Advanced Conversion Options - Java
PDF To JSON sample in Java demonstrating ‘Advanced Conversion Options’
Main.java
package com.company;
import com.google.gson.JsonObject;
import com.google.gson.JsonParser;
import okhttp3.*;
import java.io.*;
import java.net.*;
import java.nio.file.Path;
import java.nio.file.Paths;
public class Main
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
final static String API_KEY = "***********************************";
// Source PDF file
final static Path SourceFile = Paths.get(".\\sample.pdf");
// Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
final static String Pages = "";
// PDF document password. Leave empty for unprotected documents.
final static String Password = "";
// Destination JSON file name
final static Path DestinationFile = Paths.get(".\\result.json");
public static void main(String[] args) throws IOException
{
// Create HTTP client instance
OkHttpClient webClient = new OkHttpClient();
// 1. RETRIEVE THE PRESIGNED URL TO UPLOAD THE FILE.
// * If you already have a direct file URL, skip to the step 3.
// Prepare URL for `Get Presigned URL` API call
String query = String.format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name=%s",
SourceFile.getFileName());
// Prepare request
Request request = new Request.Builder()
.url(query)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL to use for the file upload
String uploadUrl = json.get("presignedUrl").getAsString();
// Get URL of uploaded file to use with later API calls
String uploadedFileUrl = json.get("url").getAsString();
// 2. UPLOAD THE FILE TO CLOUD.
if (uploadFile(webClient, API_KEY, uploadUrl, SourceFile))
{
// 3. CONVERT UPLOADED PDF FILE TO JSON
PdfToJson(webClient, API_KEY, DestinationFile, Password, Pages, uploadedFileUrl);
}
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static void PdfToJson(OkHttpClient webClient, String apiKey, Path destinationFile,
String password, String pages, String uploadedFileUrl) throws IOException
{
/*
Some of advanced options available through profiles:
(it can be single/double-quoted and contain comments.)
{
"profiles": [
{
"profile1": {
"SaveImages": "None", // Whether to extract images. Values: "None", "Embed".
"ImageFormat": "PNG", // Image format for extracted images. Values: "PNG", "JPEG", "GIF", "BMP".
"SaveVectors": false, // Whether to extract vector objects (vertical and horizontal lines). Values: true / false
"ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
"ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
"LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
"ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
"Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
"ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
"DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
"CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
"CheckPermissions": true, // Ignore document permissions. Values: true / false
}
}
]
}
*/
// Sample profile that sets advanced conversion options
// Advanced options are properties of JSONExtractor class from ByteScout JSON Extractor SDK used in the back-end:
// https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/84356d44-6249-3251-2da8-83c1f34a2f39.htm
String profiles = "{ 'profiles': [ { 'profile1': { 'TrimSpaces': 'False', 'PreserveFormattingOnTextExtraction': 'True' } } ] }";
// Prepare URL for `PDF To JSON` API call
String query = "https://api.pdf.co/v1/pdf/convert/to/json";
// Make correctly escaped (encoded) URL
URL url = null;
try
{
url = new URI(null, query, null).toURL();
}
catch (URISyntaxException e)
{
e.printStackTrace();
}
// Create JSON payload
String jsonPayload = String.format("{\"name\": \"%s\", \"password\": \"%s\", \"pages\": \"%s\", \"url\": \"%s\", \"profiles\": \"%s\"}",
destinationFile.getFileName(),
password,
pages,
uploadedFileUrl,
profiles);
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/json"), jsonPayload);
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", API_KEY) // (!) Set API Key
.addHeader("Content-Type", "application/json")
.post(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
if (response.code() == 200)
{
// Parse JSON response
JsonObject json = new JsonParser().parse(response.body().string()).getAsJsonObject();
boolean error = json.get("error").getAsBoolean();
if (!error)
{
// Get URL of generated JSON file
String resultFileUrl = json.get("url").getAsString();
// Download JSON file
downloadFile(webClient, resultFileUrl, destinationFile.toFile());
System.out.printf("Generated JSON file saved as \"%s\" file.", destinationFile.toString());
}
else
{
// Display service reported error
System.out.println(json.get("message").getAsString());
}
}
else
{
// Display request error
System.out.println(response.code() + " " + response.message());
}
}
public static boolean uploadFile(OkHttpClient webClient, String apiKey, String url, Path sourceFile) throws IOException
{
// Prepare request body
RequestBody body = RequestBody.create(MediaType.parse("application/octet-stream"), sourceFile.toFile());
// Prepare request
Request request = new Request.Builder()
.url(url)
.addHeader("x-api-key", apiKey) // (!) Set API Key
.addHeader("content-type", "application/octet-stream")
.put(body)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
return (response.code() == 200);
}
public static void downloadFile(OkHttpClient webClient, String url, File destinationFile) throws IOException
{
// Prepare request
Request request = new Request.Builder()
.url(url)
.build();
// Execute request
Response response = webClient.newCall(request).execute();
byte[] fileBytes = response.body().bytes();
// Save downloaded bytes to file
OutputStream output = new FileOutputStream(destinationFile);
output.write(fileBytes);
output.flush();
output.close();
response.close();
}
}
PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.
Download Source Code (.zip)
return to the previous page explore PDF To JSON endpoint
Copyright © 2016 - 2024 PDF.co