Parsing and reading data from Airline Tickets - C#
Document Parser sample in C# demonstrating ‘Parsing and reading data from Airline Tickets’
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 = @".\SampleTicket.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(@".\SampleTicket.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 for `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"]);
}
}
}
SampleTicket.yml
templateName: MakeMyTrip Booking
templateVersion: 4
templatePriority: 0
detectionRules:
keywords:
- MakeMyTrip
- Eticket-Dom-Flight
objects:
- name: BookingNo
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 198.75
- 85.625
- 96.875
- 12.500001
pageIndex: 0
- name: BookingDate
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
dataType: date
rectangle:
- 133.125
- 97.5000076
- 78.75
- 12.500001
pageIndex: 0
- name: DepartureFrom
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 153
- 176
- 77
- 8.5
pageIndex: 0
- name: ArrivalTo
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 285
- 176
- 84
- 8.5
pageIndex: 0
- name: DepartureAt
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
dataType: date
rectangle:
- 153.75
- 187.5
- 123.75
- 10.625
pageIndex: 0
- name: ArrivalAt
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
dataType: date
rectangle:
- 288.125
- 186.875
- 125.625008
- 11.25
pageIndex: 0
- name: FlightType
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 433.5
- 159.5
- 68
- 10.5
pageIndex: 0
- name: FlightDuration
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 474.375031
- 170.625
- 30.0000019
- 10
pageIndex: 0
- name: CabinType
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 463.125031
- 194.375015
- 51.25
- 10
pageIndex: 0
- name: PassengerName
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 85
- 238.125
- 93.125
- 14.375
pageIndex: 0
- name: PassengerType
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 229.375015
- 238.125
- 31.25
- 13.75
pageIndex: 0
- name: AirlinePNR
objectType: field
fieldProperties:
fieldType: rectangle
regex: true
rectangle:
- 375
- 240.000015
- 46.25
- 13.75
pageIndex: 0
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.