Text extraction API: Extract text from PDFs and scans

curl -X POST https://api.nutrient.io/extraction/parse \
  -H "Authorization: Bearer your_api_key_goes_here" \
  -F "file=@document.pdf" \
  -F 'instructions={"mode":"text","output":{"format":"markdown"}}'

curl -X POST https://api.nutrient.io/extraction/parse ^
  -H "Authorization: Bearer your_api_key_goes_here" ^
  -F "file=@document.pdf" ^
  -F "instructions={\"mode\":\"text\",\"output\":{\"format\":\"markdown\"}}"

package com.example.nutrient;

import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

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 NutrientParseExample {
  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("mode", "text")
          .put("output", new JSONObject()
            .put("format", "markdown")
          ).toString()
      )
      .build();

    final Request request = new Request.Builder()
      .url("https://api.nutrient.io/extraction/parse")
      .method("POST", body)
      .addHeader("Authorization", "Bearer your_api_key_goes_here")
      .build();

    final OkHttpClient client = new OkHttpClient().newBuilder().build();
    final Response response = client.newCall(request).execute();

    if (response.isSuccessful()) {
      // The response is JSON. The Markdown is in output.markdown.
      final JSONObject payload = new JSONObject(response.body().string());
      final String markdown = payload
        .getJSONObject("output")
        .getString("markdown");

      Files.writeString(Paths.get("result.md"), markdown);
    } else {
      throw new IOException(response.body().string());
    }
  }
}

using System;
using System.IO;
using System.Text.Json;
using RestSharp;

namespace NutrientParseDemo
{
  class Program
  {
    static void Main(string[] args)
    {
      var client = new RestClient("https://api.nutrient.io/extraction/parse");

      var request = new RestRequest(Method.POST)
        .AddHeader("Authorization", "Bearer your_api_key_goes_here")
        .AddFile("file", "document.pdf")
        .AddParameter(
          "instructions",
          "{\"mode\":\"text\",\"output\":{\"format\":\"markdown\"}}"
        );

      var response = client.Execute(request);

      if (response.IsSuccessful)
      {
        // The response is JSON. The Markdown is in output.markdown.
        using var document = JsonDocument.Parse(response.Content);
        var markdown = document.RootElement
          .GetProperty("output")
          .GetProperty("markdown")
          .GetString();

        File.WriteAllText("result.md", markdown);
      }
      else
      {
        Console.Write(response.Content);
      }
    }
  }
}

// This code requires Node.js. Do not run this code directly in a web browser.
import fs from "node:fs";

const form = new FormData();
form.append("file", await fs.openAsBlob("document.pdf"), "document.pdf");
form.append(
  "instructions",
  JSON.stringify({ mode: "text", output: { format: "markdown" } }),
);

const response = await fetch("https://api.nutrient.io/extraction/parse", {
  method: "POST",
  headers: { Authorization: "Bearer your_api_key_goes_here" },
  body: form,
});
if (!response.ok) throw new Error(await response.text());

const result = await response.json();
fs.writeFileSync("result.md", result.output.markdown);

import requests

response = requests.post(
    "https://api.nutrient.io/extraction/parse",
    headers={"Authorization": "Bearer your_api_key_goes_here"},
    files={"file": open("document.pdf", "rb")},
    data={
        "instructions": '{"mode":"text","output":{"format":"markdown"}}'
    },
)
response.raise_for_status()

result = response.json()
print(result["output"]["markdown"])

<?php

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.nutrient.io/extraction/parse',
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_POSTFIELDS => array(
    'instructions' => '{"mode":"text","output":{"format":"markdown"}}',
    'file' => new CURLFILE('document.pdf')
  ),
  CURLOPT_HTTPHEADER => array(
    'Authorization: Bearer your_api_key_goes_here'
  ),
));

$response = curl_exec($curl);
$status = curl_getinfo($curl, CURLINFO_HTTP_CODE);

curl_close($curl);

if ($status !== 200) {
  throw new Exception($response);
}

// The response is JSON. The Markdown is in output.markdown.
$payload = json_decode($response, true);

file_put_contents('result.md', $payload['output']['markdown']);