Parse Simple Document - C#
Document Parser sample in C# demonstrating ‘Parse Simple Document’
AmazonAWS.yml
templateName: Amazon Web Services Invoice
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- Amazon Web Services
- ATTN
- Invoice
objects:
- name: total
objectType: field
fieldProperties:
fieldType: macros
expression: TOTAL AMOUNT DUE ON{{Anything}}{{Dollar}}({{Number}})
regex: true
dataType: decimal
- name: subTotal
objectType: field
fieldProperties:
fieldType: macros
expression: '{{LineStart}}{{Spaces}}Charges{{Spaces}}{{Dollar}}({{Number}})'
regex: true
dataType: decimal
- name: dateIssued
objectType: field
fieldProperties:
fieldType: macros
expression: Invoice Date:{{Spaces}}({{Anything}}){{LineEnd}}
regex: true
dataType: date
dateFormat: MMMM d , yyyy
- name: invoiceId
objectType: field
fieldProperties:
fieldType: macros
expression: Invoice Number:{{Spaces}}({{Digits}})
regex: true
- name: companyName
objectType: field
fieldProperties:
fieldType: static
expression: Amazon Web Services, Inc.
regex: true
- name: companyWebsite
objectType: field
fieldProperties:
fieldType: static
expression: aws.amazon.com
regex: true
- name: billTo
objectType: field
fieldProperties:
fieldType: rectangle
expression: Bill to Address:{{ToggleSingleLineMode}}({{AnythingGreedy}})
regex: true
rectangle:
- 33
- 115.5
- 213.75
- 72.75
pageIndex: 0
- name: currency
objectType: field
fieldProperties:
fieldType: static
expression: USD
regex: true
- name: table1
objectType: table
tableProperties:
start:
expression: '{{LineStart}}{{Spaces}}Detail{{LineEnd}}'
regex: true
end:
expression: '{{EndOfPage}}'
regex: true
row:
expression: '{{LineStart}}{{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}{{Dollar}}(?<unitPrice>{{Number}}){{LineEnd}}'
regex: true
columns:
- name: unitPrice
dataType: decimal
DigitalOcean.yml
templateName: DigitalOcean Invoice
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- DigitalOcean
- 101 Avenue of the Americas
- Invoice Number
objects:
- name: companyName
objectType: field
fieldProperties:
fieldType: static
expression: DigitalOcean
regex: true
- name: invoiceId
objectType: field
fieldProperties:
fieldType: macros
expression: 'Invoice Number: ({{Digits}})'
regex: true
- name: dateIssued
objectType: field
fieldProperties:
fieldType: macros
expression: 'Date Issued: ({{SmartDate}})'
regex: true
dataType: date
dateFormat: auto-mdy
- name: total
objectType: field
fieldProperties:
fieldType: macros
expression: 'Total: {{Dollar}}({{Number}})'
regex: true
dataType: decimal
- name: currency
objectType: field
fieldProperties:
fieldType: static
expression: USD
regex: true
- name: table1
objectType: table
tableProperties:
start:
expression: Description{{Spaces}}Hours
regex: true
end:
expression: 'Total:'
regex: true
row:
expression: '{{LineStart}}{{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<hours>{{Digits}}){{Spaces}}(?<start>{{2Digits}}{{Minus}}{{2Digits}}{{Space}}{{2Digits}}{{Colon}}{{2Digits}}){{Spaces}}(?<end>{{2Digits}}{{Minus}}{{2Digits}}{{Space}}{{2Digits}}{{Colon}}{{2Digits}}){{Spaces}}{{Dollar}}(?<unitPrice>{{Number}})'
regex: true
columns:
- name: hours
dataType: integer
- name: unitPrice
dataType: decimal
Google.yml
templateName: Google Invoice
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- Google
- 77-0493581
- Invoice
objects:
- name: invoiceId
objectType: field
fieldProperties:
expression: Invoice number:{{Spaces}}({{Digits}})
regex: true
- name: dateIssued
objectType: field
fieldProperties:
expression: Issue date:{{Spaces}}({{SmartDate}})
regex: true
dataType: date
dateFormat: MMM d, yyyy
- name: total
objectType: field
fieldProperties:
expression: Amount due in USD:{{Spaces}}{{Number}}
regex: true
dataType: decimal
- name: subTotal
objectType: field
fieldProperties:
expression: Subtotal in USD:{{Spaces}}{{Number}}
regex: true
dataType: decimal
- name: taxRate
objectType: field
fieldProperties:
expression: State sales tax {{OpeningParenthesis}}{{Digits}}{{Percent}}{{ClosingParenthesis}}
regex: true
dataType: integer
- name: tax
objectType: field
fieldProperties:
expression: State sales tax{{Anything}}{{Number}}{{LineEnd}}
regex: true
dataType: decimal
- name: companyName
objectType: field
fieldProperties:
fieldType: static
expression: Google LLC
regex: true
- name: billTo
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 0
- 152
- 280
- 72
pageIndex: 0
- name: billingId
objectType: field
fieldProperties:
expression: Billing ID:{{Spaces}}({{DigitsOrSymbols}})
regex: true
- name: currency
objectType: field
fieldProperties:
fieldType: static
expression: USD
regex: true
- name: table1
objectType: table
tableProperties:
start:
expression: Description{{Spaces}}Interval{{Spaces}}Quantity{{Spaces}}Amount
regex: true
end:
expression: Subtotal in USD
regex: true
row:
expression: '{{LineStart}}{{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<interval>{{3Letters}}{{Space}}{{Digits}}{{Space}}{{Minus}}{{Space}}{{3Letters}}{{Space}}{{Digits}}){{Spaces}}(?<quantity>{{Digits}}){{Spaces}}(?<amount>{{Number}})'
regex: true
columns:
- name: quantity
dataType: integer
- name: amount
dataType: decimal
Program.cs
using Newtonsoft.Json;
using Newtonsoft.Json.Linq;
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using System.Threading;
// Cloud API asynchronous "Document Parser" job example.
// Allows to avoid timeout errors when processing huge or scanned PDF documents.
namespace ByteScoutWebApiExample
{
class Program
{
// The authentication key (API Key).
// Get your own by registering at https://app.pdf.co
const String API_KEY = "*************************";
// Source PDF file
const string SourceFile = @".\AmazonAWS.pdf";
//const string SourceFile = @".\DigitalOcean.pdf";
//const string SourceFile = @".\Google.pdf";
// PDF document password. Leave empty for unprotected documents.
const string Password = "";
// Destination TXT file name
const string DestinationFile = @".\result.json";
// (!) Make asynchronous job
const bool Async = true;
static void Main(string[] args)
{
// Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
// to create templates.
// Read template from file:
String templateText = File.ReadAllText(@".\AmazonAWS.yml");
//String templateText = File.ReadAllText(@".\DigitalOcean.yml");
//String templateText = File.ReadAllText(@".\Google.yml");
// Create standard .NET web client instance
WebClient webClient = new WebClient();
// Set API Key
webClient.Headers.Add("x-api-key", API_KEY);
// 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 = Uri.EscapeUriString(string.Format(
"https://api.pdf.co/v1/file/upload/get-presigned-url?contenttype=application/octet-stream&name={0}",
Path.GetFileName(SourceFile)));
try
{
// Execute request
string response = webClient.DownloadString(query);
// Parse JSON response
JObject json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Get URL to use for the file upload
string uploadUrl = json["presignedUrl"].ToString();
string uploadedFileUrl = json["url"].ToString();
// 2. UPLOAD THE FILE TO CLOUD.
webClient.Headers.Add("content-type", "application/octet-stream");
webClient.UploadFile(uploadUrl, "PUT", SourceFile); // You can use UploadData() instead if your file is byte[] or Stream
webClient.Headers.Remove("content-type");
// 3. PARSE UPLOADED PDF DOCUMENT
// URL of `Document Parser` API call
string url = "https://api.pdf.co/v1/pdf/documentparser";
Dictionary<string, object> requestBody = new Dictionary<string, object>();
requestBody.Add("template", templateText);
requestBody.Add("name", Path.GetFileName(DestinationFile));
requestBody.Add("url", uploadedFileUrl);
requestBody.Add("async", Async);
// Convert dictionary of params to JSON
string jsonPayload = JsonConvert.SerializeObject(requestBody);
// Execute request
response = webClient.UploadString(url, "POST", jsonPayload);
// Parse JSON response
json = JObject.Parse(response);
if (json["error"].ToObject<bool>() == false)
{
// Asynchronous job ID
string jobId = json["jobId"].ToString();
// Get URL of generated JSON file
string resultFileUrl = json["url"].ToString();
// Check the job status in a loop.
// If you don't want to pause the main thread you can rework the code
// to use a separate thread for the status checking and completion.
do
{
string status = CheckJobStatus(webClient, jobId); // Possible statuses: "working", "failed", "aborted", "success".
// Display timestamp and status (for demo purposes)
Console.WriteLine(DateTime.Now.ToLongTimeString() + ": " + status);
if (status == "success")
{
// Download JSON file
webClient.DownloadFile(resultFileUrl, DestinationFile);
Console.WriteLine("Generated JSON file saved as \"{0}\" file.", DestinationFile);
break;
}
else if (status == "working")
{
// Pause for a few seconds
Thread.Sleep(3000);
}
else
{
Console.WriteLine(status);
break;
}
}
while (true);
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
else
{
Console.WriteLine(json["message"].ToString());
}
}
catch (WebException e)
{
Console.WriteLine(e.ToString());
}
webClient.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static string CheckJobStatus(WebClient webClient, string jobId)
{
string url = "https://api.pdf.co/v1/job/check?jobid=" + jobId;
string response = webClient.DownloadString(url);
JObject json = JObject.Parse(response);
return Convert.ToString(json["status"]);
}
}
}
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.