PDF.co Web API - Document Parser API - Salesforce - Document Parser Demo

printable version:
PDF-co-Web-API-Salesforce-Document-Parser-Demo.pdf

document parser API in Salesforce and PDF.co Web API

PDF.co Web API is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, can generate and read barcodes from images, scans and pdf.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

DocumentParserOutputAsJSON.cls

      public class DocumentParserOutputAsJSON {
    // The authentication key (API Key).
    // Get your own by registering at https://app.pdf.co/documentation/api
    static String API_KEY = '***********************';
    
    // Direct URL of source PDF file.
    static string SourceFileUrl = 'https://bytescout-com.s3-us-west-2.amazonaws.com/files/demo-files/cloud-api/document-parser/sample-invoice.pdf';
    // PDF document password. Leave empty for unprotected documents.
    static string Password = '';

    @TestVisible
    String jsonOutput;
    public void parseDocumentAsJSON()
    {        
        try
        {
            // Create HTTP client instance
            Http http = new Http();
            HttpRequest request = new HttpRequest();
            // Set API Key
            request.setHeader('x-api-key', API_KEY);
            
            Boolean async = false;
            String inline = 'true';
            String profiles = '';
            Boolean encrypt = false;
            Boolean storeResult = false;
            // Prepare requests params as JSON
            // See documentation: https://apidocs.pdf.co
            // Create JSON payload
            JSONGenerator gen = JSON.createGenerator(true);
            gen.writeStartObject();
            gen.writeStringField('url', SourceFileUrl);
            gen.writeStringField('outputFormat', 'JSON');
            gen.writeStringField('templateId', '1');
            gen.writeBooleanField('async', async);
            gen.writeBooleanField('encrypt', encrypt);
            gen.writeStringField('inline', inline);
            gen.writeStringField('password', password);
            gen.writeStringField('profiles', profiles);
            gen.writeBooleanField('storeResult', false);
            
            gen.writeEndObject();
            // Convert dictionary of params to JSON
            String jsonPayload = gen.getAsString();
        
            // URL of 'PDF Edit' endpoint
            string url = 'https://api.pdf.co/v1/pdf/documentparser';
            request.setEndpoint(url);            
            request.setHeader('Content-Type', 'application/json;charset=UTF-8');
            request.setMethod('POST');
            request.setBody(jsonPayload);
            // Execute request
            HttpResponse response =  http.send(request);                
            
            if(response.getStatusCode() == 200)
            {
                // Parse JSON response
                Map<String, Object> json = (Map<String, Object>)JSON.deserializeUntyped(response.getBody());
                if ((Boolean)json.get('error') == false)
                {
                    jsonOutput = response.getBody();
                    System.debug('JSON '+ jsonOutput);    
                }
            }
            else
            {
                System.debug('Error Response ' + response.getBody());
                System.Debug(' Status ' + response.getStatus());
                System.Debug(' Status Code' + response.getStatusCode());
                System.Debug(' Response String' + response.toString());
            }
        }
        catch (Exception ex)
        {
            String errorBody = 'Message: ' + ex.getMessage() + ' -- Cause: ' + ex.getCause() + ' -- Stacktrace: ' + ex.getStackTraceString();
            System.Debug(errorBody);
        }
    }
}

DocumentParserOutputAsJSONTest.cls

      @isTest
public class DocumentParserOutputAsJSONTest
{
    private  testmethod static void testparseDocumentAsJSON()
    {
        Test.setMock(HttpCalloutMock.class, new DocumentParserOutputAsJSONTest.DocumentCreationMock());
        DocumentParserOutputAsJSON docParse = new DocumentParserOutputAsJSON();
        docParse.parseDocumentAsJSON();
        System.assert(docParse.jsonOutput.contains('John A. Doe'));
    }

    private  testmethod static void testparseDocumentAsJSONException()
    {
        DocumentParserOutputAsJSON docParse = new DocumentParserOutputAsJSON();
        docParse.parseDocumentAsJSON();
        System.assert(null == docParse.jsonOutput);
    }    
   
    public class DocumentCreationMock implements HttpCalloutMock {
        public HTTPResponse respond(HTTPRequest req) {
            HttpResponse res = new HttpResponse();
            String testBody = '{"hash":"John A. Doe","url":"https://pdf-temp-files.s3-us-west-2.amazonaws.com/0c336bfcef1a473d98492bda25d8da03/newDocument.pdf?X-Amz-Expires=3600&x-amz-security-token=FwoGZXIvYXdzEO7%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaDHWK1dY4d4lOgsheliKBATwE%2FZewASPTEnPxTn%2BOdYhP4h3gljAJfqbRvQptDX7wdWLmrBS7Tg4qTU6pAbxIdXChGPjBWpSbtiADJKmqkmyhkUmE8GSM1%2FGtJO6bga2pgzvFLXmzxjTf3%2BFNqwYOvbyApIZdVLoPpEKY6PlCflQtLTd30dhelm6xpB8pitbdhSjdz8KCBjIobVy%2Fjwybwp6OQgB%2FT6QkIo2dU07gtFREdn5jhRyvnS5lkccweBV1%2Bw%3D%3D&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=ASIA4NRRSZPHMV5P3JOS/20210316/us-west-2/s3/aws4_request&X-Amz-Date=20210316T124309Z&X-Amz-SignedHeaders=host;x-amz-security-token&X-Amz-Signature=95287bf3c007fed4c2c5aeea1ce75c846cc6c68b22aaf35175ebe41a105f54e1","pageCount":1,"error":false,"status":200,"name":"newDocument","remainingCredits":9913694,"credits":3}';
            res.setHeader('Content-Type', 'application/json');
            res.setBody(testBody);
            res.setStatusCode(200);
            return res;
        }
    }
}