Use Nutrient DWS Processor API to convert PDFs to HTML for web publishing, content migration, or document review in a browser.
The /build endpoint handles PDF-to-HTML conversion. Refer to the build document endpoint API reference for request details.
Configure the conversion with these steps:
- Add the source PDF as a
partsitem. - Set
output.typetohtml.
For signup, pricing, and examples, refer to the PDF-to-HTML API overview page.
Convert a PDF to HTML
The following example converts document.pdf to result.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" } }'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--Use page layout or reflow layout
HTML output supports two layout modes:
- Page layout (
page) preserves the original page structure and separates content by page. - Reflow layout (
reflow) creates continuous content without page breaks.
Use page layout to preserve page boundaries. Use reflow layout for a web article or another continuous document.
Use this instructions object to set the layout to reflow:
{ "parts": [ { "file": "document" } ], "output": { "type": "html", "layout": "reflow" }}Convert a PDF from a URL
To convert a remotely hosted PDF, send a JSON request with the source URL in parts[].file.url:
{ "parts": [ { "file": { "url": "https://example.com/document.pdf" } } ], "output": { "type": "html", "layout": "page" }}Shell
Run this request to convert a PDF from a URL:
curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "parts": [ { "file": { "url": "https://example.com/document.pdf" } } ], "output": { "type": "html", "layout": "page" } }' \ -o result.htmlConvert selected PDF pages
Use parts[].pages to convert only a page range from the source PDF. Page indexes are zero-based, and negative values count from the end of the document.
The following example converts the first three pages to HTML:
{ "parts": [ { "file": "document", "pages": { "start": 0, "end": 2 } } ], "output": { "type": "html", "layout": "page" }}The end value is inclusive, so { "start": 0, "end": 2 } includes pages zero, one, and two.
Convert password-protected PDFs
For a password-protected PDF, include the password in the source part’s password field:
{ "parts": [ { "file": "protected_document", "password": "document-password" } ], "output": { "type": "html", "layout": "reflow" }}Nutrient DWS Processor API uses the password only to open the source document for processing.
Choose a layout
Choose the HTML layout based on how you’ll use the output.
| Layout | Use when |
|---|---|
page | Preserve the document’s page boundaries and structure. |
reflow | Create continuous HTML for content migration, web publishing, indexing, or responsive display. |
PDF uses a fixed layout, while HTML supports flowing content. Review the converted HTML for layout and content accuracy, especially for complex layouts, scanned pages, and documents with many images.
Compare PDF-to-HTML and data extraction
Use PDF-to-HTML conversion when your application needs HTML output.
Use the Data Extraction API for these outputs:
- Structured data based on document layout.
- Bounding boxes, key-value pairs, and tables.
- JSON that follows a schema.
- Markdown for retrieval-augmented generation (RAG) pipelines.
Refer to the data extraction guide for details.
Combine PDF-to-HTML with other processing
The /build endpoint supports document assembly before HTML conversion. For example, a single request can merge multiple PDFs and convert the merged document to HTML.
Use this instructions object to merge two PDFs and convert them to HTML:
{ "parts": [ { "file": "cover" }, { "file": "body" } ], "output": { "type": "html", "layout": "page" }}To select pages before conversion, set parts[].pages.
Reference
A PDF-to-HTML request uses the Build API output object with HTML output:
type HTMLOutput = { type: "html",
// The layout type to use for HTML conversion. layout?: "page" | "reflow",};
type FilePart = { // Multipart field name, or a remote URL object. file: string | { url: string },
// Optional password for encrypted input PDFs. password?: string,
// Optional page range to convert. pages?: { start?: number, end?: number, },};
type BuildInstructions = { parts: FilePart[], output: HTMLOutput,};Related API reference operations
Refer to the build document endpoint API reference for conversion, page selection, and document assembly options.
Related guides
Use these resources for other conversion and processing tasks:
- Refer to the PDF-to-Markdown API conversion overview page for Markdown output with the Data Extraction API.
- Refer to the editable document conversion guide for Word, Excel, and PowerPoint output.
- Refer to the convert to images guide.
- Refer to the optical character recognition guide.
- Refer to the merge documents guide.
- Refer to the split documents guide.
- Refer to the tools and endpoints guide.