Sample request
CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/convert/to/json2' \
--header 'Content-Type: application/json' \
--header 'x-api-key: *******************' \
--data-raw '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-json/sample.pdf",
"async": false
}'
var https = require("https");
var path = require("path");
var fs = require("fs");
// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";
// Source PDF file
const SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// Destination JSON file name
const DestinationFile = "./result.json";
// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
.then(([uploadUrl, uploadedFileUrl]) => {
// 2. UPLOAD THE FILE TO CLOUD.
uploadFile(API_KEY, SourceFile, uploadUrl)
.then(() => {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
})
.catch(e => {
console.log(e);
});
})
.catch(e => {
console.log(e);
});
function getPresignedUrl(apiKey, localFile) {
return new Promise(resolve => {
// Prepare request to `Get Presigned URL` API endpoint
let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
let reqOptions = {
host: "api.pdf.co",
path: encodeURI(queryPath),
headers: { "x-api-key": API_KEY }
};
// Send request
https.get(reqOptions, (response) => {
response.on("data", (d) => {
let data = JSON.parse(d);
if (data.error == false) {
// Return presigned url we received
resolve([data.presignedUrl, data.url]);
}
else {
// Service reported error
console.log("getPresignedUrl(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("getPresignedUrl(): " + e);
});
});
}
function uploadFile(apiKey, localFile, uploadUrl) {
return new Promise(resolve => {
fs.readFile(SourceFile, (err, data) => {
request({
method: "PUT",
url: uploadUrl,
body: data,
headers: {
"Content-Type": "application/octet-stream"
}
}, (err, res, body) => {
if (!err) {
resolve();
}
else {
console.log("uploadFile() request error: " + err);
}
});
});
});
}
function convertPdfToJson(apiKey, uploadedFileUrl, password, pages, destinationFile) {
// Prepare request to `PDF To JSON` API endpoint
var queryPath = `/v1/pdf/convert/to/json2`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": apiKey,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
if (data.error == false) {
// Download JSON file
var file = fs.createWriteStream(destinationFile);
https.get(data.url, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated JSON file saved as "${destinationFile}" file.`);
});
});
}
else {
// Service reported error
console.log("convertPdfToJson(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("convertPdfToJson(): " + e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
import os
import requests # pip install requests
# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "******************************************"
# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"
# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination JSON file name
DestinationFile = ".\\result.json"
def main(args = None):
uploadedFileUrl = uploadFile(SourceFile)
if (uploadedFileUrl != None):
convertPdfToJson(uploadedFileUrl, DestinationFile)
def convertPdfToJson(uploadedFileUrl, destinationFile):
"""Converts PDF To Json using PDF.co Web API"""
# Prepare requests params as JSON
# See documentation: https://developer.pdf.co/api/pdf-to-json/basic
parameters = {}
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To Json' API request
url = "{}/pdf/convert/to/json2".format(BASE_URL)
# Execute request and get response as JSON
response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# Get URL of result file
resultFileUrl = json["url"]
# Download result file
r = requests.get(resultFileUrl, stream=True)
if (r.status_code == 200):
with open(destinationFile, 'wb') as file:
for chunk in r:
file.write(chunk)
print(f"Result file saved as \"{destinationFile}\" file.")
else:
print(f"Request error: {response.status_code} {response.reason}")
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
def uploadFile(fileName):
"""Uploads file to the cloud"""
# 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
# Prepare URL for 'Get Presigned URL' API request
url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
BASE_URL, os.path.basename(fileName))
# Execute request and get response as JSON
response = requests.get(url, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# URL to use for file upload
uploadUrl = json["presignedUrl"]
# URL for future reference
uploadedFileUrl = json["url"]
# 2. UPLOAD FILE TO CLOUD.
with open(fileName, 'rb') as file:
requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })
return uploadedFileUrl
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
return None
if __name__ == '__main__':
main()
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
namespace PDFcoApiExample
{
class Program
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const String API_KEY = "***********************************";
// Source PDF file
const string SourceFile = @".\sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const string Pages = "";
// PDF document password. Leave empty for unprotected documents.
const string Password = "";
// Destination JSON file name
const string DestinationFile = @".\result.json";
static void Main(string[] args)
{
// Create standard .NET web client instance
WebClient webClient = new WebClient();
// Set API Key
webClient.Headers.Add("x-api-key", API_KEY);
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
string query = Uri.EscapeUriString(string.Format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
Path.GetFileName(SourceFile)));
try
{
// Execute request
string response = webClient.DownloadString(query);
// Parse JSON response
JObject json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL to use for the file upload
string uploadUrl = json["presignedUrl"].ToString();
string uploadedFileUrl = json["url"].ToString();
// 2. UPLOAD THE FILE TO CLOUD.
webClient.Headers.Add("content-type", "application/octet-stream");
webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
webClient.Headers.Remove("content-type");
// 3. CONVERT UPLOADED PDF FILE TO JSON
// URL for `PDF To JSON` API call
var url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params as JSON
Dictionary<string, object> parameters = new Dictionary<string, object>();
parameters.Add("name", Path.GetFileName(DestinationFile));
parameters.Add("password", Password);
parameters.Add("pages", Pages);
parameters.Add("url", uploadedFileUrl);
// Convert dictionary of params to JSON
string jsonPayload = JsonConvert.SerializeObject(parameters);
// Execute POST request with JSON payload
response = webClient.UploadString(url, jsonPayload);
// Parse JSON response
json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL of generated JSON file
string resultFileUrl = json["url"].ToString();
// Download JSON file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
catch (WebException e)
{
Console.WriteLine(e.ToString());
}
webClient.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
package com.company;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\sample.pdf");
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
final static String Pages = "";
// PDF document password. Leave empty for unprotected documents.
final static String Password = "";
// Destination JSON file name
final static Path DestinationFile = Paths.get(".\\result.json");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
String query = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO JSON
PdfToJson(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToJson(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
// Prepare URL for `PDF To JSON` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Make correctly escaped (encoded) URL
URL url = null;
try
{
url = new URI(null, query, null).toURL();
}
catch (URISyntaxException e)
{
e.printStackTrace();
}
// Create JSON payload
String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl);
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.addHeader("Content-Type", "application/json")
.post(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL of generated JSON file
String resultFileUrl = json.get("url").getAsString();
// Download JSON file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
<?php
// Note: For input files larger than 200 KB, we recommend using async mode by setting the "async" parameter to true.
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";
// Source PDF file
$SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
$Pages = "";
// PDF document password. Leave empty for unprotected documents.
$Password = "";
// Destination JSON file name
$DestinationFile = "./result.json";
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have the direct PDF file link, go to the step 3.
$presignedUrls = getPresignedUrl($API_KEY, $SourceFile);
if ($presignedUrls !== null) {
list($uploadUrl, $uploadedFileUrl) = $presignedUrls;
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson($API_KEY, $uploadedFileUrl, $Password, $Pages, $DestinationFile);
}
}
function getPresignedUrl($apiKey, $localFile)
{
// Prepare URL for `Get Presigned URL` API call
$url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
. "?contenttype=application/octet-stream"
. "&name=" . urlencode(basename($localFile));
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "getPresignedUrl(): " . $curlError . PHP_EOL;
return null;
}
if ($statusCode != 200) {
// Display request error
echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return null;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
return null;
}
// Return the URL to use for the file upload, and the URL of the uploaded
// file to use with later API calls
return array($json["presignedUrl"], $json["url"]);
}
function uploadFile($apiKey, $localFile, $uploadUrl)
{
$fileHandle = fopen($localFile, "rb");
if ($fileHandle === false) {
echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
return false;
}
// Create request. The presigned URL expects a raw PUT of the file bytes.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $uploadUrl);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
curl_setopt($curl, CURLOPT_PUT, true);
curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
fclose($fileHandle);
if ($result === false) {
// Display CURL error
echo "uploadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
return true;
}
function convertPdfToJson($apiKey, $uploadedFileUrl, $password, $pages, $destinationFile)
{
// Prepare URL for `PDF To JSON` API call
$url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params
$parameters = array();
$parameters["name"] = basename($destinationFile);
$parameters["password"] = $password;
$parameters["pages"] = $pages;
$parameters["url"] = $uploadedFileUrl;
// Create Json payload
$data = json_encode($parameters);
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "convertPdfToJson(): " . $curlError . PHP_EOL;
return;
}
if ($statusCode != 200) {
// Display request error
echo "convertPdfToJson(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "convertPdfToJson(): " . $json["message"] . PHP_EOL;
return;
}
// Get URL of generated JSON file
$resultFileUrl = $json["url"];
// Download JSON file
if (downloadFile($resultFileUrl, $destinationFile)) {
echo "Generated JSON file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
}
}
function downloadFile($url, $destinationFile)
{
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "downloadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
// Write the file only after a successful response so failures leave no file behind
if (file_put_contents($destinationFile, $result) === false) {
echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
return false;
}
return true;
}
?>
{
"url": "https://pdf-temp-files.s3.us-west-2.amazonaws.com/example-id/sample.json",
"outputLinkValidTill": "2026-09-25T12:47:50.6815154+00:00",
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.json",
"duration": 225,
"credits": 28,
"remainingCredits": 87563
}
{
"error": true,
"status": 400,
"message": "Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password)."
}
{
"error": true,
"status": 401,
"message": "Unauthorized. Authentication is required and has failed or has not yet been provided."
}
{
"error": true,
"status": 402,
"message": "Not enough credits."
}
{
"error": true,
"status": 403,
"message": "Access forbidden for input URL."
}
{
"error": true,
"status": 404,
"message": "The requested resource could not be found."
}
{
"error": true,
"status": 408,
"message": "The server timed out waiting for the request."
}
{
"error": true,
"status": 429,
"message": "Too many requests in a given time period."
}
{
"error": true,
"status": 441,
"message": "Invalid Password. Password protected document."
}
{
"error": true,
"status": 442,
"message": "Input document is damaged or of incorrect type."
}
{
"error": true,
"status": 443,
"message": "Permissions. The operation is prohibited by document security settings."
}
{
"error": true,
"status": 444,
"message": "Profiles parsing error. Please ensure that the configuration is supported."
}
{
"error": true,
"status": 445,
"message": "Timeout error. For large documents, use asynchronous mode (async=true) and check status via /job/check."
}
{
"error": true,
"status": 446,
"message": "Some files required for conversion are missing."
}
{
"error": true,
"status": 448,
"message": "Invalid URL or HTML. Ensure the provided URL is valid and accessible."
}
{
"error": true,
"status": 449,
"message": "Invalid index range. Page index is out of range."
}
{
"error": true,
"status": 450,
"message": "Invalid page range specified."
}
{
"error": true,
"status": 452,
"message": "Invalid URL."
}
{
"error": true,
"status": 454,
"message": "Invalid parameters."
}
{
"error": true,
"status": 500,
"message": "Something went wrong. Please try again or contact support."
}
CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/convert/to/json2' \
--header 'Content-Type: application/json' \
--header 'x-api-key: *******************' \
--data-raw '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-json/sample.pdf",
"async": false
}'
var https = require("https");
var path = require("path");
var fs = require("fs");
// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";
// Source PDF file
const SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// Destination JSON file name
const DestinationFile = "./result.json";
// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
.then(([uploadUrl, uploadedFileUrl]) => {
// 2. UPLOAD THE FILE TO CLOUD.
uploadFile(API_KEY, SourceFile, uploadUrl)
.then(() => {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
})
.catch(e => {
console.log(e);
});
})
.catch(e => {
console.log(e);
});
function getPresignedUrl(apiKey, localFile) {
return new Promise(resolve => {
// Prepare request to `Get Presigned URL` API endpoint
let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
let reqOptions = {
host: "api.pdf.co",
path: encodeURI(queryPath),
headers: { "x-api-key": API_KEY }
};
// Send request
https.get(reqOptions, (response) => {
response.on("data", (d) => {
let data = JSON.parse(d);
if (data.error == false) {
// Return presigned url we received
resolve([data.presignedUrl, data.url]);
}
else {
// Service reported error
console.log("getPresignedUrl(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("getPresignedUrl(): " + e);
});
});
}
function uploadFile(apiKey, localFile, uploadUrl) {
return new Promise(resolve => {
fs.readFile(SourceFile, (err, data) => {
request({
method: "PUT",
url: uploadUrl,
body: data,
headers: {
"Content-Type": "application/octet-stream"
}
}, (err, res, body) => {
if (!err) {
resolve();
}
else {
console.log("uploadFile() request error: " + err);
}
});
});
});
}
function convertPdfToJson(apiKey, uploadedFileUrl, password, pages, destinationFile) {
// Prepare request to `PDF To JSON` API endpoint
var queryPath = `/v1/pdf/convert/to/json2`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": apiKey,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
if (data.error == false) {
// Download JSON file
var file = fs.createWriteStream(destinationFile);
https.get(data.url, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated JSON file saved as "${destinationFile}" file.`);
});
});
}
else {
// Service reported error
console.log("convertPdfToJson(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("convertPdfToJson(): " + e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
import os
import requests # pip install requests
# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "******************************************"
# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"
# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination JSON file name
DestinationFile = ".\\result.json"
def main(args = None):
uploadedFileUrl = uploadFile(SourceFile)
if (uploadedFileUrl != None):
convertPdfToJson(uploadedFileUrl, DestinationFile)
def convertPdfToJson(uploadedFileUrl, destinationFile):
"""Converts PDF To Json using PDF.co Web API"""
# Prepare requests params as JSON
# See documentation: https://developer.pdf.co/api/pdf-to-json/basic
parameters = {}
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To Json' API request
url = "{}/pdf/convert/to/json2".format(BASE_URL)
# Execute request and get response as JSON
response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# Get URL of result file
resultFileUrl = json["url"]
# Download result file
r = requests.get(resultFileUrl, stream=True)
if (r.status_code == 200):
with open(destinationFile, 'wb') as file:
for chunk in r:
file.write(chunk)
print(f"Result file saved as \"{destinationFile}\" file.")
else:
print(f"Request error: {response.status_code} {response.reason}")
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
def uploadFile(fileName):
"""Uploads file to the cloud"""
# 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
# Prepare URL for 'Get Presigned URL' API request
url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
BASE_URL, os.path.basename(fileName))
# Execute request and get response as JSON
response = requests.get(url, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# URL to use for file upload
uploadUrl = json["presignedUrl"]
# URL for future reference
uploadedFileUrl = json["url"]
# 2. UPLOAD FILE TO CLOUD.
with open(fileName, 'rb') as file:
requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })
return uploadedFileUrl
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
return None
if __name__ == '__main__':
main()
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
namespace PDFcoApiExample
{
class Program
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const String API_KEY = "***********************************";
// Source PDF file
const string SourceFile = @".\sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const string Pages = "";
// PDF document password. Leave empty for unprotected documents.
const string Password = "";
// Destination JSON file name
const string DestinationFile = @".\result.json";
static void Main(string[] args)
{
// Create standard .NET web client instance
WebClient webClient = new WebClient();
// Set API Key
webClient.Headers.Add("x-api-key", API_KEY);
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
string query = Uri.EscapeUriString(string.Format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
Path.GetFileName(SourceFile)));
try
{
// Execute request
string response = webClient.DownloadString(query);
// Parse JSON response
JObject json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL to use for the file upload
string uploadUrl = json["presignedUrl"].ToString();
string uploadedFileUrl = json["url"].ToString();
// 2. UPLOAD THE FILE TO CLOUD.
webClient.Headers.Add("content-type", "application/octet-stream");
webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
webClient.Headers.Remove("content-type");
// 3. CONVERT UPLOADED PDF FILE TO JSON
// URL for `PDF To JSON` API call
var url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params as JSON
Dictionary<string, object> parameters = new Dictionary<string, object>();
parameters.Add("name", Path.GetFileName(DestinationFile));
parameters.Add("password", Password);
parameters.Add("pages", Pages);
parameters.Add("url", uploadedFileUrl);
// Convert dictionary of params to JSON
string jsonPayload = JsonConvert.SerializeObject(parameters);
// Execute POST request with JSON payload
response = webClient.UploadString(url, jsonPayload);
// Parse JSON response
json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL of generated JSON file
string resultFileUrl = json["url"].ToString();
// Download JSON file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
catch (WebException e)
{
Console.WriteLine(e.ToString());
}
webClient.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
package com.company;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\sample.pdf");
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
final static String Pages = "";
// PDF document password. Leave empty for unprotected documents.
final static String Password = "";
// Destination JSON file name
final static Path DestinationFile = Paths.get(".\\result.json");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
String query = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO JSON
PdfToJson(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToJson(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
// Prepare URL for `PDF To JSON` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Make correctly escaped (encoded) URL
URL url = null;
try
{
url = new URI(null, query, null).toURL();
}
catch (URISyntaxException e)
{
e.printStackTrace();
}
// Create JSON payload
String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl);
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.addHeader("Content-Type", "application/json")
.post(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL of generated JSON file
String resultFileUrl = json.get("url").getAsString();
// Download JSON file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
<?php
// Note: For input files larger than 200 KB, we recommend using async mode by setting the "async" parameter to true.
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";
// Source PDF file
$SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
$Pages = "";
// PDF document password. Leave empty for unprotected documents.
$Password = "";
// Destination JSON file name
$DestinationFile = "./result.json";
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have the direct PDF file link, go to the step 3.
$presignedUrls = getPresignedUrl($API_KEY, $SourceFile);
if ($presignedUrls !== null) {
list($uploadUrl, $uploadedFileUrl) = $presignedUrls;
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson($API_KEY, $uploadedFileUrl, $Password, $Pages, $DestinationFile);
}
}
function getPresignedUrl($apiKey, $localFile)
{
// Prepare URL for `Get Presigned URL` API call
$url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
. "?contenttype=application/octet-stream"
. "&name=" . urlencode(basename($localFile));
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "getPresignedUrl(): " . $curlError . PHP_EOL;
return null;
}
if ($statusCode != 200) {
// Display request error
echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return null;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
return null;
}
// Return the URL to use for the file upload, and the URL of the uploaded
// file to use with later API calls
return array($json["presignedUrl"], $json["url"]);
}
function uploadFile($apiKey, $localFile, $uploadUrl)
{
$fileHandle = fopen($localFile, "rb");
if ($fileHandle === false) {
echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
return false;
}
// Create request. The presigned URL expects a raw PUT of the file bytes.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $uploadUrl);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
curl_setopt($curl, CURLOPT_PUT, true);
curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
fclose($fileHandle);
if ($result === false) {
// Display CURL error
echo "uploadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
return true;
}
function convertPdfToJson($apiKey, $uploadedFileUrl, $password, $pages, $destinationFile)
{
// Prepare URL for `PDF To JSON` API call
$url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params
$parameters = array();
$parameters["name"] = basename($destinationFile);
$parameters["password"] = $password;
$parameters["pages"] = $pages;
$parameters["url"] = $uploadedFileUrl;
// Create Json payload
$data = json_encode($parameters);
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "convertPdfToJson(): " . $curlError . PHP_EOL;
return;
}
if ($statusCode != 200) {
// Display request error
echo "convertPdfToJson(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "convertPdfToJson(): " . $json["message"] . PHP_EOL;
return;
}
// Get URL of generated JSON file
$resultFileUrl = $json["url"];
// Download JSON file
if (downloadFile($resultFileUrl, $destinationFile)) {
echo "Generated JSON file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
}
}
function downloadFile($url, $destinationFile)
{
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "downloadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
// Write the file only after a successful response so failures leave no file behind
if (file_put_contents($destinationFile, $result) === false) {
echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
return false;
}
return true;
}
?>
{
"url": "https://pdf-temp-files.s3.us-west-2.amazonaws.com/example-id/sample.json",
"outputLinkValidTill": "2026-09-25T12:47:50.6815154+00:00",
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.json",
"duration": 225,
"credits": 28,
"remainingCredits": 87563
}
{
"error": true,
"status": 400,
"message": "Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password)."
}
{
"error": true,
"status": 401,
"message": "Unauthorized. Authentication is required and has failed or has not yet been provided."
}
{
"error": true,
"status": 402,
"message": "Not enough credits."
}
{
"error": true,
"status": 403,
"message": "Access forbidden for input URL."
}
{
"error": true,
"status": 404,
"message": "The requested resource could not be found."
}
{
"error": true,
"status": 408,
"message": "The server timed out waiting for the request."
}
{
"error": true,
"status": 429,
"message": "Too many requests in a given time period."
}
{
"error": true,
"status": 441,
"message": "Invalid Password. Password protected document."
}
{
"error": true,
"status": 442,
"message": "Input document is damaged or of incorrect type."
}
{
"error": true,
"status": 443,
"message": "Permissions. The operation is prohibited by document security settings."
}
{
"error": true,
"status": 444,
"message": "Profiles parsing error. Please ensure that the configuration is supported."
}
{
"error": true,
"status": 445,
"message": "Timeout error. For large documents, use asynchronous mode (async=true) and check status via /job/check."
}
{
"error": true,
"status": 446,
"message": "Some files required for conversion are missing."
}
{
"error": true,
"status": 448,
"message": "Invalid URL or HTML. Ensure the provided URL is valid and accessible."
}
{
"error": true,
"status": 449,
"message": "Invalid index range. Page index is out of range."
}
{
"error": true,
"status": 450,
"message": "Invalid page range specified."
}
{
"error": true,
"status": 452,
"message": "Invalid URL."
}
{
"error": true,
"status": 454,
"message": "Invalid parameters."
}
{
"error": true,
"status": 500,
"message": "Something went wrong. Please try again or contact support."
}
PDF to JSON
PDF to JSON
Convert PDF and scanned images into JSON representation with text, fonts, images, vectors, and formatting preserved.
Sample request
CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/convert/to/json2' \
--header 'Content-Type: application/json' \
--header 'x-api-key: *******************' \
--data-raw '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-json/sample.pdf",
"async": false
}'
var https = require("https");
var path = require("path");
var fs = require("fs");
// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";
// Source PDF file
const SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// Destination JSON file name
const DestinationFile = "./result.json";
// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
.then(([uploadUrl, uploadedFileUrl]) => {
// 2. UPLOAD THE FILE TO CLOUD.
uploadFile(API_KEY, SourceFile, uploadUrl)
.then(() => {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
})
.catch(e => {
console.log(e);
});
})
.catch(e => {
console.log(e);
});
function getPresignedUrl(apiKey, localFile) {
return new Promise(resolve => {
// Prepare request to `Get Presigned URL` API endpoint
let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
let reqOptions = {
host: "api.pdf.co",
path: encodeURI(queryPath),
headers: { "x-api-key": API_KEY }
};
// Send request
https.get(reqOptions, (response) => {
response.on("data", (d) => {
let data = JSON.parse(d);
if (data.error == false) {
// Return presigned url we received
resolve([data.presignedUrl, data.url]);
}
else {
// Service reported error
console.log("getPresignedUrl(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("getPresignedUrl(): " + e);
});
});
}
function uploadFile(apiKey, localFile, uploadUrl) {
return new Promise(resolve => {
fs.readFile(SourceFile, (err, data) => {
request({
method: "PUT",
url: uploadUrl,
body: data,
headers: {
"Content-Type": "application/octet-stream"
}
}, (err, res, body) => {
if (!err) {
resolve();
}
else {
console.log("uploadFile() request error: " + err);
}
});
});
});
}
function convertPdfToJson(apiKey, uploadedFileUrl, password, pages, destinationFile) {
// Prepare request to `PDF To JSON` API endpoint
var queryPath = `/v1/pdf/convert/to/json2`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": apiKey,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
if (data.error == false) {
// Download JSON file
var file = fs.createWriteStream(destinationFile);
https.get(data.url, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated JSON file saved as "${destinationFile}" file.`);
});
});
}
else {
// Service reported error
console.log("convertPdfToJson(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("convertPdfToJson(): " + e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
import os
import requests # pip install requests
# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "******************************************"
# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"
# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination JSON file name
DestinationFile = ".\\result.json"
def main(args = None):
uploadedFileUrl = uploadFile(SourceFile)
if (uploadedFileUrl != None):
convertPdfToJson(uploadedFileUrl, DestinationFile)
def convertPdfToJson(uploadedFileUrl, destinationFile):
"""Converts PDF To Json using PDF.co Web API"""
# Prepare requests params as JSON
# See documentation: https://developer.pdf.co/api/pdf-to-json/basic
parameters = {}
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To Json' API request
url = "{}/pdf/convert/to/json2".format(BASE_URL)
# Execute request and get response as JSON
response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# Get URL of result file
resultFileUrl = json["url"]
# Download result file
r = requests.get(resultFileUrl, stream=True)
if (r.status_code == 200):
with open(destinationFile, 'wb') as file:
for chunk in r:
file.write(chunk)
print(f"Result file saved as \"{destinationFile}\" file.")
else:
print(f"Request error: {response.status_code} {response.reason}")
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
def uploadFile(fileName):
"""Uploads file to the cloud"""
# 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
# Prepare URL for 'Get Presigned URL' API request
url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
BASE_URL, os.path.basename(fileName))
# Execute request and get response as JSON
response = requests.get(url, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# URL to use for file upload
uploadUrl = json["presignedUrl"]
# URL for future reference
uploadedFileUrl = json["url"]
# 2. UPLOAD FILE TO CLOUD.
with open(fileName, 'rb') as file:
requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })
return uploadedFileUrl
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
return None
if __name__ == '__main__':
main()
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
namespace PDFcoApiExample
{
class Program
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const String API_KEY = "***********************************";
// Source PDF file
const string SourceFile = @".\sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const string Pages = "";
// PDF document password. Leave empty for unprotected documents.
const string Password = "";
// Destination JSON file name
const string DestinationFile = @".\result.json";
static void Main(string[] args)
{
// Create standard .NET web client instance
WebClient webClient = new WebClient();
// Set API Key
webClient.Headers.Add("x-api-key", API_KEY);
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
string query = Uri.EscapeUriString(string.Format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
Path.GetFileName(SourceFile)));
try
{
// Execute request
string response = webClient.DownloadString(query);
// Parse JSON response
JObject json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL to use for the file upload
string uploadUrl = json["presignedUrl"].ToString();
string uploadedFileUrl = json["url"].ToString();
// 2. UPLOAD THE FILE TO CLOUD.
webClient.Headers.Add("content-type", "application/octet-stream");
webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
webClient.Headers.Remove("content-type");
// 3. CONVERT UPLOADED PDF FILE TO JSON
// URL for `PDF To JSON` API call
var url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params as JSON
Dictionary<string, object> parameters = new Dictionary<string, object>();
parameters.Add("name", Path.GetFileName(DestinationFile));
parameters.Add("password", Password);
parameters.Add("pages", Pages);
parameters.Add("url", uploadedFileUrl);
// Convert dictionary of params to JSON
string jsonPayload = JsonConvert.SerializeObject(parameters);
// Execute POST request with JSON payload
response = webClient.UploadString(url, jsonPayload);
// Parse JSON response
json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL of generated JSON file
string resultFileUrl = json["url"].ToString();
// Download JSON file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
catch (WebException e)
{
Console.WriteLine(e.ToString());
}
webClient.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
package com.company;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\sample.pdf");
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
final static String Pages = "";
// PDF document password. Leave empty for unprotected documents.
final static String Password = "";
// Destination JSON file name
final static Path DestinationFile = Paths.get(".\\result.json");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
String query = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO JSON
PdfToJson(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToJson(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
// Prepare URL for `PDF To JSON` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Make correctly escaped (encoded) URL
URL url = null;
try
{
url = new URI(null, query, null).toURL();
}
catch (URISyntaxException e)
{
e.printStackTrace();
}
// Create JSON payload
String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl);
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.addHeader("Content-Type", "application/json")
.post(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL of generated JSON file
String resultFileUrl = json.get("url").getAsString();
// Download JSON file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
<?php
// Note: For input files larger than 200 KB, we recommend using async mode by setting the "async" parameter to true.
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";
// Source PDF file
$SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
$Pages = "";
// PDF document password. Leave empty for unprotected documents.
$Password = "";
// Destination JSON file name
$DestinationFile = "./result.json";
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have the direct PDF file link, go to the step 3.
$presignedUrls = getPresignedUrl($API_KEY, $SourceFile);
if ($presignedUrls !== null) {
list($uploadUrl, $uploadedFileUrl) = $presignedUrls;
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson($API_KEY, $uploadedFileUrl, $Password, $Pages, $DestinationFile);
}
}
function getPresignedUrl($apiKey, $localFile)
{
// Prepare URL for `Get Presigned URL` API call
$url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
. "?contenttype=application/octet-stream"
. "&name=" . urlencode(basename($localFile));
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "getPresignedUrl(): " . $curlError . PHP_EOL;
return null;
}
if ($statusCode != 200) {
// Display request error
echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return null;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
return null;
}
// Return the URL to use for the file upload, and the URL of the uploaded
// file to use with later API calls
return array($json["presignedUrl"], $json["url"]);
}
function uploadFile($apiKey, $localFile, $uploadUrl)
{
$fileHandle = fopen($localFile, "rb");
if ($fileHandle === false) {
echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
return false;
}
// Create request. The presigned URL expects a raw PUT of the file bytes.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $uploadUrl);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
curl_setopt($curl, CURLOPT_PUT, true);
curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
fclose($fileHandle);
if ($result === false) {
// Display CURL error
echo "uploadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
return true;
}
function convertPdfToJson($apiKey, $uploadedFileUrl, $password, $pages, $destinationFile)
{
// Prepare URL for `PDF To JSON` API call
$url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params
$parameters = array();
$parameters["name"] = basename($destinationFile);
$parameters["password"] = $password;
$parameters["pages"] = $pages;
$parameters["url"] = $uploadedFileUrl;
// Create Json payload
$data = json_encode($parameters);
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "convertPdfToJson(): " . $curlError . PHP_EOL;
return;
}
if ($statusCode != 200) {
// Display request error
echo "convertPdfToJson(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "convertPdfToJson(): " . $json["message"] . PHP_EOL;
return;
}
// Get URL of generated JSON file
$resultFileUrl = $json["url"];
// Download JSON file
if (downloadFile($resultFileUrl, $destinationFile)) {
echo "Generated JSON file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
}
}
function downloadFile($url, $destinationFile)
{
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "downloadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
// Write the file only after a successful response so failures leave no file behind
if (file_put_contents($destinationFile, $result) === false) {
echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
return false;
}
return true;
}
?>
{
"url": "https://pdf-temp-files.s3.us-west-2.amazonaws.com/example-id/sample.json",
"outputLinkValidTill": "2026-09-25T12:47:50.6815154+00:00",
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.json",
"duration": 225,
"credits": 28,
"remainingCredits": 87563
}
{
"error": true,
"status": 400,
"message": "Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password)."
}
{
"error": true,
"status": 401,
"message": "Unauthorized. Authentication is required and has failed or has not yet been provided."
}
{
"error": true,
"status": 402,
"message": "Not enough credits."
}
{
"error": true,
"status": 403,
"message": "Access forbidden for input URL."
}
{
"error": true,
"status": 404,
"message": "The requested resource could not be found."
}
{
"error": true,
"status": 408,
"message": "The server timed out waiting for the request."
}
{
"error": true,
"status": 429,
"message": "Too many requests in a given time period."
}
{
"error": true,
"status": 441,
"message": "Invalid Password. Password protected document."
}
{
"error": true,
"status": 442,
"message": "Input document is damaged or of incorrect type."
}
{
"error": true,
"status": 443,
"message": "Permissions. The operation is prohibited by document security settings."
}
{
"error": true,
"status": 444,
"message": "Profiles parsing error. Please ensure that the configuration is supported."
}
{
"error": true,
"status": 445,
"message": "Timeout error. For large documents, use asynchronous mode (async=true) and check status via /job/check."
}
{
"error": true,
"status": 446,
"message": "Some files required for conversion are missing."
}
{
"error": true,
"status": 448,
"message": "Invalid URL or HTML. Ensure the provided URL is valid and accessible."
}
{
"error": true,
"status": 449,
"message": "Invalid index range. Page index is out of range."
}
{
"error": true,
"status": 450,
"message": "Invalid page range specified."
}
{
"error": true,
"status": 452,
"message": "Invalid URL."
}
{
"error": true,
"status": 454,
"message": "Invalid parameters."
}
{
"error": true,
"status": 500,
"message": "Something went wrong. Please try again or contact support."
}
CURL
curl --location --request POST 'https://api.pdf.co/v1/pdf/convert/to/json2' \
--header 'Content-Type: application/json' \
--header 'x-api-key: *******************' \
--data-raw '{
"url": "https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-json/sample.pdf",
"async": false
}'
var https = require("https");
var path = require("path");
var fs = require("fs");
// `request` module is required for file upload.
// Use "npm install request" command to install.
var request = require("request");
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const API_KEY = "***********************************";
// Source PDF file
const SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const Pages = "";
// PDF document password. Leave empty for unprotected documents.
const Password = "";
// Destination JSON file name
const DestinationFile = "./result.json";
// 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
getPresignedUrl(API_KEY, SourceFile)
.then(([uploadUrl, uploadedFileUrl]) => {
// 2. UPLOAD THE FILE TO CLOUD.
uploadFile(API_KEY, SourceFile, uploadUrl)
.then(() => {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson(API_KEY, uploadedFileUrl, Password, Pages, DestinationFile);
})
.catch(e => {
console.log(e);
});
})
.catch(e => {
console.log(e);
});
function getPresignedUrl(apiKey, localFile) {
return new Promise(resolve => {
// Prepare request to `Get Presigned URL` API endpoint
let queryPath = `/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=${path.basename(SourceFile)}`;
let reqOptions = {
host: "api.pdf.co",
path: encodeURI(queryPath),
headers: { "x-api-key": API_KEY }
};
// Send request
https.get(reqOptions, (response) => {
response.on("data", (d) => {
let data = JSON.parse(d);
if (data.error == false) {
// Return presigned url we received
resolve([data.presignedUrl, data.url]);
}
else {
// Service reported error
console.log("getPresignedUrl(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("getPresignedUrl(): " + e);
});
});
}
function uploadFile(apiKey, localFile, uploadUrl) {
return new Promise(resolve => {
fs.readFile(SourceFile, (err, data) => {
request({
method: "PUT",
url: uploadUrl,
body: data,
headers: {
"Content-Type": "application/octet-stream"
}
}, (err, res, body) => {
if (!err) {
resolve();
}
else {
console.log("uploadFile() request error: " + err);
}
});
});
});
}
function convertPdfToJson(apiKey, uploadedFileUrl, password, pages, destinationFile) {
// Prepare request to `PDF To JSON` API endpoint
var queryPath = `/v1/pdf/convert/to/json2`;
// JSON payload for api request
var jsonPayload = JSON.stringify({
name: path.basename(destinationFile), password: password, pages: pages, url: uploadedFileUrl
});
var reqOptions = {
host: "api.pdf.co",
method: "POST",
path: queryPath,
headers: {
"x-api-key": apiKey,
"Content-Type": "application/json",
"Content-Length": Buffer.byteLength(jsonPayload, 'utf8')
}
};
// Send request
var postRequest = https.request(reqOptions, (response) => {
response.on("data", (d) => {
response.setEncoding("utf8");
// Parse JSON response
let data = JSON.parse(d);
if (data.error == false) {
// Download JSON file
var file = fs.createWriteStream(destinationFile);
https.get(data.url, (response2) => {
response2.pipe(file)
.on("close", () => {
console.log(`Generated JSON file saved as "${destinationFile}" file.`);
});
});
}
else {
// Service reported error
console.log("convertPdfToJson(): " + data.message);
}
});
})
.on("error", (e) => {
// Request error
console.log("convertPdfToJson(): " + e);
});
// Write request data
postRequest.write(jsonPayload);
postRequest.end();
}
import os
import requests # pip install requests
# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "******************************************"
# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"
# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination JSON file name
DestinationFile = ".\\result.json"
def main(args = None):
uploadedFileUrl = uploadFile(SourceFile)
if (uploadedFileUrl != None):
convertPdfToJson(uploadedFileUrl, DestinationFile)
def convertPdfToJson(uploadedFileUrl, destinationFile):
"""Converts PDF To Json using PDF.co Web API"""
# Prepare requests params as JSON
# See documentation: https://developer.pdf.co/api/pdf-to-json/basic
parameters = {}
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To Json' API request
url = "{}/pdf/convert/to/json2".format(BASE_URL)
# Execute request and get response as JSON
response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# Get URL of result file
resultFileUrl = json["url"]
# Download result file
r = requests.get(resultFileUrl, stream=True)
if (r.status_code == 200):
with open(destinationFile, 'wb') as file:
for chunk in r:
file.write(chunk)
print(f"Result file saved as \"{destinationFile}\" file.")
else:
print(f"Request error: {response.status_code} {response.reason}")
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
def uploadFile(fileName):
"""Uploads file to the cloud"""
# 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.
# Prepare URL for 'Get Presigned URL' API request
url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
BASE_URL, os.path.basename(fileName))
# Execute request and get response as JSON
response = requests.get(url, headers={ "x-api-key": API_KEY })
if (response.status_code == 200):
json = response.json()
if json["error"] == False:
# URL to use for file upload
uploadUrl = json["presignedUrl"]
# URL for future reference
uploadedFileUrl = json["url"]
# 2. UPLOAD FILE TO CLOUD.
with open(fileName, 'rb') as file:
requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })
return uploadedFileUrl
else:
# Show service reported error
print(json["message"])
else:
print(f"Request error: {response.status_code} {response.reason}")
return None
if __name__ == '__main__':
main()
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
namespace PDFcoApiExample
{
class Program
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const String API_KEY = "***********************************";
// Source PDF file
const string SourceFile = @".\sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
const string Pages = "";
// PDF document password. Leave empty for unprotected documents.
const string Password = "";
// Destination JSON file name
const string DestinationFile = @".\result.json";
static void Main(string[] args)
{
// Create standard .NET web client instance
WebClient webClient = new WebClient();
// Set API Key
webClient.Headers.Add("x-api-key", API_KEY);
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
string query = Uri.EscapeUriString(string.Format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
Path.GetFileName(SourceFile)));
try
{
// Execute request
string response = webClient.DownloadString(query);
// Parse JSON response
JObject json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL to use for the file upload
string uploadUrl = json["presignedUrl"].ToString();
string uploadedFileUrl = json["url"].ToString();
// 2. UPLOAD THE FILE TO CLOUD.
webClient.Headers.Add("content-type", "application/octet-stream");
webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
webClient.Headers.Remove("content-type");
// 3. CONVERT UPLOADED PDF FILE TO JSON
// URL for `PDF To JSON` API call
var url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params as JSON
Dictionary<string, object> parameters = new Dictionary<string, object>();
parameters.Add("name", Path.GetFileName(DestinationFile));
parameters.Add("password", Password);
parameters.Add("pages", Pages);
parameters.Add("url", uploadedFileUrl);
// Convert dictionary of params to JSON
string jsonPayload = JsonConvert.SerializeObject(parameters);
// Execute POST request with JSON payload
response = webClient.UploadString(url, jsonPayload);
// Parse JSON response
json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL of generated JSON file
string resultFileUrl = json["url"].ToString();
// Download JSON file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
catch (WebException e)
{
Console.WriteLine(e.ToString());
}
webClient.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
}
}
package com.company;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\sample.pdf");
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
final static String Pages = "";
// PDF document password. Leave empty for unprotected documents.
final static String Password = "";
// Destination JSON file name
final static Path DestinationFile = Paths.get(".\\result.json");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
String query = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO JSON
PdfToJson(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToJson(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
// Prepare URL for `PDF To JSON` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Make correctly escaped (encoded) URL
URL url = null;
try
{
url = new URI(null, query, null).toURL();
}
catch (URISyntaxException e)
{
e.printStackTrace();
}
// Create JSON payload
String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl);
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.addHeader("Content-Type", "application/json")
.post(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL of generated JSON file
String resultFileUrl = json.get("url").getAsString();
// Download JSON file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
<?php
// Note: For input files larger than 200 KB, we recommend using async mode by setting the "async" parameter to true.
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
$API_KEY = "***********************************";
// Source PDF file
$SourceFile = "./sample.pdf";
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
$Pages = "";
// PDF document password. Leave empty for unprotected documents.
$Password = "";
// Destination JSON file name
$DestinationFile = "./result.json";
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have the direct PDF file link, go to the step 3.
$presignedUrls = getPresignedUrl($API_KEY, $SourceFile);
if ($presignedUrls !== null) {
list($uploadUrl, $uploadedFileUrl) = $presignedUrls;
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile($API_KEY, $SourceFile, $uploadUrl)) {
// 3. CONVERT UPLOADED PDF FILE TO JSON
convertPdfToJson($API_KEY, $uploadedFileUrl, $Password, $Pages, $DestinationFile);
}
}
function getPresignedUrl($apiKey, $localFile)
{
// Prepare URL for `Get Presigned URL` API call
$url = "https://api.pdf.co/v1/file/upload/get-presigned-url"
. "?contenttype=application/octet-stream"
. "&name=" . urlencode(basename($localFile));
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "getPresignedUrl(): " . $curlError . PHP_EOL;
return null;
}
if ($statusCode != 200) {
// Display request error
echo "getPresignedUrl(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return null;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "getPresignedUrl(): " . $json["message"] . PHP_EOL;
return null;
}
// Return the URL to use for the file upload, and the URL of the uploaded
// file to use with later API calls
return array($json["presignedUrl"], $json["url"]);
}
function uploadFile($apiKey, $localFile, $uploadUrl)
{
$fileHandle = fopen($localFile, "rb");
if ($fileHandle === false) {
echo "uploadFile(): unable to open " . $localFile . PHP_EOL;
return false;
}
// Create request. The presigned URL expects a raw PUT of the file bytes.
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $uploadUrl);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "content-type: application/octet-stream"));
curl_setopt($curl, CURLOPT_PUT, true);
curl_setopt($curl, CURLOPT_INFILE, $fileHandle);
curl_setopt($curl, CURLOPT_INFILESIZE, filesize($localFile));
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
fclose($fileHandle);
if ($result === false) {
// Display CURL error
echo "uploadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "uploadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
return true;
}
function convertPdfToJson($apiKey, $uploadedFileUrl, $password, $pages, $destinationFile)
{
// Prepare URL for `PDF To JSON` API call
$url = "https://api.pdf.co/v1/pdf/convert/to/json2";
// Prepare requests params
$parameters = array();
$parameters["name"] = basename($destinationFile);
$parameters["password"] = $password;
$parameters["pages"] = $pages;
$parameters["url"] = $uploadedFileUrl;
// Create Json payload
$data = json_encode($parameters);
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HTTPHEADER, array("x-api-key: " . $apiKey, "Content-Type: application/json"));
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "convertPdfToJson(): " . $curlError . PHP_EOL;
return;
}
if ($statusCode != 200) {
// Display request error
echo "convertPdfToJson(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return;
}
$json = json_decode($result, true);
if (!empty($json["error"])) {
// Display service reported error
echo "convertPdfToJson(): " . $json["message"] . PHP_EOL;
return;
}
// Get URL of generated JSON file
$resultFileUrl = $json["url"];
// Download JSON file
if (downloadFile($resultFileUrl, $destinationFile)) {
echo "Generated JSON file saved as \"" . $destinationFile . "\" file." . PHP_EOL;
}
}
function downloadFile($url, $destinationFile)
{
// Create request
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
// Execute request
$result = curl_exec($curl);
$statusCode = curl_getinfo($curl, CURLINFO_HTTP_CODE);
$curlError = curl_error($curl);
curl_close($curl);
if ($result === false) {
// Display CURL error
echo "downloadFile(): " . $curlError . PHP_EOL;
return false;
}
if ($statusCode != 200) {
// Display request error
echo "downloadFile(): request error " . $statusCode . PHP_EOL . $result . PHP_EOL;
return false;
}
// Write the file only after a successful response so failures leave no file behind
if (file_put_contents($destinationFile, $result) === false) {
echo "downloadFile(): unable to create " . $destinationFile . PHP_EOL;
return false;
}
return true;
}
?>
{
"url": "https://pdf-temp-files.s3.us-west-2.amazonaws.com/example-id/sample.json",
"outputLinkValidTill": "2026-09-25T12:47:50.6815154+00:00",
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.json",
"duration": 225,
"credits": 28,
"remainingCredits": 87563
}
{
"error": true,
"status": 400,
"message": "Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password)."
}
{
"error": true,
"status": 401,
"message": "Unauthorized. Authentication is required and has failed or has not yet been provided."
}
{
"error": true,
"status": 402,
"message": "Not enough credits."
}
{
"error": true,
"status": 403,
"message": "Access forbidden for input URL."
}
{
"error": true,
"status": 404,
"message": "The requested resource could not be found."
}
{
"error": true,
"status": 408,
"message": "The server timed out waiting for the request."
}
{
"error": true,
"status": 429,
"message": "Too many requests in a given time period."
}
{
"error": true,
"status": 441,
"message": "Invalid Password. Password protected document."
}
{
"error": true,
"status": 442,
"message": "Input document is damaged or of incorrect type."
}
{
"error": true,
"status": 443,
"message": "Permissions. The operation is prohibited by document security settings."
}
{
"error": true,
"status": 444,
"message": "Profiles parsing error. Please ensure that the configuration is supported."
}
{
"error": true,
"status": 445,
"message": "Timeout error. For large documents, use asynchronous mode (async=true) and check status via /job/check."
}
{
"error": true,
"status": 446,
"message": "Some files required for conversion are missing."
}
{
"error": true,
"status": 448,
"message": "Invalid URL or HTML. Ensure the provided URL is valid and accessible."
}
{
"error": true,
"status": 449,
"message": "Invalid index range. Page index is out of range."
}
{
"error": true,
"status": 450,
"message": "Invalid page range specified."
}
{
"error": true,
"status": 452,
"message": "Invalid URL."
}
{
"error": true,
"status": 454,
"message": "Invalid parameters."
}
{
"error": true,
"status": 500,
"message": "Something went wrong. Please try again or contact support."
}
Try it live: PDF to JSON → API Tester — send a real request from your browser.
POST /v1/pdf/convert/to/json2
This endpoint can also be used with a specified profile to extract image data from a PDF into your JSON output.
You can extract hyperlinks from your PDF by using a profile to extract only link objects.
Request body
Attributes are case-sensitive and should be inside JSON for POST request. for example:
{ "url": "https://example.com/file1.pdf" } No query parameters accepted.To see the request size limits, please refer to the Request Size Limits.
string
required
URL to the source file
url attributestring
HTTP auth user name if required to access source URL.
string
HTTP auth password if required to access source URL.
string
default:"all pages"
Specify page indices as comma-separated values or ranges to process (e.g. “0, 1, 2-” or “1, 2, 3-7”). The first-page index is 0. Use ”!” before a number for inverted page numbers (e.g. “!0” for the last page). If not specified, the default configuration processes all pages. The input must be in string format.
boolean
default:"false"
Unwrap lines into a single line within table cells in provided PDF documents. This is only applicable when
linegrouping is set to 1.string
Defines coordinates for extraction. Use
PDF Edit Add Helperto get or measure PDF coordinates. The format is {x} {y} {width} {height}.string
default:"eng"
Set the language for OCR (text from image) to use for scanned PDF, PNG, and JPG documents input when extracting text. see Language Support. You can also use 2 languages simultaneously like this:
eng+deu (any combination).boolean
default:"false"
Set to true to return results inside the response. Otherwise, the endpoint will return a URL to the output file generated.
string
Controls how lines of text are grouped when extracting data from a PDF. Line grouping within table cells. The available modes are:
1, 2, 3. For more information, see Line Grouping.string
Password for the PDF file.
boolean
default:"false"
Set
async to true for long processes to run in the background, API will then return a jobId which you can use with the Background Job Check endpoint. Also see Webhooks & Callbacksstring
File name for the generated output, the input must be in string format.
integer
default:"60"
Set the expiration time for the output link in minutes. After this specified duration, any generated output file(s) will be automatically deleted from PDF.co Temporary Files Storage. The maximum duration for link expiration varies based on your current subscription plan. To store permanent input files (e.g. re-usable images, pdf templates, documents) consider using PDF.co Built-In Files Storage.
Show profiles properties
Show profiles properties
| Setting | Type | Description |
|---|---|---|
OCRMode | string (default Auto) | Specifies how OCR (Optical Character Recognition) should process input content, offering various modes to tailor text extraction based on content type such as images, fonts, and vector graphics. For more information, see OCR Extraction Modes. |
OCRResolution | integer (default 300) | Use this parameter to change the OCR resolution from the default 300 dpi. The range is from 72 to 1200 dpi. |
RotationAngle | integer | Use manual rotation to handle PDFs with vertically drawn text. Normally, OCR automatically detects page rotation in PDFs and extracts text accurately. However, in some cases, the PDF might not have an actual rotated page --- Rather, the text itself is drawn vertically. In such scenarios, auto-detection may fail. You can use this parameter to manually set the page rotation. The available angles are: 0, 1, 2, 3. |
LineGroupingMode | string (default None) | Controls line grouping in PDF text extraction. Modes: None (no grouping), GroupByRows (merge rows if all cells align), GroupByColumns (merge cells by column), JoinOrphanedRows (merge single-cell rows to above if no separator). |
ConsiderFontColors | boolean (default false) | Controls whether font colors should be considered when detecting table structure and merging text objects during PDF extraction. Set to true to consider font colors. |
DetectNewColumnBySpacesRatio | string (default 1.2) | Controls how spaces between words are interpreted for column detection in PDF text extraction. It defines the ratio of space width that determines when text should be treated as being in separate columns. |
AutoAlignColumnsToHeader | boolean (default true) | Controls how columns are detected and aligned during table extraction from PDF documents. It affects both table structure detection and text extraction with formatting preservation. Set to true to automatically align columns to the header row. When set to true (default), the row with the most columns is used as the header, and all other rows are aligned to this structure --- ideal for well-structured tables. When set to false, columns are analyzed independently across all rows to build the structure, which works better for inconsistent or irregular tables. |
OCRImagePreprocessingFilters (object)Image preprocessing filters for OCR. Refer to OCRImagePreprocessingFilters for usage examples.Show OCRImagePreprocessingFilters properties
Show OCRImagePreprocessingFilters properties
| Setting | Type | Description |
|---|---|---|
.AddGrayscale | boolean (default false) | Converts to grayscale before OCR. |
.AddGammaCorrection | array[string (float format)] (default ["1.4"]) | Adds a gamma correction filter. |
| Setting | Type | Description |
|---|---|---|
OCRAutoModeMinExistingTextLength | integer (default 8) | The minimum number of characters a page must have to skip OCR. If a page has fewer, OCR will run. For example, if set to 8, OCR is skipped on pages with more than 8 characters. |
SaveVectors | boolean (default false) | Controls whether to save vector graphics during PDF to HTML conversion. Set to true to save vector graphics. |
SaveImages | string (default None) | Controls how images are saved during PDF to HTML conversion. Modes: None (no images), OuterFile (save to sub-folder), Embed (embed as Base64 data:URI). |
ConsiderFontSizes | boolean (default false) | Set to true to this parameter makes the converter consider font size differences in document text when detecting and parsing table structures. This can be helpful in cases where tables are formatted using different font sizes to distinguish between headers, data cells, or other structural elements. |
ExtractionArea | array[numbe] | Extract text in a specific area by defining the extraction area - set with points in the format [x, y, width, height]. |
ExtractShadowLikeText | boolean (default true) | Controls whether to extract invisible text from a PDF document. Set to false to skip over invisible text during extraction. This is particularly useful when dealing with PDFs that contain hidden text layers or when you only want to extract visible content. When this value is set to false, OCRMode must be set to Auto to properly apply the shadow text filtering effect. |
DataEncryptionAlgorithm | string | Controls the encryption algorithm used for data encryption. See User-Controlled Encryption for more information. The available algorithms are: AES128, AES192, AES256. |
DataEncryptionKey | string | Controls the encryption key used for data encryption. See User-Controlled Encryption for more information. |
DataEncryptionIV | string | Controls the encryption IV used for data encryption. See User-Controlled Encryption for more information. |
DataDecryptionAlgorithm | string | Controls the decryption algorithm used for data decryption. See User-Controlled Encryption for more information. The available algorithms are: AES128, AES192, AES256. |
DataDecryptionKey | string | Controls the decryption key used for data decryption. See User-Controlled Encryption for more information. |
DataDecryptionIV | string | Controls the decryption IV used for data decryption. See User-Controlled Encryption for more information. |
You can use profiles to control the convert process and output of the JSON file.
Line Grouping Options
"1": GroupByRows – Each row is checked against the next row to see if they can be grouped together. Rows will only be grouped if all cells in the current row can be grouped with all cells in the next row. Useful when merging related content that spans multiple lines but belongs to the same logical row."2": GroupByColumns – Each cell is checked against the cell below it in the next row to determine if they can be grouped. Cells are grouped within the same column even if others can’t be grouped. Useful for columnar data where content in each column might span multiple lines."3": JoinOrphanedRows – Joins a row with a single cell to the previous row if there is no separator between them. Useful for handling cases with orphaned or misaligned content.
OCRImagePreprocessingFilters
To set image preprocessing filters, please use:
{
"profiles": "{\"OCRImagePreprocessingFilters.AddGrayscale()\": [], \"OCRImagePreprocessingFilters.AddGammaCorrection()\": [1.4]}"
}
Responses
Synchronous response
{
"url": "https://pdf-temp-files.s3.us-west-2.amazonaws.com/example-id/sample.json",
"outputLinkValidTill": "2026-09-25T12:47:50.6815154+00:00",
"pageCount": 1,
"error": false,
"status": 200,
"name": "sample.json",
"duration": 225,
"credits": 28,
"remainingCredits": 87563
}
HTTP response metadata
Withinline: false (the default), the response contains a url to the generated JSON file, as shown above. With inline: true, the generated JSON content is returned in body instead.
| Field | Type | Description |
|---|---|---|
url | string | URL of the generated JSON file in temporary storage. |
outputLinkValidTill | string | Timestamp when the generated output link expires. |
body | object | Generated JSON content, present when inline is true. See Generated JSON content. |
pageCount | integer | Number of pages in the PDF document. |
error | boolean | Indicates whether an error occurred (false means success) |
status | integer | Status code of the request (200, 404, 500, etc.). For more information, see Response Codes. |
name | string | Name of the output file |
credits | integer | Number of credits consumed by the request |
remainingCredits | integer | Number of credits remaining in the account |
duration | integer | Time taken for the operation in milliseconds |
jobId | string | Present in the initial response when async is true. |
jobId and a reserved URL that should be used only after the job succeeds. Poll it via Background Job Check. Errors return error: true with a status code and message. See the response examples and Response Codes.
Generated JSON content
These fields belong to the generated JSON document. Withinline: false, read them from the file at url. With inline: true, read them under the response’s body field. The paths below describe the default output structure; profiles can change the generated content.
| Path in generated JSON file | Path in inline response | Type | Description |
|---|---|---|---|
document | body.document | object | Converted document and its page details. |
document.pageCount | body.document.pageCount | string | Total number of pages in the document. |
document.pageCountWithOCRPerformed | body.document.pageCountWithOCRPerformed | string | Total number of pages in the document with OCR performed. |
document.page | body.document.page | object or array[object] | Page details: an object for one page or an array for multiple pages. |
Inconsistent URL Encoding in cURL Output: When using cURL to make API requests, the output JSON may show URL characters encoded as Unicode escape sequences. For example, the ampersand character (
&) may appear as \u0026 in the cURL output. This is normal JSON encoding behavior and does not affect the validity of the URL. The URL will function correctly when used, as JSON parsers automatically decode these escape sequences. If you’re parsing the response programmatically, your JSON parser will handle this conversion automatically.Was this page helpful?