From 5b322b67ff2e456a488f0fc748afb6a1dd374b2c Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Thu, 1 Oct 2026 13:44:04 +0530 Subject: [PATCH 1/6] 1058154: Added the README.md for newly added Data Extractor sample --- .../Convert-data-as-HTML-from-PDF/README.md | 37 ++++++++++++++++++ .../Convert-data-as-Word-from-PDF/README.md | 38 +++++++++++++++++++ 2 files changed, 75 insertions(+) create mode 100644 Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md create mode 100644 Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md new file mode 100644 index 00000000..50a991a9 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md @@ -0,0 +1,37 @@ +# Extract Structured Data from PDF as HTML + +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into HTML for easy viewing, editing, and sharing. + +## Steps to Extract Data as HTML from PDF Files + +Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. + +Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartDataExtractor.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/). + +Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file: + +```csharp +using System.IO; +using System.Text; +using Syncfusion.SmartDataExtractor; + +``` + +Step 4: Add the following code snippet in Program.cs file to extract data from PDF. + +```csharp +// Open the input PDF file as a stream. +using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.Read)) +{ + // Initialize the Smart Data Extractor. + DataExtractor extractor = new DataExtractor(); + // Extract data as HTML. + string htmlContent = extractor.ExtractDataAsHtml(stream); + // Save the extracted HTML data into an output file. + File.WriteAllText(Path.GetFullPath(@"Output/Output.html"), htmlContent); +} + +``` +For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET). + +More information about Extract data from PDF can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/net/conversions/pdf-to-word#convert-pdf-or-image-to-html-document) section. \ No newline at end of file diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md new file mode 100644 index 00000000..b6fe4963 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md @@ -0,0 +1,38 @@ +# Extract Structured Data from PDF as Word + +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into a Word document for easy editing, formatting, and sharing. + +## Steps to Extract Data as Word from PDF Files + +Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. + +Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartDataExtractor.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/). + +Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file: + +```csharp +using System.IO; +using Syncfusion.DocIO.DLS; +using Syncfusion.SmartDataExtractor; + +``` + +Step 4: Add the following code snippet in Program.cs file to extract data from PDF. + +```csharp +// Open the input PDF file as a stream. +using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.ReadWrite)) +{ + // Initialize the Smart Data Extractor. + DataExtractor extractor = new DataExtractor(); + // Extract data as a Word document. + WordDocument word = extractor.ExtractDataAsWordDocument(stream); + // Save the extracted Word data into an output file. + word.Save(Path.GetFullPath(@"Output/Output.docx")); + word.Close(); +} + +``` +For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET). + +More information about Extract data from PDF can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/net/conversions/pdf-to-word#convert-pdf-or-image-to-word-document) section. \ No newline at end of file From 4e116eb4d0d2bd6c7713b85cadd71074e4776688 Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Thu, 1 Oct 2026 13:52:05 +0530 Subject: [PATCH 2/6] added changes --- .../Convert-data-as-HTML-from-PDF/README.md | 23 +++++++++---------- .../Convert-data-as-Word-from-PDF/README.md | 19 ++++++++------- 2 files changed, 20 insertions(+), 22 deletions(-) diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md index 50a991a9..68d0da13 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md @@ -11,24 +11,23 @@ Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Ne Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file: ```csharp -using System.IO; -using System.Text; + using Syncfusion.SmartDataExtractor; ``` - Step 4: Add the following code snippet in Program.cs file to extract data from PDF. ```csharp -// Open the input PDF file as a stream. -using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.Read)) -{ - // Initialize the Smart Data Extractor. - DataExtractor extractor = new DataExtractor(); - // Extract data as HTML. - string htmlContent = extractor.ExtractDataAsHtml(stream); - // Save the extracted HTML data into an output file. - File.WriteAllText(Path.GetFullPath(@"Output/Output.html"), htmlContent); + +//Open the input PDF file as a stream. +using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read)) +{ + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as HTML. + string htmlContent = extractor.ExtractDataAsHtml(stream); + //Save the extracted data into the HTML file. + File.WriteAllText("Output.html", htmlContent); } ``` diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md index b6fe4963..977f14e1 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md @@ -11,7 +11,6 @@ Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Ne Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file: ```csharp -using System.IO; using Syncfusion.DocIO.DLS; using Syncfusion.SmartDataExtractor; @@ -20,16 +19,16 @@ using Syncfusion.SmartDataExtractor; Step 4: Add the following code snippet in Program.cs file to extract data from PDF. ```csharp -// Open the input PDF file as a stream. -using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.ReadWrite)) +//Open the input PDF file as a stream. +using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read)) { - // Initialize the Smart Data Extractor. - DataExtractor extractor = new DataExtractor(); - // Extract data as a Word document. - WordDocument word = extractor.ExtractDataAsWordDocument(stream); - // Save the extracted Word data into an output file. - word.Save(Path.GetFullPath(@"Output/Output.docx")); - word.Close(); + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as WordDocument. + WordDocument word = extractor.ExtractDataAsWordDocument(stream); + //Save the extracted Word data into an output file. + word.Save("Output.docx"); + word.Close(); } ``` From dd3b8bd415a42e2fa5bd74133677be6a8b489b19 Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Thu, 1 Oct 2026 13:56:47 +0530 Subject: [PATCH 3/6] Added readme for Barcode recognition sample --- .../.NET/Barcode-recognition/README.md | 37 +++++++++++++++++++ 1 file changed, 37 insertions(+) create mode 100644 Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md diff --git a/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md b/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md new file mode 100644 index 00000000..ca7a94b3 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md @@ -0,0 +1,37 @@ +# Extract Structured Data from PDF + +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It can also help recognize barcode content and return structured JSON with per-field confidence scores. + +## Steps to Extract Structured Data from PDF Files + +Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. + +Step 2: **Install the NuGet package:** Add the [Syncfusion.SmartDataExtractor.Net.Core](https://www.nuget.org/packages/Syncfusion.SmartDataExtractor.Net.Core) package to your project from [NuGet.org](https://www.nuget.org/). + +Step 3: **Include necessary namespaces:** Add these namespaces in your Program.cs file: + +```csharp +using System.IO; +using System.Text; +using Syncfusion.SmartDataExtractor; + +``` + +Step 4: Add the following code snippet in Program.cs file to extract data from PDF. + +```csharp +// Open the input PDF file as a stream. +using (FileStream stream = new FileStream(Path.GetFullPath("Input.pdf"), FileMode.Open, FileAccess.Read)) +{ + // Initialize the Smart Data Extractor. + DataExtractor extractor = new DataExtractor(); + // Extract data as JSON. + string data = extractor.ExtractDataAsJson(stream); + // Save the extracted JSON data into an output file. + File.WriteAllText(Path.GetFullPath(@"Output/Output.json"), data, Encoding.UTF8); +} + +``` +For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET). + +More information about Extract data from PDF can be refer in this [documentation](https://help.syncfusion.com/document-processing/data-extraction/net/working-with-data-extraction) section. \ No newline at end of file From 7ae2f256494130468e2777a4b8f8d38fd436372a Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Tue, 6 Oct 2026 15:12:36 +0530 Subject: [PATCH 4/6] added changes --- .../Convert-data-as-Word-from-PDF/README.md | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md index 977f14e1..c26ecfbd 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md @@ -20,17 +20,19 @@ Step 4: Add the following code snippet in Program.cs file to extract data from P ```csharp //Open the input PDF file as a stream. + using (FileStream stream = new FileStream("Input.pdf", FileMode.Open, FileAccess.Read)) { - //Initialize the Data Extractor. - DataExtractor extractor = new DataExtractor(); - //Extract data as WordDocument. - WordDocument word = extractor.ExtractDataAsWordDocument(stream); - //Save the extracted Word data into an output file. - word.Save("Output.docx"); - word.Close(); -} + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as WordDocument. + WordDocument document = extractor.ExtractDataAsWordDocument(stream); + using MemoryStream saveStream = new MemoryStream(); + //Save the extracted Word data into an output file. + document.Save(saveStream, FormatType.Docx); + document.Close(); +} ``` For a complete working example, download it from [GitHub](https://github.com/SyncfusionExamples/PDF-Examples/tree/master/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET). From 6e6bd659fb11ea370780ce6ce8bfbd517da437f9 Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Tue, 6 Oct 2026 17:10:31 +0530 Subject: [PATCH 5/6] Addressed feedbacks --- .../Barcode-recognition/.NET/Barcode-recognition/README.md | 6 +++--- .../.NET/Convert-data-as-HTML-from-PDF/README.md | 6 +++--- .../.NET/Convert-data-as-Word-from-PDF/README.md | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md b/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md index ca7a94b3..32346a6a 100644 --- a/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Barcode-recognition/.NET/Barcode-recognition/README.md @@ -1,8 +1,8 @@ -# Extract Structured Data from PDF +# Recognize Barcodes from PDF Files -The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It can also help recognize barcode content and return structured JSON with per-field confidence scores. +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, barcodes, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It can also help recognize barcode content and return structured JSON with per-field confidence scores. -## Steps to Extract Structured Data from PDF Files +## Steps to Recognize Barcodes from PDF Files Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md index 68d0da13..2c39bcd1 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-HTML-from-PDF/.NET/Convert-data-as-HTML-from-PDF/README.md @@ -1,8 +1,8 @@ -# Extract Structured Data from PDF as HTML +# Convert PDF to HTML -The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into HTML for easy viewing, editing, and sharing. +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, barcodes, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into HTML for easy viewing, editing, and sharing. -## Steps to Extract Data as HTML from PDF Files +## Steps to Convert PDF to HTML Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md index c26ecfbd..2cf07030 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md @@ -1,8 +1,8 @@ -# Extract Structured Data from PDF as Word +# Convert PDF to Word The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into a Word document for easy editing, formatting, and sharing. -## Steps to Extract Data as Word from PDF Files +## Steps to Convert PDF to Word Step 1: **Create a new project:** Begin by setting up a new C# Console Application project. From 7571c605398df240edb9835dfc9e75ad4c08803e Mon Sep 17 00:00:00 2001 From: venkateshwaransf5013 Date: Tue, 6 Oct 2026 17:17:03 +0530 Subject: [PATCH 6/6] added barcode in pdf to word --- .../.NET/Convert-data-as-Word-from-PDF/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md index 2cf07030..ad29a752 100644 --- a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Word-from-PDF/.NET/Convert-data-as-Word-from-PDF/README.md @@ -1,6 +1,6 @@ # Convert PDF to Word -The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into a Word document for easy editing, formatting, and sharing. +The Syncfusion® [Smart Data Extractor](https://www.syncfusion.com/document-sdk/net-pdf-data-extraction) is a .NET library used to extract document structures such as hierarchies, text blocks, images, barcodes, headers, and footers from PDFs and scanned images by analyzing visual layout patterns like lines, boxes, and alignment. It converts the extracted content into a Word document for easy editing, formatting, and sharing. ## Steps to Convert PDF to Word