static void ConvertFromStream()
{
// We need files only for demonstration purposes.
// The conversion process will be done completely in memory.
byte[] inpData = File.ReadAllBytes(@"..\..\..\..\..\..\Testing Files\example.pdf");
byte[] outData = null;
using (MemoryStream msInp = new MemoryStream(inpData))
{
// Load a document.
DocumentCore dc = DocumentCore.Load(msInp, new PdfLoadOptions()
{
PreserveGraphics = true,
DetectTables = true
});
// Save the document to another format.
using (MemoryStream outMs = new MemoryStream())
{
dc.Save(outMs, new HtmlFixedSaveOptions()
{
CssExportMode = CssExportMode.Inline,
EmbedImages = true
});
outData = outMs.ToArray();
}
}
}
/// <summary>
/// Find and replace a text using ContentRange.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/find-replace-content-net-csharp-vb.php
/// </remarks>
public static void FindAndReplace()
{
// Path to a loadable document.
string loadPath = @"..\..\critique.docx";
// Load a document intoDocumentCore.
DocumentCore dc = DocumentCore.Load(loadPath);
Regex regex = new Regex(@"bean", RegexOptions.IgnoreCase);
//Find "Bean" and Replace everywhere on "Joker :-)"
// Please note, Reverse() makes sure that action replace not affects to Find().
foreach (ContentRange item in dc.Content.Find(regex).Reverse())
{
item.Replace("Joker");
}
// Save our document into PDF format.
string savePath = "Replaced.pdf";
dc.Save(savePath, new PdfSaveOptions());
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(loadPath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(savePath)
{
UseShellExecute = true
});
}
/// <summary>
/// Convert RTF to DOCX (using Stream).
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-rtf-to-docx-in-csharp-vb.php
/// </remarks>
static void ConvertFromStream()
{
// We need files only for demonstration purposes.
// The conversion process will be done completely in memory.
string inpFile = @"..\..\example.rtf";
string outFile = @"ResultStream.docx";
byte[] inpData = File.ReadAllBytes(inpFile);
byte[] outData = null;
using (MemoryStream msInp = new MemoryStream(inpData))
{
// Load a document.
DocumentCore dc = DocumentCore.Load(msInp, new RtfLoadOptions());
// Save the document to DOCX format.
using (MemoryStream outMs = new MemoryStream())
{
dc.Save(outMs, new DocxSaveOptions());
outData = outMs.ToArray();
}
// Show the result for demonstration purposes.
if (outData != null)
{
File.WriteAllBytes(outFile, outData);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
}
}
public void CreatePDFFIleReport()
{
CreateWordFileReport(Program.expencesList, Program.incomeList);
var document = DocumentCore.Load(@"C:\Users\user\source\repos\ZenMoney\ZenMoney\bin\Debug\OutputDocument.docx");
document.Save(@"C:\Users\user\source\repos\ZenMoney\ZenMoney\bin\Debug/report.pdf");
}
/// <summary>
/// Merge all paragraphs into a single in an existing PDF document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/merge-paragraphs-in-pdf-document-net-csharp-vb.php
/// </remarks>
static void MergeParagraphs()
{
string inpFile = @"..\..\example.pdf";
string outFile = @"Result.pdf";
DocumentCore dc = DocumentCore.Load(inpFile);
Paragraph firstPar = dc.GetChildElements(true, ElementType.Paragraph).First() as Paragraph;
int lastIndex = firstPar.Inlines.Count;
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph).Reverse().Where(p => p != firstPar))
{
int last = lastIndex;
foreach (Inline inline in par.Inlines)
{
firstPar.Inlines.Insert(last++, inline.Clone(true));
}
par.Content.Delete();
}
dc.Save(outFile);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(inpFile)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
public static void ExtractPictures()
{
// Path to a document where to extract pictures.
string filePath = @"..\..\..\..\..\..\Testing Files\example.pdf";
// Directory to store extracted pictures:
DirectoryInfo imageDirectory = new DirectoryInfo(Path.GetDirectoryName(filePath));
string imageTemplate = "Picture";
// Here we store extracted images.
List <ImageData> imageInventory = new List <ImageData>();
// Load the document.
DocumentCore dc = DocumentCore.Load(filePath);
// Extract all images from document, skip duplicates.
foreach (Picture pict in dc.GetChildElements(true, ElementType.Picture))
{
// Let's avoid the adding of duplicates.
if (imageInventory.Exists((img => (img.GetStream().Length == pict.ImageData.GetStream().Length))) == false)
{
imageInventory.Add(pict.ImageData);
}
}
// Save and show all images.
for (int i = 0; i < imageInventory.Count; i++)
{
string imagePath = Path.Combine(imageDirectory.FullName, String.Format("{0}{1}.{2}", imageTemplate, i + 1, imageInventory[i].Format.ToString().ToLower()));
File.WriteAllBytes(imagePath, imageInventory[i].GetStream().ToArray());
System.Diagnostics.Process.Start(imagePath);
}
}
/// <summary>
/// How to replace a hyperlink URL by a new address.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-replace-url-csharp-vb-net.php
/// </remarks>
public static void ReplaceHyperlinksURL()
{
// Let us say, we've a DOCX document.
// And we've to replace the all URLs by the custom.
// Furthermore, let's save the result as PDF.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - URL.pdf";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Specify the custom URL.
string customURL = "https://www.sautinsoft.com";
// Loop by all hyperlinks and replace the URL (address).
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink))
{
hpl.Address = customURL;
}
// Save our document back, but in PDF format.
dc.Save(outFile, new PdfSaveOptions()
{
Compliance = PdfCompliance.PDF_14
});
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Iterates through a document and count the amount of Paragraphs and Runs.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/elementcollection-iteration.php
/// </remarks>
static void ShowInlines()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
Console.WriteLine("This document contains from:");
for (int sect = 0; sect < dc.Sections.Count; sect++)
{
Console.WriteLine("Section {0} contains from:", sect);
int totalParagraphs = 0;
Section section = dc.Sections[sect];
for (int blocks = 0; blocks < section.Blocks.Count; blocks++)
{
if (section.Blocks[blocks] is Paragraph)
{
totalParagraphs++;
Paragraph paragraph = section.Blocks[blocks] as Paragraph;
Console.Write("\t\t Paragraph {0} contains from: ", totalParagraphs);
int totalRuns = 0;
for (int i = 0; i < paragraph.Inlines.Count; i++)
{
if (paragraph.Inlines[i] is Run)
{
totalRuns++;
}
}
Console.WriteLine("{0} Run(s).", totalRuns);
}
}
}
Console.ReadKey();
}
private void Button_Click1(object sender, RoutedEventArgs e) // docx
{
//SautinSoft.Document library:
//Create: DOCX, PDF, RTF, HTML
//Load: DOCX, PDF, RTF, HTML
//Save as: DOCX, PDF, RTF, HTML, Text
//string inpFile = @"C:\Users\user\Desktop\kkkkkkkk\d\d\dokum\test.docx..docx";
//string outFile = @"C:\Users\user\Desktop\kkkkkkkk\d\d\dokum\111.pdf";
OpenFileDialog openFileDialog = new OpenFileDialog();
openFileDialog.CheckFileExists = true;
openFileDialog.Multiselect = true;
openFileDialog.Filter = "Doc files (*.docx)|*.docx|All files (*.*)|*.*";
openFileDialog.InitialDirectory = Environment.GetFolderPath(Environment.SpecialFolder.ProgramFiles);
Nullable <bool> result = openFileDialog.ShowDialog();
if (result == true)
{
string inpFile = openFileDialog.FileName; // Open document
string outFile = @"C:\Users\Mariia\Desktop\Convertor\PDFfromDOC.pdf";
DocumentCore dc = DocumentCore.Load(inpFile);
dc.Save(outFile);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
//File.OpenRead(filename);
}
//DocumentCore dc = DocumentCore.Load(inpFile);
//dc.Save(outFile);
// Open the result for demonstation purposes.
//System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile) { UseShellExecute = true });
}
/// <summary>
/// Inserts a new Run (Text element) at the start of each paragraph.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/elementcollection-insert.php
/// </remarks>
static void InsertParagraphCount()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
int paragraphNum = 1;
foreach (Element el in dc.Sections[0].GetChildElements(false))
{
if (el is Paragraph)
{
// Insert a new Run into Paragraph.InlineCollection 'Inlines'.
// InlineCollection is descendant of the base abstract class ElementCollection.
(el as Paragraph).Inlines.Insert(0, new Run(dc, "Paragraph " + paragraphNum.ToString() + " - ", new CharacterFormat()
{
BackgroundColor = Color.Orange, FontColor = Color.White
}));
paragraphNum++;
}
}
dc.Save("Result.docx");
// Show the result.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo("Result.docx")
{
UseShellExecute = true
});
}
/// <summary>
/// Generate reports using a custom data source (collection of custom classes Actor and Order).
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/mail-merge-custom-data-source-net-csharp-vb.php
/// </remarks>
static void CustomDataSource()
{
// Populate some data that we will use in the mail merge.
List <Actor> actors = new List <Actor>();
actors.Add(new Actor("Arnold Schwarzenegger", "12989 Chalon Road, Los Angeles, CA 90049"));
actors.Add(new Actor("Sylvester Stallone", "30 Beverly Park Terrace, Beverly Hills, CA 90210"));
// Populate some data for nesting in the mail merge.
actors[0].Orders.Add(new Order("Bowflex SelectTech 1090 Adjustable Dumbbell", 2));
actors[0].Orders.Add(new Order("Gold's Gym Kettlebell Kit, 5-15 Lbs.", 1));
actors[1].Orders.Add(new Order("Weider Cast Iron Olympic Hammertone Weight Set, 300 Lb.", 1));
// Load the template document.
DocumentCore dc = DocumentCore.Load(@"..\..\OrdersTemplate.docx");
// To be able to mail merge from your own data source, it must be wrapped into an object that implements the IMailMergeDataSource interface.
CustomMailMergeDataSource customDataSource = new CustomMailMergeDataSource(actors);
// Execute the mail merge.
dc.MailMerge.Execute(customDataSource);
string resultPath = "Orders.docx";
// Save the output to file.
dc.Save(resultPath);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(resultPath)
{
UseShellExecute = true
});
}
/// <summary>
/// Loads a document into DocumentCore (dc) from an array of bytes.
/// </summary>
/// <remarks>
/// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/load-document.php
/// </remarks>
static void LoadFromBytes()
{
// Get document bytes from a file.
byte[] fileBytes = File.ReadAllBytes(@"..\..\example.pdf");
DocumentCore dc = null;
using (MemoryStream ms = new MemoryStream(fileBytes))
{
// With PdfLoadOptions we explicitly set that a loadable document is PDF.
PdfLoadOptions pdfLO = new PdfLoadOptions()
{
// 'false' - means to load vector graphics as is. Don't transform it to raster images.
RasterizeVectorGraphics = false,
// The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
// In case of 'true' the component will detect and recreate tables from graphic lines.
DetectTables = false,
// 'true' - Load embedded fonts from PDF document, even if the font with the same name is installed in your System.
PreserveEmbeddedFonts = false,
// Load only first 2 pages from the document.
PageIndex = 0,
PageCount = 2
};
dc = DocumentCore.Load(ms, pdfLO);
}
if (dc != null)
{
Console.WriteLine("Loaded successfully!");
}
Console.ReadKey();
}
/// <summary>
/// How to clone an element in DOCX document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/cloning-element-net-csharp-vb.php
/// </remarks>
static void CloningElement()
{
string filePath = @"..\..\Parsing.docx";
string cloningFile = "Cloning.docx";
DocumentCore dc = DocumentCore.Load(filePath);
// Clone section.
dc.Sections.Add(dc.Sections[0].Clone(true));
// Clone paragraphs.
foreach (Block item in dc.Sections[0].Blocks)
{
dc.Sections.Last().Blocks.Add(item.Clone(true));
}
// Save the result.
dc.Save(cloningFile);
// Show the result.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(cloningFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Generates a table report with regions using XML document as a data source.
/// </summary>
/// <remarks>
/// See details at: https://www.sautinsoft.com/products/document/help/net/developer-guide/mail-merge-table-report-with-regions-net-csharp-vb.php
/// </remarks>
public static void TableReportWithRegions()
{
// Create the Dataset and read the XML.
DataSet ds = new DataSet();
ds.ReadXml(@"..\..\Orders.xml");
// Load the template document.
string templatePath = @"..\..\InvoiceTemplate.docx";
DocumentCore dc = DocumentCore.Load(templatePath);
// Execute the mail merge.
dc.MailMerge.Execute(ds.Tables["Order"]);
string resultPath = "Invoices.pdf";
// Save the output to file
dc.Save(resultPath);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(resultPath)
{
UseShellExecute = true
});
}
/// <summary>
/// Convert PDF to RTF (file to file).
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-pdf-to-rtf-in-csharp-vb.php
/// </remarks>
static void ConvertFromFile()
{
string inpFile = @"..\..\example.pdf";
string outFile = @"Result.rtf";
// Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
PdfLoadOptions pdfLO = new PdfLoadOptions()
{
// 'false' - means to load vector graphics as is. Don't transform it to raster images.
RasterizeVectorGraphics = false,
// The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
// In case of 'true' the component will detect and recreate tables from graphic lines.
DetectTables = false,
// 'true' - Load embedded fonts from PDF document, even if the font with the same name is installed in your System.
PreserveEmbeddedFonts = false
};
DocumentCore dc = DocumentCore.Load(inpFile, pdfLO);
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Find Text and replace it with a Picture using ContentRange.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/find-replace-content-net-csharp-vb.php
/// </remarks>
public static void FindTextAndReplaceImage()
{
// Path to a loadable document.
string loadPath = @"..\..\Critique_signature.docx";
string pictPath = @"..\..\Smile.png";
// Load a document intoDocumentCore.
DocumentCore dc = DocumentCore.Load(loadPath);
//Find "<signature>" Text and Replace everywhere with the "Smile.png"
// Please note, Reverse() makes sure that action replace not affects to Find().
Regex regex = new Regex(@"<signature>", RegexOptions.IgnoreCase);
Picture picture = new Picture(dc, InlineLayout.Inline(new Size(50, 50)), pictPath);
foreach (ContentRange item in dc.Content.Find(regex).Reverse())
{
item.Replace(picture.Content);
}
// Save our document into PDF format.
string savePath = @"..\..\Replaced_signature.pdf";
dc.Save(savePath, new PdfSaveOptions());
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(loadPath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(savePath)
{
UseShellExecute = true
});
}
/// <summary>
/// Delete a specific text from DOCX document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/delete-text-from-docx-document-net-csharp-vb.php
/// </remarks>
static void DeleteText()
{
string filePath = @"..\..\example.docx";
string fileResult = @"Result.pdf";
string textToDelete = "document";
DocumentCore dc = DocumentCore.Load(filePath);
int countDel = 0;
foreach (ContentRange cr in dc.Content.Find(textToDelete).Reverse())
{
cr.Delete();
countDel++;
}
Console.WriteLine("The text: \"" + textToDelete + "\" - was deleted " + countDel.ToString() + " time(s).");
Console.ReadKey();
dc.Save(fileResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(fileResult)
{
UseShellExecute = true
});
}
private void BtnConverter_Click(object sender, EventArgs e)
{
try
{
if (string.IsNullOrEmpty(txtFileName.Text))
{
return;
}
var docPath = txtFileName.Text;
var pdfPath = docPath.Replace(".docx", ".pdf");
var dc = DocumentCore.Load(docPath);
dc.Save(pdfPath);
txtFileName.Text = string.Empty;
btnSelecionar.Enabled = true;
btnConverter.Enabled = false;
MessageBox.Show(this, "Arquivo convertido com sucesso!", @"Sucesso", MessageBoxButtons.OK, MessageBoxIcon.Information);
}
catch (Exception ex)
{
Console.WriteLine("Erro:", ex.Message);
txtFileName.Text = string.Empty;
btnSelecionar.Enabled = true;
btnConverter.Enabled = false;
}
}
public string Read(string path)
{
var dc = DocumentCore.Load(path);
var runList = dc.GetChildElements(true, ElementType.Run).Select(x => x.Content.ToString());
return(string.Concat(runList));
}
/// <summary>
/// Copy a document to other document. Supported any formats (PDF, DOCX, RTF, HTML).
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/importing-element-net-csharp-vb.php
/// </remarks>
static void ImportingElement()
{
string file1 = @"..\..\digitalsignature.docx";
string file2 = @"..\..\Parsing.docx";
string resultFile = "Importing.docx";
// Load files.
DocumentCore dc = DocumentCore.Load(file1);
DocumentCore dc1 = DocumentCore.Load(file2);
// New Import Session to improve performance.
var session = new ImportSession(dc1, dc);
// Import all sections from source document.
foreach (Section sourceSection in dc1.Sections)
{
Section destinationSection = dc.Import(sourceSection, true, session);
dc.Sections.Add(destinationSection);
}
// Save the result.
dc.Save(resultFile);
// Show the result.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(resultFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Open a document and delete some content.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/delete-content-net-csharp-vb.php
/// </remarks>
public static void DeleteContent()
{
string loadPath = @"..\..\example.docx";
string savePath = "Result.docx";
DocumentCore dc = DocumentCore.Load(loadPath);
// Remove the text "This" from all paragraphs in 1st section.
foreach (Paragraph par in dc.Sections[0].GetChildElements(true, ElementType.Paragraph))
{
var findText = par.Content.Find("This");
if (findText != null)
{
foreach (ContentRange cr in findText)
{
cr.Delete();
}
}
}
dc.Save(savePath);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(loadPath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(savePath)
{
UseShellExecute = true
});
}
/// <summary>
/// Insert a picture to custom page and position into existing DOCX document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-picture-jpg-image-to-custom-docx-page-and-position-net-csharp-vb.php
/// </remarks>
static void InsertPictureToCustomPageAndPosition()
{
// In this example we'll insert the picture to 1st after the word "Sign:".
string inpFile = @"..\..\example.docx";
string outFile = @"Result.docx";
string pictFile = @"..\..\picture.jpg";
DocumentCore dc = DocumentCore.Load(inpFile);
DocumentPaginator dp = dc.GetPaginator();
// Find the text "Sign:" on the 1st page.
ContentRange cr = dp.Pages[0].Content.Find("Sign:").LastOrDefault();
if (cr != null)
{
Picture pic = new Picture(dc, pictFile);
cr.End.Insert(pic.Content);
}
// Save the document as new DOCX and open it.
dc.Save(outFile);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Inserts a new paragraph into an existing PDF document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-paragraphs-to-pdf-document-net-csharp-vb.php
/// </remarks>
static void InsertParagraph()
{
string inpFile = @"..\..\example.pdf";
string outFile = @"Result.pdf";
DocumentCore dc = DocumentCore.Load(inpFile);
Paragraph p = new Paragraph(dc);
p.Content.Start.Insert("Alexander Pushkin was a great russian romantic poet " +
"and writer who is considered by a lot of people as the best russian poet and the founder " +
"of contemporary russian literature.",
new CharacterFormat()
{
Size = 20, FontName = "Verdana", FontColor = new Color("#358CCB")
});
p.ParagraphFormat.Alignment = HorizontalAlignment.Justify;
// Insert the paragraph as 1st element in the 1st section.
dc.Sections[0].Blocks.Insert(0, p);
dc.Save(outFile);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
public void LoadPages(int pagesCount)
{
for (int i = 0; i < pagesCount; i++)
{
List <SautinSoft.Document.Tables.TableRow> rowContent = new List <SautinSoft.Document.Tables.TableRow>();
DocumentCore dc = DocumentCore.Load(folderPath + @"\Page - " + (i + 1).ToString() + ".pdf");
foreach (SautinSoft.Document.Tables.TableRow run in dc.GetChildElements(true, ElementType.TableRow))
{
rowContent.Add(run);
}
;
foreach (SautinSoft.Document.Section run in dc.GetChildElements(true, ElementType.Section))
{
date = run.Blocks[run.Blocks.Count - 2].Content.ToString().Replace("\r\n", "").Substring(4, 10);
break;
}
;
foreach (SautinSoft.Document.Paragraph run in dc.GetChildElements(true, ElementType.Paragraph))
{
if (run.Content.ToString().Contains("Дата принятия уполномоченным банком"))
{
adoptionDate = run.Inlines[7].Content.ToString();
break;
}
}
;
ParseAndGetInfo(rowContent, i + 1);
}
}
/// <summary>
/// Deletes a specific paragraphs in an existing DOCX and save it as new PDF.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/delete-paragraphs-in-docx-document-net-csharp-vb.php
/// </remarks>
static void DeleteParagraphs()
{
string filePath = @"..\..\example.docx";
string fileResult = @"Result.pdf";
DocumentCore dc = DocumentCore.Load(filePath);
// Note, remove paragraphs only inside the first section.
Section section = dc.Sections[0];
// Let's remove all paragraphs containing the text "Jack".
for (int i = 0; i < section.Blocks.Count; i++)
{
if (section.Blocks[i].Content.Find("Jack").Count() > 0)
{
section.Blocks.RemoveAt(i);
i--;
}
}
dc.Save(fileResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(fileResult)
{
UseShellExecute = true
});
}
/// <summary>
/// How to delete all hyperlink objects.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-delete-url-csharp-vb-net.php
/// </remarks>
public static void DeleteHyperlinksObjects()
{
// Let us say, we've a DOCX document.
// And we've to remove the hyperlink objects.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - Delete Hyperlinks completely.pdf";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Loop by all hyperlinks and replace the URL (address).
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink).Reverse())
{
hpl.ParentCollection.Remove(hpl);
}
// Save our document back, but in PDF format.
dc.Save(outFile, new PdfSaveOptions()
{
Compliance = PdfCompliance.PDF_14
});
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// How to get a content from a document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/get-content-net-csharp-vb.php
/// </remarks>
public static void GetContent()
{
// Path to an input document.
string documentPath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(documentPath);
StringBuilder sb = new StringBuilder();
// Get content of each paragraph in the document.
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph))
{
// The property 'Content' returns the content as ContentRange.
// Get content and append it into StringBuilder.
sb.AppendFormat("Paragraph: {0}", par.Content.ToString());
sb.AppendLine();
}
// Get content of each Run where the text color is Red.
foreach (Run run in dc.GetChildElements(true, ElementType.Run))
{
if (run.CharacterFormat.FontColor == Color.Red)
{
// The property 'Content' returns the content as ContentRange.
// Get content and append it into StringBuilder.
sb.AppendFormat("Red color: {0}", run.Content.ToString());
sb.AppendLine();
}
}
Console.WriteLine(sb.ToString());
Console.ReadKey();
}
private void buttonGetDocument_Click(object sender, EventArgs e)
{
SetDefaultDataTable();
List <string> lS1 = new List <string>(); // Лист всех элементов из .docx
OpenFileDialog opf = new OpenFileDialog();
opf.Filter = "Word 2007 Documents (*.docx)|*.docx";
if (opf.ShowDialog() == DialogResult.OK)
{
string filename = opf.FileName; // Path to Docx file.
DocumentCore dc = DocumentCore.Load(filename);
StringBuilder sb = new StringBuilder();
// Get content of each Run where the text color is Red.
foreach (Paragraph run in dc.GetChildElements(true, ElementType.Paragraph))
{
string str = run.Content.ToString();
string[] strpath = str.Split('\r'); // Не удавалось расплитить по '\r\n'. Расплититл по '\r'.
str = strpath[0]; // Хвост отбросил.
if (str != "") // Проверка на какой-либо элемент. В том числе и филды.
{
lS1.Add(str); // Список всех элементов документа, где каждый первый - Id, а каждый второй - дата.
}
}
ToTable TTable = new ToTable();
string FieldId = lS1[0];
string FieldData = lS1[1];
lS1.Remove(FieldId);
lS1.Remove(FieldData);
DataTable DT = TTable.ConvertToTable(lS1, FieldId, FieldData, GetPathAndName(opf.FileName)[1]);
dataGridView1.DataSource = DT;
}
}
/// <summary>
/// Replace all Run elements with Bold formatting to Italic and mark them by yellow.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/manipulation.php
/// </remarks>
static void Manipulation()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
string filePathResult = @"Result-file.pdf";
foreach (Run run in dc.GetChildElements(true, ElementType.Run))
{
if (run.CharacterFormat.Bold == true)
{
run.CharacterFormat.Bold = false;
run.CharacterFormat.Italic = true;
run.CharacterFormat.BackgroundColor = Color.Yellow;
}
}
dc.Save(filePathResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePathResult)
{
UseShellExecute = true
});
}
// How to modify an existing table in a document.
public static void ModifyTable()
{
string sourcePath = @"..\..\..\..\..\..\Testing Files\table.docx";
string destPath = Path.ChangeExtension(sourcePath, ".modified.pdf");
// Load a document with a table.
DocumentCore dc = DocumentCore.Load(sourcePath);
// Find a first table in the document.
Table table = (Table)dc.GetChildElements(true, ElementType.Table).First();
// Set dashed borders and yellow background for all cells.
for (int r = 0; r < table.Rows.Count; r++)
{
for (int c = 0; c < table.Rows[r].Cells.Count; c++)
{
TableCell cell = table.Rows[r].Cells[c];
cell.CellFormat.Borders.SetBorders(MultipleBorderTypes.Outside, BorderStyle.Dashed, Color.Black, 1);
cell.CellFormat.BackgroundColor = new Color("#FFCC00");
}
}
// Save the document as PDF.
dc.Save(destPath, new PdfSaveOptions());
// Show the source and the dest documents.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(sourcePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(destPath)
{
UseShellExecute = true
});
}