Skip to content

Commit 3f3cf11

Browse files
praveenHari24praveenHari24
authored
Merge pull request #1 from SyncfusionExamples/837695-ExtractTextSample
837695 -Added the Text Extraction sample and README file
2 parents efc6565 + 4b45d1d commit 3f3cf11

File tree

11 files changed

+274
-2
lines changed

11 files changed

+274
-2
lines changed

‎README.md‎

Lines changed: 136 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,2 +1,136 @@
1-
# how-to-extract-text-from-a-PDF-document-in-net
2-
How to Extract Text from a PDF Document in .NET using the PDF Library
1+
# How to Extract Text from a PDF Document in .NET using the PDF Library
2+
3+
## Introduction
4+
A quick start .NET console project that shows how to extract text from a PDF document using the Syncfusion PDF Library.
5+
6+
## System requirement
7+
**Framework and SDKs**
8+
* .NET SDK (version 5.0 or later)
9+
10+
**IDEs**
11+
* Visual Studio 2019/ Visual Studio 2022
12+
13+
## Extract text from a specific page
14+
We will create a new .NET console application, add the Syncfusion PDF library package, and write the code
15+
16+
```csharp
17+
//Get stream from an existing PDF document.
18+
FileStream docStream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read);
19+
//Load the PDF document.
20+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
21+
//Load the first page.
22+
PdfPageBase page = loadedDocument.Pages[0];
23+
//Extract text from first page.
24+
string extractedText = page.ExtractText();
25+
//Save the text.
26+
File.WriteAllText("Result.txt", extractedText);
27+
//Close the document.
28+
loadedDocument.Close(true);
29+
```
30+
31+
**Output Image**
32+
<img src="TextExtraction/TextExtractionSample/Output_images/Output.png" alt="output_image" width="100%" Height="Auto"/>
33+
34+
## Layout-based text extraction
35+
We will create a new .NET console application, add the Syncfusion PDF library package, and write the code
36+
37+
```csharp
38+
//Get stream from an existing PDF document.
39+
FileStream docStream = new FileStream("Invoice.pdf", FileMode.Open, FileAccess.Read);
40+
//Load the PDF document.
41+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
42+
//Load first page.
43+
PdfPageBase page = loadedDocument.Pages[0];
44+
//Extract text from first page.
45+
string extractedTexts = page.ExtractText(true);
46+
//Save the text.
47+
File.WriteAllText("data.txt", extractedTexts);
48+
//Close the document.
49+
loadedDocument.Close(true);
50+
```
51+
52+
**Output Image**
53+
<img src="TextExtraction/TextExtractionSample/Output_images/Layout-based-text-extraction.png" alt="output_image" width="100%" Height="Auto"/>
54+
55+
## Extract text from the entire PDF document
56+
We will create a new .NET console application, add the Syncfusion PDF library package, and write the code
57+
58+
```csharp
59+
//Get stream from an existing PDF document.
60+
FileStream docStream = new FileStream("Data.pdf", FileMode.Open, FileAccess.Read);
61+
//Load the PDF document.
62+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
63+
string extractedText = string.Empty;
64+
//Extract all the text from the PDF document pages.
65+
foreach (PdfLoadedPage loadedPage in loadedDocument.Pages) {
66+
extractedText += loadedPage.ExtractText();
67+
}
68+
//Save the text to file.
69+
File.WriteAllText("data.txt", extractedText);
70+
//Close the document.
71+
loadedDocument.Close(true);
72+
```
73+
74+
**Output Image**
75+
<img src="TextExtraction/TextExtractionSample/Output_images/ExtractText.png" alt="output_image" width="100%" Height="Auto"/>
76+
77+
## Extract text from predefined bounds
78+
We will create a new .NET console application, add the Syncfusion PDF library package, and write the code
79+
80+
```csharp
81+
//Get stream from an existing PDF document.
82+
FileStream docStream = new FileStream("Invoice.pdf", FileMode.Open, FileAccess.Read);
83+
//Load the PDF document.
84+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
85+
//Get the first page of the loaded PDF document.
86+
PdfPageBase page = loadedDocument.Pages[0];
87+
//Create line collection.
88+
var lineCollection = new TextLineCollection();
89+
//Extract text from the first page.
90+
page.ExtractText(out lineCollection);
91+
RectangleF textBounds = new RectangleF(474.96198f, 161.62997f, 50.040073f, 9);
92+
string invoiceNumber = "";
93+
//Get the text provided in the bounds.
94+
foreach (TextLine textLine in lineCollection.TextLine) {
95+
foreach (TextWord word in textLine.WordCollection) {
96+
if (textBounds==word.Bounds) {
97+
invoiceNumber = word.Text;
98+
break;
99+
}
100+
}
101+
}
102+
//Save the text to file.
103+
File.WriteAllText("data.txt", invoiceNumber);
104+
//Close the PDF document.
105+
loadedDocument.Close(true);
106+
```
107+
108+
**Output Image**
109+
<img src="TextExtraction/TextExtractionSample/Output_images/Extract-text-from-predefined-bounds.png" alt="output_image" width="100%" Height="Auto"/>
110+
111+
## How to run the examples
112+
* Download this project to a location in your disk.
113+
* Open the solution file using Visual Studio.
114+
* Rebuild the solution to install the required NuGet package.
115+
* Run the application.
116+
117+
## Resources
118+
* **Product page:** [Syncfusion PDF Framework](https://www.syncfusion.com/document-processing/pdf-framework/net)
119+
* **Documentation page:** [Syncfusion .NET PDF library](https://help.syncfusion.com/file-formats/pdf/overview)
120+
* **Online demo:** [Syncfusion .NET PDF library - Online demos](https://ej2.syncfusion.com/aspnetcore/PDF/CompressExistingPDF#/bootstrap5)
121+
* **Blog:** [Syncfusion .NET PDF library - Blog](https://www.syncfusion.com/blogs/category/pdf)
122+
* **Knowledge Base:** [Syncfusion .NET PDF library - Knowledge Base](https://www.syncfusion.com/kb/windowsforms/pdf)
123+
* **EBooks:** [Syncfusion .NET PDF library - EBooks](https://www.syncfusion.com/succinctly-free-ebooks)
124+
* **FAQ:** [Syncfusion .NET PDF library - FAQ](https://www.syncfusion.com/faq/)
125+
126+
## Support and feedback
127+
* For any other queries, reach our [Syncfusion support team](https://www.syncfusion.com/support/directtrac/incidents/newincident?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples) or post the queries through the [community forums](https://www.syncfusion.com/forums?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples).
128+
* Request new feature through [Syncfusion feedback portal](https://www.syncfusion.com/feedback?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples).
129+
130+
## License
131+
This is a commercial product and requires a paid license for possession or use. Syncfusion’s licensed software, including this component, is subject to the terms and conditions of [Syncfusion's EULA](https://www.syncfusion.com/eula/es/?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples). You can purchase a licnense [here](https://www.syncfusion.com/sales/products?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples) or start a free 30-day trial [here](https://www.syncfusion.com/account/manage-trials/start-trials?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples).
132+
133+
## About Syncfusion
134+
Founded in 2001 and headquartered in Research Triangle Park, N.C., Syncfusion has more than 26,000+ customers and more than 1 million users, including large financial institutions, Fortune 500 companies, and global IT consultancies.
135+
136+
Today, we provide 1600+ components and frameworks for web ([Blazor](https://www.syncfusion.com/blazor-components?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [ASP.NET Core](https://www.syncfusion.com/aspnet-core-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [ASP.NET MVC](https://www.syncfusion.com/aspnet-mvc-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [ASP.NET WebForms](https://www.syncfusion.com/jquery/aspnet-webforms-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [JavaScript](https://www.syncfusion.com/javascript-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [Angular](https://www.syncfusion.com/angular-ui-components?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [React](https://www.syncfusion.com/react-ui-components?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [Vue](https://www.syncfusion.com/vue-ui-components?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), and [Flutter](https://www.syncfusion.com/flutter-widgets?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples)), mobile ([Xamarin](https://www.syncfusion.com/xamarin-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [Flutter](https://www.syncfusion.com/flutter-widgets?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [UWP](https://www.syncfusion.com/uwp-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), and [JavaScript](https://www.syncfusion.com/javascript-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples)), and desktop development ([WinForms](https://www.syncfusion.com/winforms-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [WPF](https://www.syncfusion.com/wpf-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [WinUI(Preview)](https://www.syncfusion.com/winui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples), [Flutter](https://www.syncfusion.com/flutter-widgets?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples) and [UWP](https://www.syncfusion.com/uwp-ui-controls?utm_source=github&utm_medium=listing&utm_campaign=github-docio-examples)). We provide ready-to-deploy enterprise software for dashboards, reports, data integration, and big data processing. Many customers have saved millions in licensing fees by deploying our software.

‎TextExtraction/TextExtractionSample.sln‎

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
2+
Microsoft Visual Studio Solution File, Format Version 12.00
3+
# Visual Studio Version 17
4+
VisualStudioVersion = 17.6.33417.168
5+
MinimumVisualStudioVersion = 10.0.40219.1
6+
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "TextExtractionSample", "TextExtractionSample\TextExtractionSample.csproj", "{4C54D05A-A656-444D-9835-58E5E54436BA}"
7+
EndProject
8+
Global
9+
GlobalSection(SolutionConfigurationPlatforms) = preSolution
10+
Debug|Any CPU = Debug|Any CPU
11+
Release|Any CPU = Release|Any CPU
12+
EndGlobalSection
13+
GlobalSection(ProjectConfigurationPlatforms) = postSolution
14+
{4C54D05A-A656-444D-9835-58E5E54436BA}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
15+
{4C54D05A-A656-444D-9835-58E5E54436BA}.Debug|Any CPU.Build.0 = Debug|Any CPU
16+
{4C54D05A-A656-444D-9835-58E5E54436BA}.Release|Any CPU.ActiveCfg = Release|Any CPU
17+
{4C54D05A-A656-444D-9835-58E5E54436BA}.Release|Any CPU.Build.0 = Release|Any CPU
18+
EndGlobalSection
19+
GlobalSection(SolutionProperties) = preSolution
20+
HideSolutionNode = FALSE
21+
EndGlobalSection
22+
GlobalSection(ExtensibilityGlobals) = postSolution
23+
SolutionGuid = {7A30187C-B337-4CF6-B556-3A1BBC0FDF07}
24+
EndGlobalSection
25+
EndGlobal

‎TextExtraction/TextExtractionSample/Data.pdf‎

3.14 KB
Binary file not shown.

‎TextExtraction/TextExtractionSample/Input.pdf‎

1.85 KB
Binary file not shown.

‎TextExtraction/TextExtractionSample/Invoice.pdf‎

6.49 KB
Binary file not shown.

‎TextExtraction/TextExtractionSample/Output_images/Extract-text-from-predefined-bounds.png‎

17.6 KB
Loading

‎TextExtraction/TextExtractionSample/Output_images/ExtractText.png‎

106 KB
Loading

‎TextExtraction/TextExtractionSample/Output_images/Layout-based-text-extraction.png‎

42.9 KB
Loading

‎TextExtraction/TextExtractionSample/Output_images/Output.png‎

60.7 KB
Loading

‎TextExtraction/TextExtractionSample/Program.cs‎

Lines changed: 99 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,99 @@
1+
using Syncfusion.Pdf.Parsing;
2+
using Syncfusion.Pdf;
3+
using Syncfusion.Drawing;
4+
5+
namespace TextExtractionSample {
6+
internal class Program {
7+
static void Main(string[] args) {
8+
Syncfusion.Licensing.SyncfusionLicenseProvider.RegisterLicense("YOUR LICENSE KEY");
9+
10+
ExtractText();
11+
//Extract_Layout();
12+
//ExtractText_EntirePDF();
13+
//Extract_Bounds();
14+
15+
}
16+
/// <summary>
17+
/// Extract text from a specific page
18+
/// </summary>
19+
static void ExtractText() {
20+
//Get stream from an existing PDF document.
21+
FileStream docStream = new FileStream(Path.GetFullPath("../../../Input.pdf"), FileMode.Open, FileAccess.Read);
22+
//Load the PDF document.
23+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
24+
//Load the first page.
25+
PdfPageBase page = loadedDocument.Pages[0];
26+
//Extract text from first page.
27+
string extractedText = page.ExtractText();
28+
//Save the text.
29+
File.WriteAllText("Result.txt", extractedText);
30+
//Close the document.
31+
loadedDocument.Close(true);
32+
}
33+
/// <summary>
34+
/// Layout-based text extraction
35+
/// </summary>
36+
static void Extract_Layout() {
37+
//Get stream from an existing PDF document.
38+
FileStream docStream = new FileStream(Path.GetFullPath("../../../Invoice.pdf"), FileMode.Open, FileAccess.Read);
39+
//Load the PDF document.
40+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
41+
//Load first page.
42+
PdfPageBase page = loadedDocument.Pages[0];
43+
//Extract text from first page.
44+
string extractedTexts = page.ExtractText(true);
45+
//Save the text.
46+
File.WriteAllText("data.txt", extractedTexts);
47+
//Close the document.
48+
loadedDocument.Close(true);
49+
}
50+
/// <summary>
51+
/// Extract text from the entire PDF document
52+
/// </summary>
53+
static void ExtractText_EntirePDF() {
54+
//Get stream from an existing PDF document.
55+
FileStream docStream = new FileStream(Path.GetFullPath("../../../Data.pdf"), FileMode.Open, FileAccess.Read);
56+
//Load the PDF document.
57+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
58+
string extractedText = string.Empty;
59+
// Extract all the text from the PDF document pages.
60+
foreach (PdfLoadedPage loadedPage in loadedDocument.Pages) {
61+
extractedText += loadedPage.ExtractText();
62+
}
63+
//Save the text to file.
64+
File.WriteAllText("data.txt", extractedText);
65+
//Close the document.
66+
loadedDocument.Close(true);
67+
}
68+
/// <summary>
69+
/// Extract text from predefined bounds
70+
/// </summary>
71+
static void Extract_Bounds() {
72+
//Get stream from an existing PDF document.
73+
FileStream docStream = new FileStream(Path.GetFullPath("../../../Invoice.pdf"), FileMode.Open, FileAccess.Read);
74+
//Load the PDF document.
75+
PdfLoadedDocument loadedDocument = new PdfLoadedDocument(docStream);
76+
//Get the first page of the loaded PDF document.
77+
PdfPageBase page = loadedDocument.Pages[0];
78+
//Create line collection.
79+
var lineCollection = new TextLineCollection();
80+
//Extract text from the first page.
81+
page.ExtractText(out lineCollection);
82+
RectangleF textBounds = new RectangleF(474.96198f, 161.62997f, 50.040073f, 9);
83+
string invoiceNumber = "";
84+
//Get the text provided in the bounds.
85+
foreach (TextLine textLine in lineCollection.TextLine) {
86+
foreach (TextWord word in textLine.WordCollection) {
87+
if (textBounds==word.Bounds) {
88+
invoiceNumber = word.Text;
89+
break;
90+
}
91+
}
92+
}
93+
//Save the text.
94+
File.WriteAllText("data.txt", invoiceNumber);
95+
//Close the PDF document.
96+
loadedDocument.Close(true);
97+
}
98+
}
99+
}

0 commit comments

Comments
 (0)