Use Nutrient DWS to convert PDF files into HTML when the workflow needs markup output instead of static PDFs. Start with a cloud PDF-to-HTML API built for document publishing, content reuse, markup conversion, and downstream HTML workflows.
Use a PDF-to-HTML API when the workflow needs HTML and markup output for publishing, reuse, migration, and browser-facing document workflows.
Use REST, Postman, JavaScript, Python, Java, C#, PHP, or HTTP to automate PDF-to-HTML conversion inside content, publishing, and markup pipelines.
Connect HTML markup conversion to getting started, pricing, and the broader converter and markup workflows so teams can validate the right output path quickly.
This example will convert your uploaded PDF file to an HTML.
Try it out in three steps
document.pdf to your project folder.result.html in your project folder to view the results.curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer your_api_key_here" \ -o result.html \ --fail \ -F file=@document.pdf \ -F instructions='{ "parts": [ { "file": "file" } ], "output": { "type": "html" } }'curl -X POST https://api.nutrient.io/build ^ -H "Authorization: Bearer your_api_key_here" ^ -o result.html ^ --fail ^ -F file=@document.pdf ^ -F instructions="{\"parts\": [{\"file\": \"file\"}], \"output\": {\"type\": \"html\"}}"package com.example.pspdfkit;
import java.io.File;import java.io.IOException;import java.nio.file.FileSystems;import java.nio.file.Files;import java.nio.file.StandardCopyOption;
import org.json.JSONArray;import org.json.JSONObject;
import okhttp3.MediaType;import okhttp3.MultipartBody;import okhttp3.OkHttpClient;import okhttp3.Request;import okhttp3.RequestBody;import okhttp3.Response;
public final class PspdfkitApiExample { public static void main(final String[] args) throws IOException { final RequestBody body = new MultipartBody.Builder() .setType(MultipartBody.FORM) .addFormDataPart( "file", "document.pdf", RequestBody.create( MediaType.parse("application/pdf"), new File("document.pdf") ) ) .addFormDataPart( "instructions", new JSONObject() .put("parts", new JSONArray() .put(new JSONObject() .put("file", "file") ) ) .put("output", new JSONObject() .put("type", "html") ).toString() ) .build();
final Request request = new Request.Builder() .url("https://api.nutrient.io/build") .method("POST", body) .addHeader("Authorization", "Bearer your_api_key_here") .build();
final OkHttpClient client = new OkHttpClient() .newBuilder() .build();
final Response response = client.newCall(request).execute();
if (response.isSuccessful()) { Files.copy( response.body().byteStream(), FileSystems.getDefault().getPath("result.html"), StandardCopyOption.REPLACE_EXISTING ); } else { // Handle the error throw new IOException(response.body().string()); } }}using System;using System.IO;using System.Net;using RestSharp;
namespace PspdfkitApiDemo{ class Program { static void Main(string[] args) { var client = new RestClient("https://api.nutrient.io/build");
var request = new RestRequest(Method.POST) .AddHeader("Authorization", "Bearer your_api_key_here") .AddFile("file", "document.pdf") .AddParameter("instructions", new JsonObject { ["parts"] = new JsonArray { new JsonObject { ["file"] = "file" } }, ["output"] = new JsonObject { ["type"] = "html" } }.ToString());
request.AdvancedResponseWriter = (responseStream, response) => { if (response.StatusCode == HttpStatusCode.OK) { using (responseStream) { using var outputFileWriter = File.OpenWrite("result.html"); responseStream.CopyTo(outputFileWriter); } } else { var responseStreamReader = new StreamReader(responseStream); Console.Write(responseStreamReader.ReadToEnd()); } };
client.Execute(request); } }}// This code requires Node.js. Do not run this code directly in a web browser.
const axios = require('axios')const FormData = require('form-data')const fs = require('fs')
const formData = new FormData()formData.append('instructions', JSON.stringify({ parts: [ { file: "file" } ], output: { type: "html" }}))formData.append('file', fs.createReadStream('document.pdf'))
;(async () => { try { const response = await axios.post('https://api.nutrient.io/build', formData, { headers: formData.getHeaders({ 'Authorization': 'Bearer your_api_key_here' }), responseType: "stream" })
response.data.pipe(fs.createWriteStream("result.html")) } catch (e) { const errorString = await streamToString(e.response.data) console.log(errorString) }})()
function streamToString(stream) { const chunks = [] return new Promise((resolve, reject) => { stream.on("data", (chunk) => chunks.push(Buffer.from(chunk))) stream.on("error", (err) => reject(err)) stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8"))) })}import requestsimport json
response = requests.request( 'POST', 'https://api.nutrient.io/build', headers = { 'Authorization': 'Bearer your_api_key_here' }, files = { 'file': open('document.pdf', 'rb') }, data = { 'instructions': json.dumps({ 'parts': [ { 'file': 'file' } ], 'output': { 'type': 'html' } }) }, stream = True)
if response.ok: with open('result.html', 'wb') as fd: for chunk in response.iter_content(chunk_size=8096): fd.write(chunk)else: print(response.text) exit()<?php
$FileHandle = fopen('result.html', 'w+');
$curl = curl_init();
curl_setopt_array($curl, array( CURLOPT_URL => 'https://api.nutrient.io/build', CURLOPT_CUSTOMREQUEST => 'POST', CURLOPT_RETURNTRANSFER => true, CURLOPT_ENCODING => '', CURLOPT_POSTFIELDS => array( 'instructions' => '{ "parts": [ { "file": "file" } ], "output": { "type": "html" } }', 'file' => new CURLFILE('document.pdf') ), CURLOPT_HTTPHEADER => array( 'Authorization: Bearer your_api_key_here' ), CURLOPT_FILE => $FileHandle,));
$response = curl_exec($curl);
curl_close($curl);
fclose($FileHandle);POST https://api.nutrient.io/build HTTP/1.1Content-Type: multipart/form-data; boundary=--customboundaryAuthorization: Bearer your_api_key_here
--customboundaryContent-Disposition: form-data; name="instructions"Content-Type: application/json
{ "parts": [ { "file": "file" } ], "output": { "type": "html" }}--customboundaryContent-Disposition: form-data; name="file"; filename="document.pdf"Content-Type: application/pdf
(file data)--customboundary--Most common next steps
Use the following:
Get started:
Platform resources:
No input or resulting documents are stored on our infrastructure. All files are deleted as soon as a request finishes. Alternatively, check out our self-hosted product.
All communication between your application and Nutrient is done via HTTPS to ensure your data is encrypted when it’s sent to us.
All payments are handled by Paddle. Nutrient DWS Processor API never has direct access to any of your payment data.
A PDF-to-HTML API converts PDF documents into HTML markup over a REST endpoint, so you can publish, reuse, or migrate PDF content into browser-facing and downstream HTML workflows. Nutrient DWS Processor API performs the conversion server-side — no desktop software or local install required.
Yes. Conversion retains the document’s text, images, and structure so the resulting HTML reflects the original layout for publishing and content-reuse workflows.
The API is REST-based, so it works from any language that can make an HTTP request. Ready-to-use examples are available for JavaScript, Python, Java, C#, PHP, and HTTP (curl), plus a Postman collection for the fastest first request.
Conversion runs on the cloud Processor API and handles typical document workloads. For current limits and large-file handling, see the Processor API documentation.
Send the PDF to the Processor API over REST and request HTML output. The getting started guide covers API key setup, and the Postman collection gets a first conversion running quickly. See the Processor API pricing page for credit details.
Create an account to get your DWS Processor API key and start making API calls.