Extract text from PDF API

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.json \
  --fail \
  -F [email protected] \
  -F instructions='{
      "parts": [
        {
          "file": "document"
        }
      ],
      "output": {
        "type": "json-content",
        "plainText": true,
        "structuredText": true
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.json ^
  --fail ^
  -F [email protected] ^
  -F instructions="{\"parts\": [{\"file\": \"document\"}], \"output\": {\"type\": \"json-content\", \"plainText\": true, \"structuredText\": true}}"

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(
        "document",
        "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", "document")
            )
          )
          .put("output", new JSONObject()
            .put("type", "json-content")
            .put("plainText", true)
            .put("structuredText", true)
          ).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.json"),
        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("document", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "document"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "json-content",
            ["plainText"] = true,
            ["structuredText"] = true
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.json");
            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: "document"
    }
  ],
  output: {
    type: "json-content",
    plainText: true,
    structuredText: true
  }
}))
formData.append('document', 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.json"))
  } 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 requests
import json

response = requests.request(
  'POST',
  'https://api.nutrient.io/build',
  headers = {
    'Authorization': 'Bearer your_api_key_here'
  },
  files = {
    'document': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'document'
        }
      ],
      'output': {
        'type': 'json-content',
        'plainText': True,
        'structuredText': True
      }
    })
  },
  stream = True
)

if response.ok:
  with open('result.json', 'wb') as fd:
    for chunk in response.iter_content(chunk_size=8096):
      fd.write(chunk)
else:
  print(response.text)
  exit()

<?php

$FileHandle = fopen('result.json', '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": "document"
        }
      ],
      "output": {
        "type": "json-content",
        "plainText": true,
        "structuredText": true
      }
    }',
    'document' => 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/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here

--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json

{
  "parts": [
    {
      "file": "document"
    }
  ],
  "output": {
    "type": "json-content",
    "plainText": true,
    "structuredText": true
  }
}
--customboundary
Content-Disposition: form-data; name="document"; filename="document.pdf"
Content-Type: application/pdf

(document data)
--customboundary--