static void Main(string[] args)
{
byte[] pdfBytes = File.ReadAllBytes(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages.pdf");
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
f.OpenPdf(pdfBytes);
if (f.PageCount > 0)
{
byte[] word = f.ToWord();
System.IO.File.WriteAllBytes(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_sautinSoft.rtf", word);
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.InlineCSS = true;
string html = f.ToHtml();
System.IO.File.WriteAllText(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_sautinSoft.html", html);
//Console.WriteLine(html);
//Console.WriteLine("In base64 rtf: {0}", Convert.ToBase64String(word));
string rez = GetText(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages.pdf");
System.IO.File.WriteAllText(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_iTextSharp.txt", rez);
System.IO.File.WriteAllText(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_iTextSharp.rtf", rez);
string rHTML = ConvertPdf(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages.pdf", @"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_iTextSharp.html");
//string spireReturn = SpirePDF(@"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages.pdf", @"C:\Users\adit.shah\source\repos\aditshh\RTFToPDF\SampleFile\sampleWithImages_SpirePDF.html");
Console.ReadLine();
}
}
static void Main(string[] args)
{
#region Property
//Put your pdf file path
string pathToPdf = @"C:/Users/dhire/Downloads/Compressed/Convert PDF file to HTML file in C# - Step by Step/table.pdf";
string pathToHtml = Path.ChangeExtension(pathToPdf, ".htm");
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
#endregion
#region Declaration
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
f.OpenPdf(pathToPdf);
if (f.PageCount > 0)
{
int result = f.ToHtml(pathToHtml);
if (result == 0)
{
System.Diagnostics.Process.Start(pathToHtml);
}
}
#endregion
}
private static void ConvertPdfStreamToHtml()
{
string pathToPdf = @"..\..\..\..\..\simple text.pdf";
string pathToHtml = Path.ChangeExtension(pathToPdf, ".htm");
// This list will be filled by images after the PDF to HTML conversion.
List <Image> imgCollection = new List <Image>();
// Convert PDF to HTML in memory
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// Let's force the component to store images inside HTML document
// using base-64 encoding.
// Thus the component will not use HDD.
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
f.HtmlOptions.InlineCSS = true;
// This property is necessary only for registered version
//f.Serial = "XXXXXXXXXXX";
// Read a PDF document to byte array
// Assume that we have a PDF document as Stream.
using (FileStream fs = File.OpenRead(pathToPdf))
{
f.OpenPdf(fs);
if (f.PageCount > 0)
{
// Convert PDF to HTML string.
string html = f.ToHtml(1, f.PageCount, imgCollection);
// Show info about images.
Console.WriteLine("After converting we've got {0} image(s):", imgCollection.Count);
foreach (Image img in imgCollection)
{
Console.WriteLine("\t {0,4} x {1,4} px", img.Width, img.Height);
}
Console.WriteLine("Press any key ...");
Console.ReadLine();
// Save HTML to a file only for demonstration purposes.
if (html != null)
{
File.WriteAllText(pathToHtml, html);
System.Diagnostics.Process.Start(pathToHtml);
}
}
}
}
static void Main(string[] args)
{
// Convert PDF to separate HTMLs.
// Each PDF page will be converted to a single HTML document.
string pdfFile = @"..\..\simple text.pdf";
DirectoryInfo htmlDir = new DirectoryInfo("htmls");
if (!htmlDir.Exists)
{
htmlDir.Create();
}
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// This property is necessary only for licensed version.
//f.Serial = "XXXXXXXXXXX";
f.HtmlOptions.IncludeImageInHtml = false;
// Path (must exist) to a directory to store images after converting.
f.HtmlOptions.ImageFolder = htmlDir.FullName;
f.OpenPdf(pdfFile);
if (f.PageCount > 0)
{
// Convert each PDF page to separate HTML document.
// simple text.html, simple text.html ... simple text.html.
for (int page = 1; page <= f.PageCount; page++)
{
f.HtmlOptions.Title = $"Page {page}";
f.HtmlOptions.ImageSubFolder = String.Format("page{0}_images", page);
string htmlString = f.ToHtml(page, page);
// Save htmlString to file
string htmlFile = Path.Combine(htmlDir.FullName, $"Page{page}.html");
File.WriteAllText(htmlFile, htmlString);
// Let's open only 1st and last pages.
if (page == 1 || page == f.PageCount)
{
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(htmlFile)
{
UseShellExecute = true
});
}
}
}
}
private static void ConvertPdfStreamToHtml()
{
// We need files only for demonstration purposes.
// The whole conversion process will be done in memory.
string templateFile = "/Users/user/Downloads/1022out.pdf";
string outFile = "/Users/user/Downloads/1022out.html";
// Convert PDF to HTML in memory
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// This property is necessary only for licensed version.
//f.Serial = "XXXXXXXXXXX";
// Let's force the component to store images inside HTML document
// using base-64 encoding.
// Thus the component will not use HDD.
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
// Assume that we have a PDF document as Stream.
using (FileStream fs = File.OpenRead(templateFile))
{
f.OpenPdf(fs);
if (f.PageCount > 0)
{
// Convert PDF to HTML to a MemoryStream.
using (MemoryStream msHtml = new MemoryStream())
{
int res = f.ToHtml(msHtml);
// Open the result for demonstation purposes.
if (res == 0)
{
File.WriteAllBytes(outFile, msHtml.ToArray());
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
}
}
}
}
private static void ConvertPdfBytesToHtml()
{
// We need files only for demonstration purposes.
// The whole conversion process will be done in memory.
string pdfFile = @"..\..\simple text.pdf";
string htmlFile = "Result.html";
// Convert PDF to HTML in memory
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// This property is necessary only for licensed version.
//f.Serial = "XXXXXXXXXXX";
// Let's force the component to store images inside HTML document
// using base-64 encoding.
// Thus the component will not use HDD.
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
// Read a PDF document to byte array
// Assume that we already have the PDF as array of bytes.
byte[] pdf = File.ReadAllBytes(pdfFile);
f.OpenPdf(pdf);
if (f.PageCount > 0)
{
// Convert PDF to HTML in memory
string html = f.ToHtml();
// Save HTML to the file only for demonstration purpose.
if (html != null)
{
File.WriteAllText(htmlFile, html);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(htmlFile)
{
UseShellExecute = true
});
}
}
}
static void Main(string[] args)
{
// Convert PDF to separate HTMLs.
// Each PDF page will be converted to a single HTML document.
// Path to PDF file.
string pdfPath = Path.GetFullPath(@"..\..\..\..\..\simple text.pdf");
// Directory to store HTML documents.
string htmlDir = Path.GetDirectoryName(pdfPath);
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
f.HtmlOptions.IncludeImageInHtml = false;
// Path (must exist) to a directory to store images after converting. Notice also to the property "ImageSubFolder".
f.HtmlOptions.ImageFolder = htmlDir;
f.OpenPdf(pdfPath);
// Convert each PDF page to separate HTML document.
// simple text.html, simple text.html ... simple text.html.
for (int page = 1; page <= f.PageCount; page++)
{
f.HtmlOptions.Title = String.Format("Simple Text - Page {0}", page);
f.HtmlOptions.ImageSubFolder = String.Format("images-page{0}", page);
string htmlString = f.ToHtml(page, page);
// Save htmlString to file
string htmlPath = Path.Combine(htmlDir, String.Format("Page{0}.html", page));
File.WriteAllText(htmlPath, htmlString);
// Let's show first and last HTML pages.
if (page == 1 || page == f.PageCount)
{
System.Diagnostics.Process.Start(htmlPath);
}
}
}
private static void ConvertPdfStreamToHtml()
{
string pathToPdf = @"..\..\..\..\..\simple text.pdf";
string pathToHtml = Path.ChangeExtension(pathToPdf, ".htm");
// Convert PDF to HTML in memory
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// Let's force the component to store images inside HTML document
// using base-64 encoding.
// Thus the component will not use HDD.
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
f.HtmlOptions.InlineCSS = true;
// This property is necessary only for registered version
//f.Serial = "XXXXXXXXXXX";
// Read a PDF document to byte array
// Assume that we have a PDF document as Stream.
using (FileStream fs = File.OpenRead(pathToPdf))
{
f.OpenPdf(fs);
if (f.PageCount > 0)
{
// Convert PDF to HTML string.
string html = f.ToHtml();
// Save HTML to a file only for demonstration purposes.
if (html != null)
{
File.WriteAllText(pathToHtml, html);
System.Diagnostics.Process.Start(pathToHtml);
}
}
}
}
public Task ConvertPDFToHTML()
{
var tcs = new TaskCompletionSource <int>();
this.htmlPath = string.Empty;
SautinSoft.PdfFocus f = null;
try
{
this.htmlPath = GetTempFolderPath() + DateTime.Now.ToFileTime() + ".html";
this.master.bi.LogBusyProgress("Openning pdf file..");
f = new SautinSoft.PdfFocus();
f.OpenPdf(inputFilePath);
if (f.PageCount > 0)
{
this.master.bi.LogBusyProgress("Converting pdf to html..");
f.ToHtml(htmlPath);
}
}
catch (Exception ex)
{
this.master.bi.BusyOff();
this.htmlPath = string.Empty;
Helper.LogError(this.GetType().Name, MethodBase.GetCurrentMethod().Name, ex);
}
finally
{
if (f != null)
{
f.ClosePdf();
}
}
return(tcs.Task);
}
public ActionResult Index(HttpPostedFileBase file)
{
if (file != null && file.ContentLength > 0)
{
var getfileextension = System.IO.Path.GetExtension(file.FileName);
if (string.IsNullOrEmpty(getfileextension) || getfileextension != ".pdf")
{
ViewBag.Message = "Only pdf file allow to convert.";
}
else
{
try
{
//Get the File Name. Remove space characters from File Name.
string fileName = file.FileName.Replace(" ", string.Empty);
var filename = System.IO.Path.GetFileNameWithoutExtension(fileName);
var tickervalue = DateTime.Now.Ticks;
var newpdffilename = string.Format("{0}{1}{2}", filename, tickervalue, ".pdf");
var newhtmlfilename = string.Format("{0}{1}{2}", filename, tickervalue, ".html");
//Save the PDF file.
var brieffile = "brief_1/";
var lastrec = _context.tblBriefs.OrderByDescending(o => o.Id).FirstOrDefault();
if (lastrec != null)
{
brieffile = "brief_" + (lastrec.Id + 1) + "/";
}
var brieffilepath = Server.MapPath("~/htmlfiles/") + brieffile;
if (!Directory.Exists(brieffilepath))
{
Directory.CreateDirectory(brieffilepath);
}
string inputPath = brieffilepath + newpdffilename;
string outputhtmlPath = brieffilepath + newhtmlfilename;
file.SaveAs(inputPath);
#region Convert Html using Sautinsoft
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
f.EmbeddedImagesFormat = SautinSoft.PdfFocus.eImageFormat.Auto;
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.InlineCSS = true;
f.HtmlOptions.RenderMode = SautinSoft.PdfFocus.CHtmlOptions.eHtmlRenderMode.Fixed;
f.HtmlOptions.UseNumericCharacterReference = true;
f.HtmlOptions.KeepCharScaleAndSpacing = true;
f.OpenPdf(inputPath);
if (f.PageCount > 0)
{
int res = f.ToHtml(outputhtmlPath);
}
#endregion
#region save data in brief table
tblBrief tbl = new tblBrief()
{
FileName = Path.GetFileNameWithoutExtension(newhtmlfilename),
FilePath = "~/htmlfiles/" + brieffile,
CreatedDate = DateTime.UtcNow
};
_context.tblBriefs.Add(tbl);
_context.SaveChanges();
#endregion
ViewBag.Message = "File uploaded and converted";
ViewBag.generatedfile = newhtmlfilename;
}
catch (Exception ex)
{
ViewBag.Message = "ERROR:" + ex.Message.ToString();
}
}
}
else
{
ViewBag.Message = "You have not specified a file.";
}
var AllDataList = _context.tblBriefs.OrderByDescending(o => o.CreatedDate).ToList();
return(View(AllDataList));
}
private static void ConvertPdfBytesToHtml()
{
// We need files only for demonstration purposes.
// The whole conversion process will be done in memory.
string pdfFile = @"..\..\simple text.pdf";
string htmlFile = "Result.htm";
// This is the list with extracted images.
// It will be filled by images after the conversion.
List <Image> imgCollection = new List <Image>();
// Convert PDF to HTML in memory
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
// This property is necessary only for licensed version.
//f.Serial = "XXXXXXXXXXX";
// Let's force the component to store images inside HTML document
// using base-64 encoding.
// Thus the component will not use HDD.
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
// Read a PDF document to byte array.
// Assume that we already have the PDF as array of bytes.
byte[] pdf = File.ReadAllBytes(pdfFile);
f.OpenPdf(pdf);
if (f.PageCount > 0)
{
// Convert PDF to HTML in memory
string htmlString = f.ToHtml(1, f.PageCount, imgCollection);
// Save HTML to a file only for the demonstration purpose.
if (htmlString != null)
{
// Show info about images and save them
Console.WriteLine("After converting we've got {0} image(s):", imgCollection.Count);
DirectoryInfo imgDir = new DirectoryInfo("Extracted Images");
if (!imgDir.Exists)
{
imgDir.Create();
}
int count = 1;
foreach (Image img in imgCollection)
{
Console.WriteLine("\t {0,4} x {1,4} px", img.Width, img.Height);
string imageFileName = Path.Combine(imgDir.FullName, String.Format($"pict{count}.jpg"));
img.Save(imageFileName, System.Drawing.Imaging.ImageFormat.Jpeg);
count++;
}
// Open the result for demonstration purposes.
File.WriteAllText(htmlFile, htmlString);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(htmlFile)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(imgDir.FullName)
{
UseShellExecute = true
});
}
}
}
public ActionResult UploadEdit(string[] FormatTags, string[] Pseudonyms, HttpPostedFileBase file, FormCollection form, [Bind(Include = "ProfileID, Title, LikesOn," +
"CommentsOn, CritiqueOn, DescriptionText")] Writing doc)
{
String FileExt = Path.GetExtension(file.FileName).ToUpper();
if (CheckExtEdit(FileExt))
{
AccessPermission ap = new AccessPermission()
{
PublicAccess = form["PublicAccess"] != null ? true : false,
FriendAccess = form["FriendAccess"] != null ? true : false,
PublisherAccess = form["PublisherAccess"] != null ? true : false,
MinorAccess = form["MinorAccess"] != null ? true : false
};
db.AccessPermissions.Add(ap);
db.SaveChanges();
if (!ModelState.IsValid)
{
Stream str = file.InputStream;
BinaryReader Br = new BinaryReader(str);
Byte[] FileData = Br.ReadBytes((Int32)str.Length);
string html = string.Empty;
string[] namestring = file.FileName.Split('.');
if (FileExt == ".PDF" || FileExt == "PDF")
{
SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();
f.OpenPdf(FileData);
if (f.PageCount > 0)
{
f.HtmlOptions.IncludeImageInHtml = true;
f.HtmlOptions.Title = "Simple text";
html = f.ToHtml();
}
}
else if (FileExt == ".DOCX" || FileExt == "DOCX" || FileExt == ".DOC" || FileExt == "DOC")
{
html = ConvertToHtml(Path.GetFullPath(file.FileName));
}
else
{
ViewBag.FileStatus = "Model Invalid";
return(View());
}
Writing wr = new Writing()
{
ProfileID = Int32.Parse(form["ProfileID"]),
AccessPermissionID = ap.AccessPermissionID,
Title = form["Title"],
AddDate = DateTime.Now,
EditDate = null,
LikesOn = form["LikesOn"] != null ? true : false,
CommentsOn = form["CommentsOn"] != null ? true : false,
CritiqueOn = form["CritiqueOn"] != null ? true : false,
UsePseudonymsInAdditionToUsername = form["UsePseudonymsInAdditionToUsername"] != null ? true : false,
DocType = ".HTML",
DescriptionText = form["DescriptionText"],
Document = Encoding.Unicode.GetBytes(html),
WritingFileName = namestring[0] + ".html"
};
db.Writings.Add(wr);
db.SaveChanges();
int id = wr.WritingID;
ap = db.AccessPermissions.Find(ap.AccessPermissionID);
ap.WritingID = id;
db.Entry(ap).State = EntityState.Modified;
db.SaveChanges();
if (FormatTags != null)
{
foreach (var selection in FormatTags)
{
WritingFormat wf = new WritingFormat()
{
WritingID = id,
FormatID = Int32.Parse(selection)
};
db.WritingFormats.Add(wf);
db.SaveChanges();
}
}
if (Pseudonyms != null)
{
foreach (var selection in Pseudonyms)
{
WritingPseudonym wp = new WritingPseudonym()
{
WritingID = id,
PseudonymID = Int32.Parse(selection)
};
db.WritingPseudonyms.Add(wp);
db.SaveChanges();
}
}
return(RedirectToAction("Index", "Home", new { @id = id }));
}
else
{
ViewBag.FileStatus = "File Type Not valid: Valid file type for edit is currently .PDF";
return(View());
}
}
else
{
ViewBag.FileStatus = "Invalid file format.";
return(View());
}
}
