensitive"": false," + "\n" +
			@"    ""name"": ""invoice-extracted""" + "\n" +
			@"}";
			request.AddParameter("application/json", body,  ParameterType.RequestBody);
			IRestResponse response = client.Execute(request);
			Console.WriteLine(response.Content);
		}
	}
}
Python
import requests
import json

url = "https://api.pdf.co/v1/pdf/split2"

payload = json.dumps({
 "url": "https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf",
 "searchString": "invoice number",
 "excludeKeyPages": False,
 "regexSearch": False,
 "caseSensitive": False,
 "name": "invoice-extracted"
})
headers = {
	'Content-Type': 'application/json',
	'x-api-key': ''
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)
Powershell
$headers = New-Object "System.Collections.Generic.Dictionary[[String],[String]]"
$headers.Add("Content-Type", "application/json")
$headers.Add("x-api-key", "")

$body = "{`n    `"url`": `"https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/pdf-split/multiple-invoices.pdf`",`n    `"searchString`": `"invoice number`",`n    `"excludeKeyPages`": false,`n    `"regexSearch`": false,`n    `"caseSensitive`": false,`n    `"name`": `"invoice-extracted`"`n}"

$response = Invoke-RestMethod 'https://api.pdf.co/v1/pdf/split2' -Method 'POST' -Headers $headers -Body $body
$response | ConvertTo-Json