diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF.sln b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF.sln new file mode 100644 index 00000000..97a684a8 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF.sln @@ -0,0 +1,25 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio Version 18 +VisualStudioVersion = 18.9.12120.119 stable +MinimumVisualStudioVersion = 10.0.40219.1 +Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Convert-data-as-Excel-from-PDF", "Convert-data-as-Excel-from-PDF\Convert-data-as-Excel-from-PDF.csproj", "{88085F33-AC4F-D6AB-F085-D466B200233D}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|Any CPU = Debug|Any CPU + Release|Any CPU = Release|Any CPU + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {88085F33-AC4F-D6AB-F085-D466B200233D}.Debug|Any CPU.ActiveCfg = Debug|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Debug|Any CPU.Build.0 = Debug|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Release|Any CPU.ActiveCfg = Release|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Release|Any CPU.Build.0 = Release|Any CPU + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection + GlobalSection(ExtensibilityGlobals) = postSolution + SolutionGuid = {492422DA-0C62-412E-A5E9-9F85164F6C5E} + EndGlobalSection +EndGlobal diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Convert-data-as-Excel-from-PDF.csproj b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Convert-data-as-Excel-from-PDF.csproj new file mode 100644 index 00000000..7315d903 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Convert-data-as-Excel-from-PDF.csproj @@ -0,0 +1,24 @@ + + + + Exe + net8.0 + Convert_data_as_Excel_from_PDF + enable + enable + + + + + + + + + Always + + + Always + + + + diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Data/Input.pdf b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Data/Input.pdf new file mode 100644 index 00000000..aac2ac79 Binary files /dev/null and b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Data/Input.pdf differ diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Output/.gitkeep b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Output/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Program.cs b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Program.cs new file mode 100644 index 00000000..5b72399c --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/Program.cs @@ -0,0 +1,15 @@ +using Syncfusion.XlsIO; +using Syncfusion.SmartDataExtractor; + +//Open the input PDF file as a stream. +using (FileStream stream = new FileStream(Path.GetFullPath(@"Data/Input.pdf"), FileMode.Open, FileAccess.ReadWrite)) +{ +  //Initialize the Data Extractor. +  DataExtractor extractor = new DataExtractor(); +  //Extract data as Excel Document. +  IWorkbook excel = extractor.ExtractDataAsExcel(stream); +  //Save the extracted excel data into an output file. +  excel.SaveAs(Path.GetFullPath(@"Output/Output.xlsx")); +  excel.Close(); +} + \ No newline at end of file diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/README.md new file mode 100644 index 00000000..47e53b6d --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-Excel-from-PDF/.NET/Convert-data-as-Excel-from-PDF/README.md @@ -0,0 +1,39 @@ +# Convert PDF to Excel + +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 an Excel workbook for easy editing, formatting, and sharing. + +## Steps to Convert PDF to Excel + +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 Syncfusion.XlsIO; +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("Input.pdf", FileMode.Open, FileAccess.Read)) +{ + + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as Excel workbook. + IWorkbook excelWorkbook = extractor.ExtractDataAsExcel(stream); + using MemoryStream saveStream = new MemoryStream(); + //Save the extracted Excel data into an output file. + excelWorkbook.SaveAs(saveStream); + excelWorkbook.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-Excel-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-excel#convert-pdf-or-image-to-excel-document) section. \ No newline at end of file diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF.sln b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF.sln new file mode 100644 index 00000000..a3501bd4 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF.sln @@ -0,0 +1,25 @@ + +Microsoft Visual Studio Solution File, Format Version 12.00 +# Visual Studio Version 18 +VisualStudioVersion = 18.9.12120.119 stable +MinimumVisualStudioVersion = 10.0.40219.1 +Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Convert-data-as-PPTX-from-PDF", "Convert-data-as-PPTX-from-PDF\Convert-data-as-PPTX-from-PDF.csproj", "{88085F33-AC4F-D6AB-F085-D466B200233D}" +EndProject +Global + GlobalSection(SolutionConfigurationPlatforms) = preSolution + Debug|Any CPU = Debug|Any CPU + Release|Any CPU = Release|Any CPU + EndGlobalSection + GlobalSection(ProjectConfigurationPlatforms) = postSolution + {88085F33-AC4F-D6AB-F085-D466B200233D}.Debug|Any CPU.ActiveCfg = Debug|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Debug|Any CPU.Build.0 = Debug|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Release|Any CPU.ActiveCfg = Release|Any CPU + {88085F33-AC4F-D6AB-F085-D466B200233D}.Release|Any CPU.Build.0 = Release|Any CPU + EndGlobalSection + GlobalSection(SolutionProperties) = preSolution + HideSolutionNode = FALSE + EndGlobalSection + GlobalSection(ExtensibilityGlobals) = postSolution + SolutionGuid = {492422DA-0C62-412E-A5E9-9F85164F6C5E} + EndGlobalSection +EndGlobal diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Convert-data-as-PPTX-from-PDF.csproj b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Convert-data-as-PPTX-from-PDF.csproj new file mode 100644 index 00000000..820a609d --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Convert-data-as-PPTX-from-PDF.csproj @@ -0,0 +1,24 @@ + + + + Exe + net8.0 + Convert_data_as_PPTX_from_PDF + enable + enable + + + + + + + + + Always + + + Always + + + + diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Data/Input.pdf b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Data/Input.pdf new file mode 100644 index 00000000..9d6d0087 Binary files /dev/null and b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Data/Input.pdf differ diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Output/.gitkeep b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Output/.gitkeep new file mode 100644 index 00000000..e69de29b diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Program.cs b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Program.cs new file mode 100644 index 00000000..749d3441 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/Program.cs @@ -0,0 +1,14 @@ +using Syncfusion.Presentation; +using Syncfusion.SmartDataExtractor; + +//Open the input PDF file as a stream. +using (FileStream stream = new FileStream(Path.GetFullPath(@"Data/Input.pdf"), FileMode.Open, FileAccess.ReadWrite)) +{ + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as Presentation. + IPresentation pptxDoc = extractor.ExtractDataAsPresentation(stream); + //Save the extracted pptx data into an output file. + pptxDoc.Save(Path.GetFullPath(@"Output/Output.pptx")); + pptxDoc.Close(); +} diff --git a/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/README.md b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/README.md new file mode 100644 index 00000000..55d40768 --- /dev/null +++ b/Data-Extraction/Smart-Data-Extractor/Convert-data-as-PPTX-from-PDF/.NET/Convert-data-as-PPTX-from-PDF/README.md @@ -0,0 +1,39 @@ +# Convert PDF to PowerPoint + +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 PowerPoint presentation for easy editing, formatting, and sharing. + +## Steps to Convert PDF to PowerPoint + +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 Syncfusion.Presentation; +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("Input.pdf", FileMode.Open, FileAccess.Read)) +{ + + //Initialize the Data Extractor. + DataExtractor extractor = new DataExtractor(); + //Extract data as Presentation. + IPresentation presentation = extractor.ExtractDataAsPresentation(stream); + using MemoryStream saveStream = new MemoryStream(); + //Save the extracted PowerPoint data into an output file. + presentation.Save(saveStream); + presentation.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-PPTX-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-pptx#convert-pdf-or-image-to-pptx-document) section. \ No newline at end of file