OCR API Java: Extract Text and Data from PDFs and Images

import java.net.URI;
import java.net.http.*;
import java.nio.file.*;

// Multipart upload omitted for brevity; JSON parsed with your library of choice.
String apiKey = "YOUR_API_KEY";
String base = "https://docuocr.com/api/documents";
HttpClient http = HttpClient.newHttpClient();

// 1. Upload the PDF or image, get a file_id (multipart body built with a boundary)
HttpRequest upload = HttpRequest.newBuilder(URI.create(base + "/upload"))
    .header("Authorization", "Bearer " + apiKey)
    .header("Content-Type", "multipart/form-data; boundary=X")
    .POST(HttpRequest.BodyPublishers.ofByteArray(multipart("invoice.pdf")))
    .build();
String fileId = json(http.send(upload, HttpResponse.BodyHandlers.ofString()).body(), "file_id");

// 2. Start extraction, get a job hash
HttpRequest extract = HttpRequest.newBuilder(URI.create(base + "/extract"))
    .header("Authorization", "Bearer " + apiKey)
    .header("Content-Type", "application/json")
    .POST(HttpRequest.BodyPublishers.ofString("{\"file_id\":\"" + fileId + "\"}"))
    .build();
String hash = json(http.send(extract, HttpResponse.BodyHandlers.ofString()).body(), "extraction_hash");

// 3. Poll until the JSON is ready
HttpRequest get = HttpRequest.newBuilder(URI.create(base + "/extraction/" + hash))
    .header("Authorization", "Bearer " + apiKey).build();
String body;
do {
    Thread.sleep(2000);
    body = http.send(get, HttpResponse.BodyHandlers.ofString()).body();
} while (!json(body, "status").equals("completed"));

// body now holds fields, tables and confidence as JSON, ready to map with Jackson
System.out.println(body);